{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9992892679459844,
  "eval_steps": 500,
  "global_step": 703,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 8.976748246707771,
      "learning_rate": 2.8169014084507043e-07,
      "loss": 1.2046,
      "step": 1
    },
    {
      "epoch": 0.01,
      "grad_norm": 9.141400774480953,
      "learning_rate": 1.4084507042253523e-06,
      "loss": 1.212,
      "step": 5
    },
    {
      "epoch": 0.01,
      "grad_norm": 9.49864441857399,
      "learning_rate": 2.8169014084507046e-06,
      "loss": 1.1487,
      "step": 10
    },
    {
      "epoch": 0.02,
      "grad_norm": 3.2926935702992415,
      "learning_rate": 4.225352112676057e-06,
      "loss": 1.0049,
      "step": 15
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.7117549060658137,
      "learning_rate": 5.633802816901409e-06,
      "loss": 0.9194,
      "step": 20
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.2735260163319009,
      "learning_rate": 7.042253521126761e-06,
      "loss": 0.8716,
      "step": 25
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.0790301127605728,
      "learning_rate": 8.450704225352114e-06,
      "loss": 0.864,
      "step": 30
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.7414273564854603,
      "learning_rate": 9.859154929577466e-06,
      "loss": 0.8359,
      "step": 35
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.6656956199139998,
      "learning_rate": 1.1267605633802819e-05,
      "loss": 0.8614,
      "step": 40
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.6590669608248467,
      "learning_rate": 1.2676056338028171e-05,
      "loss": 0.8375,
      "step": 45
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.6842437677529626,
      "learning_rate": 1.4084507042253522e-05,
      "loss": 0.8306,
      "step": 50
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.6080481338431981,
      "learning_rate": 1.5492957746478872e-05,
      "loss": 0.8391,
      "step": 55
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.5829909243761902,
      "learning_rate": 1.6901408450704228e-05,
      "loss": 0.8211,
      "step": 60
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.5774288402112024,
      "learning_rate": 1.830985915492958e-05,
      "loss": 0.8104,
      "step": 65
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.6037500273154381,
      "learning_rate": 1.9718309859154933e-05,
      "loss": 0.7882,
      "step": 70
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.5823339744513759,
      "learning_rate": 1.9998023297700656e-05,
      "loss": 0.8226,
      "step": 75
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.5970199949943188,
      "learning_rate": 1.9989994283927287e-05,
      "loss": 0.7805,
      "step": 80
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.5863046182186602,
      "learning_rate": 1.997579437055642e-05,
      "loss": 0.8011,
      "step": 85
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.6404658915624578,
      "learning_rate": 1.9955432328988437e-05,
      "loss": 0.8092,
      "step": 90
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.5889469279145607,
      "learning_rate": 1.9928920737019735e-05,
      "loss": 0.8111,
      "step": 95
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.5999505405000287,
      "learning_rate": 1.9896275971073326e-05,
      "loss": 0.8034,
      "step": 100
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.5958697553643331,
      "learning_rate": 1.9857518196082964e-05,
      "loss": 0.783,
      "step": 105
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.6235891380868392,
      "learning_rate": 1.981267135303714e-05,
      "loss": 0.7986,
      "step": 110
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.6386697510622403,
      "learning_rate": 1.976176314419051e-05,
      "loss": 0.8173,
      "step": 115
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.6223044203965952,
      "learning_rate": 1.9704825015952005e-05,
      "loss": 0.7981,
      "step": 120
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.6801656349332326,
      "learning_rate": 1.9641892139460133e-05,
      "loss": 0.8018,
      "step": 125
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.5736017682468991,
      "learning_rate": 1.9573003388857476e-05,
      "loss": 0.7801,
      "step": 130
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.6377284634315731,
      "learning_rate": 1.949820131727783e-05,
      "loss": 0.8233,
      "step": 135
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.5834471085873422,
      "learning_rate": 1.9417532130560784e-05,
      "loss": 0.7792,
      "step": 140
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.5750039228232332,
      "learning_rate": 1.933104565871001e-05,
      "loss": 0.79,
      "step": 145
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.5788157023616078,
      "learning_rate": 1.9238795325112867e-05,
      "loss": 0.7823,
      "step": 150
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.5905988672413683,
      "learning_rate": 1.9140838113540347e-05,
      "loss": 0.7907,
      "step": 155
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.6036919615732501,
      "learning_rate": 1.9037234532947737e-05,
      "loss": 0.7859,
      "step": 160
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.5744116424871404,
      "learning_rate": 1.8928048580097758e-05,
      "loss": 0.7902,
      "step": 165
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.5858290882445865,
      "learning_rate": 1.8813347700029244e-05,
      "loss": 0.7756,
      "step": 170
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.6203103361508707,
      "learning_rate": 1.869320274439583e-05,
