{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06519719347707686,
  "eval_steps": 500,
  "global_step": 2035,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003203793291256848,
      "grad_norm": 2697.9695951365356,
      "learning_rate": 2.910112359550562e-06,
      "loss": 2.1080955505371093,
      "step": 10
    },
    {
      "epoch": 0.0006407586582513696,
      "grad_norm": 150.28792394404246,
      "learning_rate": 3.921348314606742e-06,
      "loss": 1.051735782623291,
      "step": 20
    },
    {
      "epoch": 0.0009611379873770544,
      "grad_norm": 11.728004906904669,
      "learning_rate": 4.932584269662922e-06,
      "loss": 0.8452852249145508,
      "step": 30
    },
    {
      "epoch": 0.0012815173165027392,
      "grad_norm": 79.82045143025138,
      "learning_rate": 5.943820224719102e-06,
      "loss": 0.8374807357788085,
      "step": 40
    },
    {
      "epoch": 0.001601896645628424,
      "grad_norm": 15.487828868814473,
      "learning_rate": 6.955056179775282e-06,
      "loss": 0.8031275749206543,
      "step": 50
    },
    {
      "epoch": 0.0019222759747541088,
      "grad_norm": 26.189373840069653,
      "learning_rate": 7.966292134831462e-06,
      "loss": 0.7619327545166016,
      "step": 60
    },
    {
      "epoch": 0.002242655303879794,
      "grad_norm": 24.510054444181353,
      "learning_rate": 8.977528089887641e-06,
      "loss": 0.788119888305664,
      "step": 70
    },
    {
      "epoch": 0.0025630346330054784,
      "grad_norm": 27.619677813912134,
      "learning_rate": 9.988764044943822e-06,
      "loss": 0.8074554443359375,
      "step": 80
    },
    {
      "epoch": 0.0028834139621311634,
      "grad_norm": 53.27561070809039,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.7780509948730469,
      "step": 90
    },
    {
      "epoch": 0.003203793291256848,
      "grad_norm": 20.22293994140261,
      "learning_rate": 1.2011235955056182e-05,
      "loss": 0.7639347076416015,
      "step": 100
    },
    {
      "epoch": 0.003524172620382533,
      "grad_norm": 28.55291130912943,
      "learning_rate": 1.3022471910112362e-05,
      "loss": 0.7700469970703125,
      "step": 110
    },
    {
      "epoch": 0.0038445519495082176,
      "grad_norm": 7.520305767933223,
      "learning_rate": 1.403370786516854e-05,
      "loss": 0.7953043937683105,
      "step": 120
    },
    {
      "epoch": 0.004164931278633903,
      "grad_norm": 96.08078842951305,
      "learning_rate": 1.504494382022472e-05,
      "loss": 0.8506025314331055,
      "step": 130
    },
    {
      "epoch": 0.004485310607759588,
      "grad_norm": 948.131373093307,
      "learning_rate": 1.60561797752809e-05,
      "loss": 0.8122509002685547,
      "step": 140
    },
    {
      "epoch": 0.004805689936885272,
      "grad_norm": 128.55037969805156,
      "learning_rate": 1.706741573033708e-05,
      "loss": 0.7938695907592773,
      "step": 150
    },
    {
      "epoch": 0.005126069266010957,
      "grad_norm": 25.93618158094234,
      "learning_rate": 1.8078651685393256e-05,
      "loss": 0.8438175201416016,
      "step": 160
    },
    {
      "epoch": 0.005446448595136642,
      "grad_norm": 9.528266971779534,
      "learning_rate": 1.908988764044944e-05,
      "loss": 0.9011789321899414,
      "step": 170
    },
    {
      "epoch": 0.005766827924262327,
      "grad_norm": 4.6353029582495315,
      "learning_rate": 2e-05,
      "loss": 0.8190475463867187,
      "step": 180
    },
    {
      "epoch": 0.006087207253388012,
      "grad_norm": 7.804600561994388,
      "learning_rate": 2e-05,
      "loss": 0.7879319667816163,
      "step": 190
    },
    {
      "epoch": 0.006407586582513696,
      "grad_norm": 8.759193053432988,
      "learning_rate": 2e-05,
      "loss": 0.8373113632202148,
      "step": 200
    },
    {
      "epoch": 0.006727965911639381,
      "grad_norm": 5.7645630188571495,
      "learning_rate": 2e-05,
      "loss": 0.8225456237792969,
      "step": 210
    },
    {
      "epoch": 0.007048345240765066,
      "grad_norm": 2.975476645382291,
      "learning_rate": 2e-05,
      "loss": 0.7898527145385742,
      "step": 220
    },
    {
      "epoch": 0.007368724569890751,
      "grad_norm": 3.5660713690110923,
      "learning_rate": 2e-05,
      "loss": 0.7848415374755859,
      "step": 230
    },
    {
      "epoch": 0.007689103899016435,
      "grad_norm": 3.776542520178389,