      "loss": 0.7945,
      "step": 175
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.6094752243332237,
      "learning_rate": 1.8567687927700255e-05,
      "loss": 0.8089,
      "step": 180
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.6065177506682852,
      "learning_rate": 1.8436880781451545e-05,
      "loss": 0.7866,
      "step": 185
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.6422514480326399,
      "learning_rate": 1.8300862106273113e-05,
      "loss": 0.7661,
      "step": 190
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.5976731025044114,
      "learning_rate": 1.8159715921991612e-05,
      "loss": 0.7518,
      "step": 195
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.5813547875268166,
      "learning_rate": 1.801352941573718e-05,
      "loss": 0.777,
      "step": 200
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.6079636229603744,
      "learning_rate": 1.786239288808727e-05,
      "loss": 0.7517,
      "step": 205
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.6116028297485965,
      "learning_rate": 1.770639969728726e-05,
      "loss": 0.7582,
      "step": 210
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.6104535774475512,
      "learning_rate": 1.7545646201582304e-05,
      "loss": 0.7739,
      "step": 215
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.6092743685177864,
      "learning_rate": 1.738023169969608e-05,
      "loss": 0.7747,
      "step": 220
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.5879141856316753,
      "learning_rate": 1.721025836949317e-05,
      "loss": 0.7601,
      "step": 225
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.5801521678476529,
      "learning_rate": 1.703583120486297e-05,
      "loss": 0.7831,
      "step": 230
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.6538515323321731,
      "learning_rate": 1.6857057950864134e-05,
      "loss": 0.7792,
      "step": 235
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.6283544032704685,
      "learning_rate": 1.6674049037169565e-05,
      "loss": 0.7699,
      "step": 240
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.5680653535007143,
      "learning_rate": 1.648691750985314e-05,
      "loss": 0.7465,
      "step": 245
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.6108554255786504,
      "learning_rate": 1.6295778961560242e-05,
      "loss": 0.7615,
      "step": 250
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.5595610558009545,
      "learning_rate": 1.6100751460105244e-05,
      "loss": 0.7517,
      "step": 255
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.5638534604629722,
      "learning_rate": 1.5901955475540087e-05,
      "loss": 0.7433,
      "step": 260
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.6290842137244347,
      "learning_rate": 1.5699513805738942e-05,
      "loss": 0.7546,
      "step": 265
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.5899201877158341,
      "learning_rate": 1.549355150054501e-05,
      "loss": 0.7586,
      "step": 270
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.5848454901161203,
      "learning_rate": 1.5284195784526196e-05,
      "loss": 0.7435,
      "step": 275
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.6441906832873957,
      "learning_rate": 1.5071575978387505e-05,
      "loss": 0.7557,
      "step": 280
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.5889076952992223,
      "learning_rate": 1.4855823419088576e-05,
      "loss": 0.7523,
      "step": 285
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.6138750994803515,
      "learning_rate": 1.4637071378715807e-05,
      "loss": 0.7466,
      "step": 290
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.5460450262431842,
      "learning_rate": 1.4415454982159121e-05,
      "loss": 0.7575,
      "step": 295
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.5958584774428966,
      "learning_rate": 1.419111112364422e-05,
      "loss": 0.7651,
      "step": 300
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.5892595546498745,
      "learning_rate": 1.3964178382171942e-05,
      "loss": 0.7509,
      "step": 305
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.5824299769787271,
      "learning_rate": 1.3734796935916888e-05,
      "loss": 0.7248,
      "step": 310
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.564819905580984,
      "learning_rate": 1.3503108475638244e-05,
      "loss": 0.7288,
      "step": 315
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.6263083055380363,
      "learning_rate": 1.326925611715627e-05,
      "loss": 0.7559,
      "step": 320
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.5885749596082486,
      "learning_rate": 1.3033384312948487e-05,
      "loss": 0.7448,
      "step": 325
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.6217412195838338,
      "learning_rate": 1.2795638762920254e-05,
      "loss": 0.742,
      "step": 330
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.6379002045294617,
      "learning_rate": 1.2556166324404747e-05,
      "loss": 0.7099,
      "step": 335
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.5539140087654301,
      "learning_rate": 1.2315114921448012e-05,
      "loss": 0.7362,
      "step": 340
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.5709158729850722,
      "learning_rate": 1.2072633453435092e-05,
      "loss": 0.7259,
      "step": 345
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.6103140402089173,
      "learning_rate": 1.1828871703113686e-05,
      "loss": 0.7525,
      "step": 350
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.6006237395857831,
      "learning_rate": 1.158398024407215e-05,
      "loss": 0.7443,
      "step": 355