      "learning_rate": 2e-05,
      "loss": 0.7830493927001954,
      "step": 240
    },
    {
      "epoch": 0.008009483228142121,
      "grad_norm": 5.652886706438173,
      "learning_rate": 2e-05,
      "loss": 0.7420679092407226,
      "step": 250
    },
    {
      "epoch": 0.008329862557267805,
      "grad_norm": 2.7433625896377887,
      "learning_rate": 2e-05,
      "loss": 0.8062055587768555,
      "step": 260
    },
    {
      "epoch": 0.00865024188639349,
      "grad_norm": 4.993469336501579,
      "learning_rate": 2e-05,
      "loss": 0.7772369384765625,
      "step": 270
    },
    {
      "epoch": 0.008970621215519175,
      "grad_norm": 5.978072597304008,
      "learning_rate": 2e-05,
      "loss": 0.7567183494567871,
      "step": 280
    },
    {
      "epoch": 0.00929100054464486,
      "grad_norm": 20.0019916771175,
      "learning_rate": 2e-05,
      "loss": 0.7632350921630859,
      "step": 290
    },
    {
      "epoch": 0.009611379873770544,
      "grad_norm": 1813.803400221406,
      "learning_rate": 2e-05,
      "loss": 0.7820405006408692,
      "step": 300
    },
    {
      "epoch": 0.00993175920289623,
      "grad_norm": 15.257478921571794,
      "learning_rate": 2e-05,
      "loss": 0.8594757080078125,
      "step": 310
    },
    {
      "epoch": 0.010252138532021914,
      "grad_norm": 26.97548621262987,
      "learning_rate": 2e-05,
      "loss": 0.8610923767089844,
      "step": 320
    },
    {
      "epoch": 0.0105725178611476,
      "grad_norm": 21.892790276243126,
      "learning_rate": 2e-05,
      "loss": 0.8686389923095703,
      "step": 330
    },
    {
      "epoch": 0.010892897190273284,
      "grad_norm": 16.06260184223094,
      "learning_rate": 2e-05,
      "loss": 0.8639827728271484,
      "step": 340
    },
    {
      "epoch": 0.011213276519398968,
      "grad_norm": 29.260614803206966,
      "learning_rate": 2e-05,
      "loss": 0.7904685497283935,
      "step": 350
    },
    {
      "epoch": 0.011533655848524654,
      "grad_norm": 16.44688311222318,
      "learning_rate": 2e-05,
      "loss": 0.8587644577026368,
      "step": 360
    },
    {
      "epoch": 0.011854035177650338,
      "grad_norm": 70.37237245987374,
      "learning_rate": 2e-05,
      "loss": 0.8287432670593262,
      "step": 370
    },
    {
      "epoch": 0.012174414506776024,
      "grad_norm": 7.352519778805397,
      "learning_rate": 2e-05,
      "loss": 0.8243340492248535,
      "step": 380
    },
    {
      "epoch": 0.012494793835901708,
      "grad_norm": 7.57180002114558,
      "learning_rate": 2e-05,
      "loss": 0.8488252639770508,
      "step": 390
    },
    {
      "epoch": 0.012815173165027392,
      "grad_norm": 4.028963614155682,
      "learning_rate": 2e-05,
      "loss": 0.800967788696289,
      "step": 400
    },
    {
      "epoch": 0.013135552494153078,
      "grad_norm": 7.604607607710578,
      "learning_rate": 2e-05,
      "loss": 0.8435401916503906,
      "step": 410
    },
    {
      "epoch": 0.013455931823278762,
      "grad_norm": 5.686576942826079,
      "learning_rate": 2e-05,
      "loss": 0.8086394309997559,
      "step": 420
    },
    {
      "epoch": 0.013776311152404446,
      "grad_norm": 29.16934098168494,
      "learning_rate": 2e-05,
      "loss": 0.8092558860778809,
      "step": 430
    },
    {
      "epoch": 0.014096690481530132,
      "grad_norm": 7.838527647928418,
      "learning_rate": 2e-05,
      "loss": 0.7873313903808594,
      "step": 440
    },
    {
      "epoch": 0.014417069810655816,
      "grad_norm": 4.360151373268049,
      "learning_rate": 2e-05,
      "loss": 0.8105262756347656,
      "step": 450
    },
    {
      "epoch": 0.014737449139781502,
      "grad_norm": 3.093592672180748,
      "learning_rate": 2e-05,
      "loss": 0.7954371452331543,
      "step": 460
    },
    {
      "epoch": 0.015057828468907186,
      "grad_norm": 2.8867780320165948,
      "learning_rate": 2e-05,
      "loss": 0.7867568969726563,
      "step": 470
    },
    {
      "epoch": 0.01537820779803287,
      "grad_norm": 2.5525945956595404,
      "learning_rate": 2e-05,
      "loss": 0.7605972290039062,
      "step": 480
    },
    {
      "epoch": 0.015698587127158554,
      "grad_norm": 4.350350397516954,
      "learning_rate": 2e-05,
      "loss": 0.7946616172790527,
      "step": 490
    },
    {
      "epoch": 0.016018966456284242,
      "grad_norm": 2.5601326184252624,
      "learning_rate": 2e-05,
      "loss": 0.7657347679138183,
      "step": 500
    },
    {
      "epoch": 0.016339345785409926,
      "grad_norm": 3.0411596315285943,
      "learning_rate": 2e-05,
      "loss": 0.7469792366027832,
      "step": 510
    },
    {
      "epoch": 0.01665972511453561,
      "grad_norm": 1.6677799044175043,
      "learning_rate": 2e-05,
      "loss": 0.737004280090332,
      "step": 520
    },
    {
      "epoch": 0.016980104443661295,
      "grad_norm": 4.326231014259539,
      "learning_rate": 2e-05,
      "loss": 0.7799790859222412,
      "step": 530
    },
    {
      "epoch": 0.01730048377278698,
      "grad_norm": 2.732975416289203,
      "learning_rate": 2e-05,
      "loss": 0.8164985656738282,
      "step": 540
    },
    {
      "epoch": 0.017620863101912666,
      "grad_norm": 2.1962459439491036,
      "learning_rate": 2e-05,
      "loss": 0.7743217468261718,
      "step": 550
    },
    {
      "epoch": 0.01794124243103835,
      "grad_norm": 4.329667095154606,
      "learning_rate": 2e-05,
      "loss": 0.8150390625,
      "step": 560
    },
    {
      "epoch": 0.018261621760164035,
      "grad_norm": 1.7505089770107007,
      "learning_rate": 2e-05,
      "loss": 0.8161712646484375,
      "step": 570
    },
    {
      "epoch": 0.01858200108928972,
      "grad_norm": 1.94080520422082,
      "learning_rate": 2e-05,
      "loss": 0.7340856075286866,
      "step": 580
    },
    {
      "epoch": 0.018902380418415403,
      "grad_norm": 3.767043072114596,
      "learning_rate": 2e-05,
      "loss": 0.7465179443359375,
      "step": 590
    },
    {
      "epoch": 0.019222759747541087,
      "grad_norm": 2.134739515696804,
      "learning_rate": 2e-05,
      "loss": 0.7511123657226563,
      "step": 600
    },
    {
      "epoch": 0.019543139076666775,
      "grad_norm": 2.6553715328436724,
      "learning_rate": 2e-05,
      "loss": 0.7474520683288575,
      "step": 610
    },
    {
      "epoch": 0.01986351840579246,
      "grad_norm": 23.554705629944248,
      "learning_rate": 2e-05,
      "loss": 0.7547467708587646,
      "step": 620
    },
    {
      "epoch": 0.020183897734918143,
      "grad_norm": 9.663715178820514,
      "learning_rate": 2e-05,
      "loss": 0.7591798782348633,
      "step": 630
    },
    {
      "epoch": 0.020504277064043827,
      "grad_norm": 2.857655614152204,
      "learning_rate": 2e-05,
      "loss": 0.7372615814208985,
      "step": 640
    },
    {
      "epoch": 0.02082465639316951,
      "grad_norm": 19.794443617215876,
      "learning_rate": 2e-05,
      "loss": 0.7473020076751709,
      "step": 650
    },
    {
      "epoch": 0.0211450357222952,
      "grad_norm": 3.4519708452708513,
      "learning_rate": 2e-05,
      "loss": 0.7669941902160644,
      "step": 660
    },
    {
      "epoch": 0.021465415051420883,
      "grad_norm": 4.439475537657204,
      "learning_rate": 2e-05,
      "loss": 0.7708707809448242,
      "step": 670
    },
    {
      "epoch": 0.021785794380546567,
      "grad_norm": 4.288236090232602,
      "learning_rate": 2e-05,
      "loss": 0.75105299949646,
      "step": 680
    },
    {
      "epoch": 0.02210617370967225,
      "grad_norm": 19.247483032059645,
      "learning_rate": 2e-05,
      "loss": 0.7456221580505371,
      "step": 690
    },
    {
      "epoch": 0.022426553038797935,
      "grad_norm": 6.277608344095431,
      "learning_rate": 2e-05,
      "loss": 0.772921371459961,
      "step": 700
    },
    {
      "epoch": 0.022746932367923623,
      "grad_norm": 3.5768536610883284,
      "learning_rate": 2e-05,
      "loss": 0.7416125297546386,
      "step": 710
    },
    {
      "epoch": 0.023067311697049307,
      "grad_norm": 15.05269132810213,
      "learning_rate": 2e-05,
      "loss": 0.7103744506835937,
      "step": 720
    },
    {
      "epoch": 0.02338769102617499,
      "grad_norm": 4.468376174246059,
      "learning_rate": 2e-05,
      "loss": 0.727785873413086,
      "step": 730
    },
    {
      "epoch": 0.023708070355300676,
      "grad_norm": 5.087071299517523,
      "learning_rate": 2e-05,
      "loss": 0.7700984477996826,
      "step": 740
    },
    {
      "epoch": 0.02402844968442636,
      "grad_norm": 11.288253253171709,
      "learning_rate": 2e-05,
      "loss": 0.7581868648529053,
      "step": 750
    },
    {
      "epoch": 0.024348829013552047,