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.5730036044160878,
      "learning_rate": 1.1338110347728973e-05,
      "loss": 0.7488,
      "step": 360
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.6357913417816614,
      "learning_rate": 1.1091413889891211e-05,
      "loss": 0.7451,
      "step": 365
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.6484616619442031,
      "learning_rate": 1.0844043256939585e-05,
      "loss": 0.7513,
      "step": 370
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.6147553788096094,
      "learning_rate": 1.05961512516982e-05,
      "loss": 0.7547,
      "step": 375
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.6026348227570094,
      "learning_rate": 1.0347890999046998e-05,
      "loss": 0.7291,
      "step": 380
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.5607221603847458,
      "learning_rate": 1.00994158513353e-05,
      "loss": 0.729,
      "step": 385
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.5908644383211163,
      "learning_rate": 9.850879293654829e-06,
      "loss": 0.7319,
      "step": 390
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.5697397462576617,
      "learning_rate": 9.602434849030747e-06,
      "loss": 0.7522,
      "step": 395
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.5939805294573912,
      "learning_rate": 9.354235983589229e-06,
      "loss": 0.7285,
      "step": 400
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.5755564582128363,
      "learning_rate": 9.106436011760229e-06,
      "loss": 0.7102,
      "step": 405
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.6451432716799574,
      "learning_rate": 8.859188001573916e-06,
      "loss": 0.7511,
      "step": 410
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.5843168824282191,
      "learning_rate": 8.61264468010932e-06,
      "loss": 0.7022,
      "step": 415
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.6112413168467156,
      "learning_rate": 8.3669583391536e-06,
      "loss": 0.7275,
      "step": 420
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.581022238822059,
      "learning_rate": 8.122280741130177e-06,
      "loss": 0.737,
      "step": 425
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.5858683287529846,
      "learning_rate": 7.878763025353875e-06,
      "loss": 0.7456,
      "step": 430
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.5983662476814803,
      "learning_rate": 7.636555614670953e-06,
      "loss": 0.7443,
      "step": 435
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.5853808275325328,
      "learning_rate": 7.395808122541697e-06,
      "loss": 0.7456,
      "step": 440
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.6178373733573391,
      "learning_rate": 7.156669260622997e-06,
      "loss": 0.7272,
      "step": 445
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.5767484461478896,
      "learning_rate": 6.9192867469079625e-06,
      "loss": 0.7355,
      "step": 450
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.6095308999494778,
      "learning_rate": 6.683807214479323e-06,
      "loss": 0.737,
      "step": 455
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.5757726348096623,
      "learning_rate": 6.450376120933008e-06,
      "loss": 0.725,
      "step": 460
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.6084178997751468,
      "learning_rate": 6.219137658527819e-06,
      "loss": 0.7484,
      "step": 465
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.5625041815811782,
      "learning_rate": 5.990234665116713e-06,
      "loss": 0.7322,
      "step": 470
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.6160006018394228,
      "learning_rate": 5.7638085359147235e-06,
      "loss": 0.7235,
      "step": 475
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.6035240580848604,
      "learning_rate": 5.539999136157977e-06,
      "loss": 0.7094,
      "step": 480
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.5166781636185539,
      "learning_rate": 5.318944714707861e-06,
      "loss": 0.7209,
      "step": 485
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.5822772862847312,
      "learning_rate": 5.100781818653549e-06,
      "loss": 0.7088,
      "step": 490
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.6227541043433473,
      "learning_rate": 4.885645208965779e-06,
      "loss": 0.7295,
      "step": 495
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.54846199474894,
      "learning_rate": 4.673667777253944e-06,
      "loss": 0.7452,
      "step": 500
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.6040144782037625,
      "learning_rate": 4.464980463677846e-06,
      "loss": 0.736,
      "step": 505
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.5847697359147894,
      "learning_rate": 4.25971217606493e-06,
      "loss": 0.7364,
      "step": 510
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.597219775666177,
      "learning_rate": 4.057989710282897e-06,
      "loss": 0.7288,
      "step": 515
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.5379233895836751,
      "learning_rate": 3.859937671916833e-06,
      "loss": 0.7383,
      "step": 520
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.6251650029425307,
      "learning_rate": 3.6656783992993885e-06,
      "loss": 0.7264,
      "step": 525
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.6054608357116987,
      "learning_rate": 3.475331887941388e-06,
      "loss": 0.7384,
      "step": 530
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.5551297177270929,
      "learning_rate": 3.2890157164096315e-06,
      "loss": 0.7398,
      "step": 535
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.6396725383662202,