      "grad_norm": 3.27468779155936,
      "learning_rate": 2e-05,
      "loss": 0.7562522888183594,
      "step": 760
    },
    {
      "epoch": 0.02466920834267773,
      "grad_norm": 7.595749246101231,
      "learning_rate": 2e-05,
      "loss": 0.7546162605285645,
      "step": 770
    },
    {
      "epoch": 0.024989587671803416,
      "grad_norm": 2.1701956042711728,
      "learning_rate": 2e-05,
      "loss": 0.7503818511962891,
      "step": 780
    },
    {
      "epoch": 0.0253099670009291,
      "grad_norm": 7.551313750149006,
      "learning_rate": 2e-05,
      "loss": 0.7194967269897461,
      "step": 790
    },
    {
      "epoch": 0.025630346330054784,
      "grad_norm": 3.0982279258014085,
      "learning_rate": 2e-05,
      "loss": 0.7183728218078613,
      "step": 800
    },
    {
      "epoch": 0.025950725659180468,
      "grad_norm": 2.2319456779746507,
      "learning_rate": 2e-05,
      "loss": 0.741051197052002,
      "step": 810
    },
    {
      "epoch": 0.026271104988306156,
      "grad_norm": 2.1272967612583904,
      "learning_rate": 2e-05,
      "loss": 0.7074191093444824,
      "step": 820
    },
    {
      "epoch": 0.02659148431743184,
      "grad_norm": 2.3756745796722125,
      "learning_rate": 2e-05,
      "loss": 0.7466435909271241,
      "step": 830
    },
    {
      "epoch": 0.026911863646557524,
      "grad_norm": 3.9008908753860925,
      "learning_rate": 2e-05,
      "loss": 0.7262076377868653,
      "step": 840
    },
    {
      "epoch": 0.027232242975683208,
      "grad_norm": 2.0561831766929806,
      "learning_rate": 2e-05,
      "loss": 0.7282081604003906,
      "step": 850
    },
    {
      "epoch": 0.027552622304808892,
      "grad_norm": 5.818198655017998,
      "learning_rate": 2e-05,
      "loss": 0.7566670894622802,
      "step": 860
    },
    {
      "epoch": 0.02787300163393458,
      "grad_norm": 2.1494490230827337,
      "learning_rate": 2e-05,
      "loss": 0.7288908958435059,
      "step": 870
    },
    {
      "epoch": 0.028193380963060264,
      "grad_norm": 1.409242496714709,
      "learning_rate": 2e-05,
      "loss": 0.7215320587158203,
      "step": 880
    },
    {
      "epoch": 0.028513760292185948,
      "grad_norm": 7.0920590147047164,
      "learning_rate": 2e-05,
      "loss": 0.7246700286865234,
      "step": 890
    },
    {
      "epoch": 0.028834139621311632,
      "grad_norm": 1.5684095793164903,
      "learning_rate": 2e-05,
      "loss": 0.7144109725952148,
      "step": 900
    },
    {
      "epoch": 0.029154518950437316,
      "grad_norm": 1.3316395400018082,
      "learning_rate": 2e-05,
      "loss": 0.7477982997894287,
      "step": 910
    },
    {
      "epoch": 0.029474898279563004,
      "grad_norm": 1.3602729023468434,
      "learning_rate": 2e-05,
      "loss": 0.7173037528991699,
      "step": 920
    },
    {
      "epoch": 0.029795277608688688,
      "grad_norm": 49.53643391306756,
      "learning_rate": 2e-05,
      "loss": 0.7678704738616944,
      "step": 930
    },
    {
      "epoch": 0.030115656937814372,
      "grad_norm": 4.340394359223178,
      "learning_rate": 2e-05,
      "loss": 0.7031218528747558,
      "step": 940
    },
    {
      "epoch": 0.030436036266940057,
      "grad_norm": 2.1203555620583736,
      "learning_rate": 2e-05,
      "loss": 0.7084536552429199,
      "step": 950
    },
    {
      "epoch": 0.03075641559606574,
      "grad_norm": 1.3371075573755178,
      "learning_rate": 2e-05,
      "loss": 0.7464202880859375,
      "step": 960
    },
    {
      "epoch": 0.03107679492519143,
      "grad_norm": 1.6473009838115498,
      "learning_rate": 2e-05,
      "loss": 0.7116725444793701,
      "step": 970
    },
    {
      "epoch": 0.03139717425431711,
      "grad_norm": 3.385121877804678,
      "learning_rate": 2e-05,
      "loss": 0.738076114654541,
      "step": 980
    },
    {
      "epoch": 0.0317175535834428,
      "grad_norm": 1.7147230699245448,
      "learning_rate": 2e-05,
      "loss": 0.7158563137054443,
      "step": 990
    },
    {
      "epoch": 0.032037932912568484,
      "grad_norm": 3.3445220753393468,
      "learning_rate": 2e-05,
      "loss": 0.8030566215515137,
      "step": 1000
    },
    {
      "epoch": 0.032358312241694165,
      "grad_norm": 2.077502109986157,
      "learning_rate": 2e-05,
      "loss": 0.7472703456878662,
      "step": 1010
    },
    {
      "epoch": 0.03267869157081985,
      "grad_norm": 17.329143506946714,
      "learning_rate": 2e-05,
      "loss": 0.7366230964660645,
      "step": 1020
    },
    {
      "epoch": 0.03299907089994553,
      "grad_norm": 2.6268238025254735,
      "learning_rate": 2e-05,
      "loss": 0.7404189109802246,
      "step": 1030
    },
    {
      "epoch": 0.03331945022907122,
      "grad_norm": 1.977866371730136,
      "learning_rate": 2e-05,
      "loss": 0.7236545085906982,
      "step": 1040
    },
    {
      "epoch": 0.03363982955819691,
      "grad_norm": 1.498659413315871,
      "learning_rate": 2e-05,
      "loss": 0.7335420608520508,
      "step": 1050
    },
    {
      "epoch": 0.03396020888732259,
      "grad_norm": 1.7062214656423396,
      "learning_rate": 2e-05,
      "loss": 0.7051788330078125,
      "step": 1060
    },
    {
      "epoch": 0.03428058821644828,
      "grad_norm": 1.3397922877558162,
      "learning_rate": 2e-05,
      "loss": 0.7626142024993896,
      "step": 1070
    },
    {
      "epoch": 0.03460096754557396,
      "grad_norm": 3.93050291862445,
      "learning_rate": 2e-05,
      "loss": 0.7514806270599366,
      "step": 1080
    },
    {
      "epoch": 0.034921346874699645,
      "grad_norm": 3.398990137450838,
      "learning_rate": 2e-05,
      "loss": 0.7132882595062255,
      "step": 1090
    },
    {
      "epoch": 0.03524172620382533,
      "grad_norm": 1.4600798546048035,
      "learning_rate": 2e-05,
      "loss": 0.716385793685913,
      "step": 1100
    },
    {
      "epoch": 0.03556210553295101,
      "grad_norm": 1.3160301135986112,
      "learning_rate": 2e-05,
      "loss": 0.7191272735595703,
      "step": 1110
    },
    {
      "epoch": 0.0358824848620767,
      "grad_norm": 1.2481731524679547,
      "learning_rate": 2e-05,
      "loss": 0.7158429145812988,
      "step": 1120
    },
    {
      "epoch": 0.03620286419120238,
      "grad_norm": 2.8179317711592504,
      "learning_rate": 2e-05,
      "loss": 0.7038905143737793,
      "step": 1130
    },
    {
      "epoch": 0.03652324352032807,
      "grad_norm": 1.8284267025580432,
      "learning_rate": 2e-05,
      "loss": 0.7065417289733886,
      "step": 1140
    },
    {
      "epoch": 0.03684362284945375,
      "grad_norm": 2.212892645914091,
      "learning_rate": 2e-05,
      "loss": 0.7265023708343505,
      "step": 1150
    },
    {
      "epoch": 0.03716400217857944,
      "grad_norm": 2.2597923858522404,
      "learning_rate": 2e-05,
      "loss": 0.7199366569519043,
      "step": 1160
    },
    {
      "epoch": 0.037484381507705125,
      "grad_norm": 2.0160695548330936,
      "learning_rate": 2e-05,
      "loss": 0.7658578395843506,
      "step": 1170
    },
    {
      "epoch": 0.037804760836830806,
      "grad_norm": 2.5572488896871843,
      "learning_rate": 2e-05,
      "loss": 0.7220034599304199,
      "step": 1180
    },
    {
      "epoch": 0.03812514016595649,
      "grad_norm": 2.459122478774182,
      "learning_rate": 2e-05,
      "loss": 0.6983201026916503,
      "step": 1190
    },
    {
      "epoch": 0.038445519495082174,
      "grad_norm": 5.318818273924634,
      "learning_rate": 2e-05,
      "loss": 0.7152614116668701,
      "step": 1200
    },
    {
      "epoch": 0.03876589882420786,
      "grad_norm": 4.348661337562832,
      "learning_rate": 2e-05,
      "loss": 0.7531236171722412,
      "step": 1210
    },
    {
      "epoch": 0.03908627815333355,
      "grad_norm": 3.5073096880649666,
      "learning_rate": 2e-05,
      "loss": 0.7070003509521484,
      "step": 1220
    },
    {
      "epoch": 0.03940665748245923,
      "grad_norm": 6.250765626260255,
      "learning_rate": 2e-05,
      "loss": 0.7422648429870605,
      "step": 1230
    },
    {
      "epoch": 0.03972703681158492,
      "grad_norm": 2.1134272476858693,
      "learning_rate": 2e-05,
      "loss": 0.7167387962341308,
      "step": 1240
    },
    {
      "epoch": 0.0400474161407106,
      "grad_norm": 2.728613864385018,
      "learning_rate": 2e-05,
      "loss": 0.7613626480102539,
      "step": 1250
    },
    {
      "epoch": 0.040367795469836286,
      "grad_norm": 2.8289243765180094,
      "learning_rate": 2e-05,
      "loss": 0.7406154155731202,
      "step": 1260
    },
    {
      "epoch": 0.040688174798961974,
      "grad_norm": 1.460978022101602,
      "learning_rate": 2e-05,
      "loss": 0.7171460628509522,
      "step": 1270