      "learning_rate": 3.1068449736977015e-06,
      "loss": 0.7341,
      "step": 540
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.5648152571609389,
      "learning_rate": 2.9289321881345257e-06,
      "loss": 0.7244,
      "step": 545
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.57252018708692,
      "learning_rate": 2.755387257874764e-06,
      "loss": 0.7228,
      "step": 550
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.5878135364575673,
      "learning_rate": 2.5863173830138212e-06,
      "loss": 0.7181,
      "step": 555
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.5840059710891027,
      "learning_rate": 2.4218269993694733e-06,
      "loss": 0.7286,
      "step": 560
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.5438192269829342,
      "learning_rate": 2.262017713971063e-06,
      "loss": 0.712,
      "step": 565
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.5350040038892513,
      "learning_rate": 2.106988242295981e-06,
      "loss": 0.7312,
      "step": 570
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.5423604435174225,
      "learning_rate": 1.9568343472923524e-06,
      "loss": 0.7155,
      "step": 575
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.6113034501153347,
      "learning_rate": 1.8116487802254868e-06,
      "loss": 0.7282,
      "step": 580
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.6023686669705883,
      "learning_rate": 1.6715212233846656e-06,
      "loss": 0.7159,
      "step": 585
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.5618755550032292,
      "learning_rate": 1.5365382346857005e-06,
      "loss": 0.7349,
      "step": 590
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.5579514856251387,
      "learning_rate": 1.4067831942033904e-06,
      "loss": 0.7106,
      "step": 595
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.5910581925001689,
      "learning_rate": 1.2823362526669825e-06,
      "loss": 0.7074,
      "step": 600
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.5595582019084373,
      "learning_rate": 1.1632742819504406e-06,
      "loss": 0.7244,
      "step": 605
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.6034146234727371,
      "learning_rate": 1.0496708275880497e-06,
      "loss": 0.7237,
      "step": 610
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.5913679291364223,
      "learning_rate": 9.415960633447674e-07,
      "loss": 0.7158,
      "step": 615
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.5694936405039339,
      "learning_rate": 8.391167478693241e-07,
      "loss": 0.7209,
      "step": 620
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.5805765466263503,
      "learning_rate": 7.422961834568565e-07,
      "loss": 0.7097,
      "step": 625
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.5641375110299046,
      "learning_rate": 6.51194176946588e-07,
      "loss": 0.711,
      "step": 630
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.5928177799223828,
      "learning_rate": 5.658670027786561e-07,
      "loss": 0.713,
      "step": 635
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.6022673346018554,
      "learning_rate": 4.863673682329373e-07,
      "loss": 0.7395,
      "step": 640
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.588777849626458,
      "learning_rate": 4.1274438087135273e-07,
      "loss": 0.7435,
      "step": 645
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.52867680060555,
      "learning_rate": 3.450435182037104e-07,
      "loss": 0.6871,
      "step": 650
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.5676798921047626,
      "learning_rate": 2.8330659959589944e-07,
      "loss": 0.727,
      "step": 655
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.5666677388076765,
      "learning_rate": 2.275717604377292e-07,
      "loss": 0.7329,
      "step": 660
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.5389907093110754,
      "learning_rate": 1.7787342858638589e-07,
      "loss": 0.7136,
      "step": 665
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.571817712811333,
      "learning_rate": 1.3424230310007946e-07,
      "loss": 0.739,
      "step": 670
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.5830917030629162,
      "learning_rate": 9.670533527498139e-08,
      "loss": 0.7209,
      "step": 675
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.5837803782222483,
      "learning_rate": 6.528571199719502e-08,
      "loss": 0.7322,
      "step": 680
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.5711509584660898,
      "learning_rate": 4.000284142003264e-08,
      "loss": 0.7113,
      "step": 685
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.5826105062040772,
      "learning_rate": 2.0872340975438555e-08,
      "loss": 0.7327,
      "step": 690
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.5724533629251033,
      "learning_rate": 7.906027726981568e-09,
      "loss": 0.715,
      "step": 695
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5578776974422313,
      "learning_rate": 1.111911070356131e-09,
      "loss": 0.7072,
      "step": 700
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.7502214908599854,
      "eval_runtime": 9.4753,
      "eval_samples_per_second": 52.769,
      "eval_steps_per_second": 1.689,
      "step": 703
    },
    {
      "epoch": 1.0,
      "step": 703,
      "total_flos": 101830592102400.0,
      "train_loss": 0.7627222812701425,
      "train_runtime": 5862.0034,
      "train_samples_per_second": 15.353,
      "train_steps_per_second": 0.12
    }
  ],
  "logging_steps": 5,
  "max_steps": 703,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 101830592102400.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}