    },
    {
      "epoch": 0.041008554128087654,
      "grad_norm": 11.187948658326427,
      "learning_rate": 2e-05,
      "loss": 0.7119218349456787,
      "step": 1280
    },
    {
      "epoch": 0.04132893345721334,
      "grad_norm": 1.5366780655953838,
      "learning_rate": 2e-05,
      "loss": 0.7250003337860107,
      "step": 1290
    },
    {
      "epoch": 0.04164931278633902,
      "grad_norm": 2.6451401695263392,
      "learning_rate": 2e-05,
      "loss": 0.7535340785980225,
      "step": 1300
    },
    {
      "epoch": 0.04196969211546471,
      "grad_norm": 5.247231775991024,
      "learning_rate": 2e-05,
      "loss": 0.7120182991027832,
      "step": 1310
    },
    {
      "epoch": 0.0422900714445904,
      "grad_norm": 1.265414487137248,
      "learning_rate": 2e-05,
      "loss": 0.7114714622497559,
      "step": 1320
    },
    {
      "epoch": 0.04261045077371608,
      "grad_norm": 32.52328999465322,
      "learning_rate": 2e-05,
      "loss": 0.6845267295837403,
      "step": 1330
    },
    {
      "epoch": 0.042930830102841766,
      "grad_norm": 6.1768247607509394,
      "learning_rate": 2e-05,
      "loss": 0.702857780456543,
      "step": 1340
    },
    {
      "epoch": 0.04325120943196745,
      "grad_norm": 7.1933410968196725,
      "learning_rate": 2e-05,
      "loss": 0.72010817527771,
      "step": 1350
    },
    {
      "epoch": 0.043571588761093134,
      "grad_norm": 1.1755562476246728,
      "learning_rate": 2e-05,
      "loss": 0.6978877067565918,
      "step": 1360
    },
    {
      "epoch": 0.04389196809021882,
      "grad_norm": 2.8540830213502844,
      "learning_rate": 2e-05,
      "loss": 0.7204657554626465,
      "step": 1370
    },
    {
      "epoch": 0.0442123474193445,
      "grad_norm": 1.1871852286932287,
      "learning_rate": 2e-05,
      "loss": 0.7182430267333985,
      "step": 1380
    },
    {
      "epoch": 0.04453272674847019,
      "grad_norm": 1.0566209393736636,
      "learning_rate": 2e-05,
      "loss": 0.7123696804046631,
      "step": 1390
    },
    {
      "epoch": 0.04485310607759587,
      "grad_norm": 4.237024261846737,
      "learning_rate": 2e-05,
      "loss": 0.6963154792785644,
      "step": 1400
    },
    {
      "epoch": 0.04517348540672156,
      "grad_norm": 2.008976090493564,
      "learning_rate": 2e-05,
      "loss": 0.6849660396575927,
      "step": 1410
    },
    {
      "epoch": 0.045493864735847246,
      "grad_norm": 1.3493113476458192,
      "learning_rate": 2e-05,
      "loss": 0.7087863922119141,
      "step": 1420
    },
    {
      "epoch": 0.04581424406497293,
      "grad_norm": 1.0453265260241618,
      "learning_rate": 2e-05,
      "loss": 0.6820076942443848,
      "step": 1430
    },
    {
      "epoch": 0.046134623394098614,
      "grad_norm": 1.367769743280532,
      "learning_rate": 2e-05,
      "loss": 0.7149313926696778,
      "step": 1440
    },
    {
      "epoch": 0.046455002723224295,
      "grad_norm": 1.5424097504581287,
      "learning_rate": 2e-05,
      "loss": 0.7253753185272217,
      "step": 1450
    },
    {
      "epoch": 0.04677538205234998,
      "grad_norm": 2.3372729347553025,
      "learning_rate": 2e-05,
      "loss": 0.7671535015106201,
      "step": 1460
    },
    {
      "epoch": 0.04709576138147567,
      "grad_norm": 1.8742828809078558,
      "learning_rate": 2e-05,
      "loss": 0.7182416915893555,
      "step": 1470
    },
    {
      "epoch": 0.04741614071060135,
      "grad_norm": 6.87172572472952,
      "learning_rate": 2e-05,
      "loss": 0.7154425621032715,
      "step": 1480
    },
    {
      "epoch": 0.04773652003972704,
      "grad_norm": 2.4729840403642545,
      "learning_rate": 2e-05,
      "loss": 0.7049578666687012,
      "step": 1490
    },
    {
      "epoch": 0.04805689936885272,
      "grad_norm": 1.3804743410158802,
      "learning_rate": 2e-05,
      "loss": 0.7238261222839355,
      "step": 1500
    },
    {
      "epoch": 0.04837727869797841,
      "grad_norm": 1.2556616325656202,
      "learning_rate": 2e-05,
      "loss": 0.7582721710205078,
      "step": 1510
    },
    {
      "epoch": 0.048697658027104095,
      "grad_norm": 1.4068662819395166,
      "learning_rate": 2e-05,
      "loss": 0.6943454742431641,
      "step": 1520
    },
    {
      "epoch": 0.049018037356229775,
      "grad_norm": 1.5191574570193485,
      "learning_rate": 2e-05,
      "loss": 0.7089879512786865,
      "step": 1530
    },
    {
      "epoch": 0.04933841668535546,
      "grad_norm": 1.1100647663489502,
      "learning_rate": 2e-05,
      "loss": 0.6814855098724365,
      "step": 1540
    },
    {
      "epoch": 0.049658796014481144,
      "grad_norm": 1.2368089337986163,
      "learning_rate": 2e-05,
      "loss": 0.7276053428649902,
      "step": 1550
    },
    {
      "epoch": 0.04997917534360683,
      "grad_norm": 1.596887157213148,
      "learning_rate": 2e-05,
      "loss": 0.7387615203857422,
      "step": 1560
    },
    {
      "epoch": 0.05029955467273251,
      "grad_norm": 1.3857783026385584,
      "learning_rate": 2e-05,
      "loss": 0.6814603805541992,
      "step": 1570
    },
    {
      "epoch": 0.0506199340018582,
      "grad_norm": 1.5717792680161595,
      "learning_rate": 2e-05,
      "loss": 0.6634132385253906,
      "step": 1580
    },
    {
      "epoch": 0.05094031333098389,
      "grad_norm": 5.076622025769138,
      "learning_rate": 2e-05,
      "loss": 0.7170121669769287,
      "step": 1590
    },
    {
      "epoch": 0.05126069266010957,
      "grad_norm": 3.075120261257635,
      "learning_rate": 2e-05,
      "loss": 0.6901824951171875,
      "step": 1600
    },
    {
      "epoch": 0.051581071989235255,
      "grad_norm": 3.1443073556392838,
      "learning_rate": 2e-05,
      "loss": 0.7126097679138184,
      "step": 1610
    },
    {
      "epoch": 0.051901451318360936,
      "grad_norm": 1.3279065854265553,
      "learning_rate": 2e-05,
      "loss": 0.696572208404541,
      "step": 1620
    },
    {
      "epoch": 0.052221830647486624,
      "grad_norm": 2.2922495579972213,
      "learning_rate": 2e-05,
      "loss": 0.7236587047576905,
      "step": 1630
    },
    {
      "epoch": 0.05254220997661231,
      "grad_norm": 1.853599288786833,
      "learning_rate": 2e-05,
      "loss": 0.6959040641784668,
      "step": 1640
    },
    {
      "epoch": 0.05286258930573799,
      "grad_norm": 1.6356938422959257,
      "learning_rate": 2e-05,
      "loss": 0.6883045196533203,
      "step": 1650
    },
    {
      "epoch": 0.05318296863486368,
      "grad_norm": 1.4258158618988481,
      "learning_rate": 2e-05,
      "loss": 0.7095949172973632,
      "step": 1660
    },
    {
      "epoch": 0.05350334796398936,
      "grad_norm": 1.3818626048983265,
      "learning_rate": 2e-05,
      "loss": 0.7279641628265381,
      "step": 1670
    },
    {
      "epoch": 0.05382372729311505,
      "grad_norm": 1.3148725391903133,
      "learning_rate": 2e-05,
      "loss": 0.7071706295013428,
      "step": 1680
    },
    {
      "epoch": 0.054144106622240736,
      "grad_norm": 1.3205843385485543,
      "learning_rate": 2e-05,
      "loss": 0.7102875709533691,
      "step": 1690
    },
    {
      "epoch": 0.054464485951366416,
      "grad_norm": 1.0245118537391376,
      "learning_rate": 2e-05,
      "loss": 0.7355536460876465,
      "step": 1700
    },
    {
      "epoch": 0.054784865280492104,
      "grad_norm": 0.9830319826014532,
      "learning_rate": 2e-05,
      "loss": 0.711072301864624,
      "step": 1710
    },
    {
      "epoch": 0.055105244609617784,
      "grad_norm": 2.2427073223135,
      "learning_rate": 2e-05,
      "loss": 0.7257272720336914,
      "step": 1720
    },
    {
      "epoch": 0.05542562393874347,
      "grad_norm": 1.7432652030049554,
      "learning_rate": 2e-05,
      "loss": 0.7266391754150391,
      "step": 1730
    },
    {
      "epoch": 0.05574600326786916,
      "grad_norm": 7.3855085380936965,
      "learning_rate": 2e-05,
      "loss": 0.7229394435882568,
      "step": 1740
    },
    {
      "epoch": 0.05606638259699484,
      "grad_norm": 2.1417039515536542,
      "learning_rate": 2e-05,
      "loss": 0.6833599090576172,
      "step": 1750
    },
    {
      "epoch": 0.05638676192612053,
      "grad_norm": 2.4468519837946165,
      "learning_rate": 2e-05,
      "loss": 0.7663132667541503,
      "step": 1760
    },
    {
      "epoch": 0.05670714125524621,
      "grad_norm": 3.0137174378050293,
      "learning_rate": 2e-05,
      "loss": 0.7224421977996827,
      "step": 1770
    },
    {
      "epoch": 0.057027520584371896,
      "grad_norm": 2.2523438896707706,
      "learning_rate": 2e-05,
      "loss": 0.7207423210144043,
      "step": 1780
    },
    {
      "epoch": 0.057347899913497584,
      "grad_norm": 2.919705865322085,
      "learning_rate": 2e-05,
      "loss": 0.6854898452758789,
      "step": 1790
    },
    {
      "epoch": 0.057668279242623265,
      "grad_norm": 3.984396788478948,
      "learning_rate": 2e-05,
      "loss": 0.7234033107757568,
      "step": 1800
    },
    {
      "epoch": 0.05798865857174895,
      "grad_norm": 6.67851094941151,
      "learning_rate": 2e-05,
      "loss": 0.7022351264953614,
      "step": 1810
    },
    {
      "epoch": 0.05830903790087463,
      "grad_norm": 1.6866126836675677,
      "learning_rate": 2e-05,
      "loss": 0.7415154457092286,
      "step": 1820
    },
    {
      "epoch": 0.05862941723000032,
      "grad_norm": 3.218820869797509,
      "learning_rate": 2e-05,
      "loss": 0.7005694389343262,
      "step": 1830
    },
    {
      "epoch": 0.05894979655912601,
      "grad_norm": 3.0737908739781106,
      "learning_rate": 2e-05,
      "loss": 0.6981851100921631,
      "step": 1840
    },
    {
      "epoch": 0.05927017588825169,
      "grad_norm": 2.2327032848527795,
      "learning_rate": 2e-05,
      "loss": 0.7604454040527344,
      "step": 1850
    },
    {
      "epoch": 0.059590555217377376,
      "grad_norm": 2.8761311961580973,
      "learning_rate": 2e-05,
      "loss": 0.6888795852661133,
      "step": 1860
    },
    {
      "epoch": 0.05991093454650306,
      "grad_norm": 2.2317201691382533,
      "learning_rate": 2e-05,
      "loss": 0.708838415145874,
      "step": 1870
    },
    {
      "epoch": 0.060231313875628745,
      "grad_norm": 2.0355186191234806,
      "learning_rate": 2e-05,
      "loss": 0.7040927886962891,
      "step": 1880
    },
    {
      "epoch": 0.06055169320475443,
      "grad_norm": 2.014047361446366,
      "learning_rate": 2e-05,
      "loss": 0.7197917461395263,
      "step": 1890
    },
    {
      "epoch": 0.06087207253388011,
      "grad_norm": 1.977104681851146,
      "learning_rate": 2e-05,
      "loss": 0.6776611328125,
      "step": 1900
    },
    {
      "epoch": 0.0611924518630058,
      "grad_norm": 13.901447338457938,
      "learning_rate": 2e-05,
      "loss": 0.6899932861328125,
      "step": 1910
    },
    {
      "epoch": 0.06151283119213148,
      "grad_norm": 2.1123993495266435,
      "learning_rate": 2e-05,
      "loss": 0.6683700084686279,
      "step": 1920
    },
    {
      "epoch": 0.06183321052125717,
      "grad_norm": 2.3306798040564676,
      "learning_rate": 2e-05,
      "loss": 0.691620922088623,
      "step": 1930
    },
    {
      "epoch": 0.06215358985038286,
      "grad_norm": 13.395393364218384,
      "learning_rate": 2e-05,
      "loss": 0.7234976768493653,
      "step": 1940
    },
    {
      "epoch": 0.06247396917950854,
      "grad_norm": 7.087449907589583,
      "learning_rate": 2e-05,
      "loss": 0.7050728797912598,
      "step": 1950
    },
    {
      "epoch": 0.06279434850863422,
      "grad_norm": 2.912496650205425,
      "learning_rate": 2e-05,
      "loss": 0.6966752529144287,
      "step": 1960
    },
    {
      "epoch": 0.06311472783775991,
      "grad_norm": 8.623415554665941,
      "learning_rate": 2e-05,
      "loss": 0.67595534324646,
      "step": 1970
    },
    {
      "epoch": 0.0634351071668856,
      "grad_norm": 3.239938193275378,
      "learning_rate": 2e-05,
      "loss": 0.6972695350646972,
      "step": 1980
    },
    {
      "epoch": 0.06375548649601127,
      "grad_norm": 4.165992500546785,
      "learning_rate": 2e-05,
      "loss": 0.7464128017425538,
      "step": 1990
    },
    {
      "epoch": 0.06407586582513697,
      "grad_norm": 3.308146075178026,
      "learning_rate": 2e-05,
      "loss": 0.7509006023406982,
      "step": 2000
    },
    {
      "epoch": 0.06439624515426265,
      "grad_norm": 3.4969526861271802,
      "learning_rate": 2e-05,
      "loss": 0.7300586700439453,
      "step": 2010
    },
    {
      "epoch": 0.06471662448338833,
      "grad_norm": 4.743378784447764,
      "learning_rate": 2e-05,
      "loss": 0.6886860847473144,
      "step": 2020
    },
    {
      "epoch": 0.06503700381251401,
      "grad_norm": 1.9438372463888733,
      "learning_rate": 2e-05,
      "loss": 0.705808448791504,
      "step": 2030
    }
  ],
  "logging_steps": 10,
  "max_steps": 5935,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2035,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 963613493821440.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}