{
  "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": 8.976618038646277,
      "learning_rate": 2.8169014084507043e-07,
      "loss": 1.2046,
      "step": 1
    },
    {
      "epoch": 0.01,
      "grad_norm": 9.12950183658323,
      "learning_rate": 1.4084507042253523e-06,
      "loss": 1.2117,
      "step": 5
    },
    {
      "epoch": 0.01,
      "grad_norm": 9.470582272109555,
      "learning_rate": 2.8169014084507046e-06,
      "loss": 1.1487,
      "step": 10
    },
    {
      "epoch": 0.02,
      "grad_norm": 3.298228638351113,
      "learning_rate": 4.225352112676057e-06,
      "loss": 1.0049,
      "step": 15
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.6882426355197893,
      "learning_rate": 5.633802816901409e-06,
      "loss": 0.9194,
      "step": 20
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.2713113746044633,
      "learning_rate": 7.042253521126761e-06,
      "loss": 0.8716,
      "step": 25
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.0798985958176581,
      "learning_rate": 8.450704225352114e-06,
      "loss": 0.864,
      "step": 30
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.7403180014309052,
      "learning_rate": 9.859154929577466e-06,
      "loss": 0.8359,
      "step": 35
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.6646311223634714,
      "learning_rate": 1.1267605633802819e-05,
      "loss": 0.8614,
      "step": 40
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.6593031879361225,
      "learning_rate": 1.2676056338028171e-05,
      "loss": 0.8375,
      "step": 45
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.6848734508736534,
      "learning_rate": 1.4084507042253522e-05,
      "loss": 0.8305,
      "step": 50
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.607938821978484,
      "learning_rate": 1.5492957746478872e-05,
      "loss": 0.8392,
      "step": 55
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.5835312438044307,
      "learning_rate": 1.6901408450704228e-05,
      "loss": 0.8211,
      "step": 60
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.5785695089038153,
      "learning_rate": 1.830985915492958e-05,
      "loss": 0.8104,
      "step": 65
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.6041477487355849,
      "learning_rate": 1.9718309859154933e-05,
      "loss": 0.7881,
      "step": 70
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.5827780932059524,
      "learning_rate": 1.9998023297700656e-05,
      "loss": 0.8227,
      "step": 75
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.5965623592450553,
      "learning_rate": 1.9989994283927287e-05,
      "loss": 0.7805,
      "step": 80
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.5862237875540276,
      "learning_rate": 1.997579437055642e-05,
      "loss": 0.8011,
      "step": 85
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.6398990841425803,
      "learning_rate": 1.9955432328988437e-05,
      "loss": 0.8092,
      "step": 90
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.5892745053482765,
      "learning_rate": 1.9928920737019735e-05,
      "loss": 0.8111,
      "step": 95
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.6020877373053659,
      "learning_rate": 1.9896275971073326e-05,
      "loss": 0.8034,
      "step": 100
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.5950163528352244,
      "learning_rate": 1.9857518196082964e-05,
      "loss": 0.783,
      "step": 105
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.6219407257978654,
      "learning_rate": 1.981267135303714e-05,
      "loss": 0.7986,
      "step": 110
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.6390371388931367,
      "learning_rate": 1.976176314419051e-05,
      "loss": 0.8172,
      "step": 115
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.6237373520959375,
      "learning_rate": 1.9704825015952005e-05,
      "loss": 0.7981,
      "step": 120
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.6799237392350457,
      "learning_rate": 1.9641892139460133e-05,
      "loss": 0.8019,
      "step": 125
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.5744917640149093,
      "learning_rate": 1.9573003388857476e-05,
      "loss": 0.7802,
      "step": 130
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.6373020618232809,
      "learning_rate": 1.949820131727783e-05,
      "loss": 0.8233,
      "step": 135
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.5813679472234877,
      "learning_rate": 1.9417532130560784e-05,
      "loss": 0.7793,
      "step": 140
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.5752342288229056,
      "learning_rate": 1.933104565871001e-05,
      "loss": 0.7901,
      "step": 145
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.5794685365516447,
      "learning_rate": 1.9238795325112867e-05,
      "loss": 0.7823,
      "step": 150
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.5914869332169176,
      "learning_rate": 1.9140838113540347e-05,
      "loss": 0.7906,
      "step": 155
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.602426155045894,
      "learning_rate": 1.9037234532947737e-05,
      "loss": 0.7858,
      "step": 160
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.5749535966002742,
      "learning_rate": 1.8928048580097758e-05,
      "loss": 0.7902,
      "step": 165
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.586281192585965,
      "learning_rate": 1.8813347700029244e-05,
      "loss": 0.7756,
      "step": 170
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.6233741174701375,
      "learning_rate": 1.869320274439583e-05,
      "loss": 0.7945,
      "step": 175
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.6098071502533721,
      "learning_rate": 1.8567687927700255e-05,
      "loss": 0.8089,
      "step": 180
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.6064829730589661,
      "learning_rate": 1.8436880781451545e-05,
      "loss": 0.7866,
      "step": 185
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.6415063522870069,
      "learning_rate": 1.8300862106273113e-05,
      "loss": 0.7661,
      "step": 190
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.5976369233036758,
      "learning_rate": 1.8159715921991612e-05,
      "loss": 0.7518,
      "step": 195
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.5808209243272175,
      "learning_rate": 1.801352941573718e-05,
      "loss": 0.777,
      "step": 200
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.6085478615714451,
      "learning_rate": 1.786239288808727e-05,
      "loss": 0.7517,
      "step": 205
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.6110100484028232,
      "learning_rate": 1.770639969728726e-05,
      "loss": 0.7582,
      "step": 210
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.6103064740938433,
      "learning_rate": 1.7545646201582304e-05,
      "loss": 0.7739,
      "step": 215
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.6095643766898001,
      "learning_rate": 1.738023169969608e-05,
      "loss": 0.7747,
      "step": 220
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.5878428144325306,
      "learning_rate": 1.721025836949317e-05,
      "loss": 0.7601,
      "step": 225
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.580193134978998,
      "learning_rate": 1.703583120486297e-05,
      "loss": 0.7831,
      "step": 230
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.6531767240234573,
      "learning_rate": 1.6857057950864134e-05,
      "loss": 0.7792,
      "step": 235
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.6269016285983363,
      "learning_rate": 1.6674049037169565e-05,
      "loss": 0.7699,
      "step": 240
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.5676615892406944,
      "learning_rate": 1.648691750985314e-05,
      "loss": 0.7465,
      "step": 245
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.6103636647559819,
      "learning_rate": 1.6295778961560242e-05,
      "loss": 0.7615,
      "step": 250
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.5602858008551354,
      "learning_rate": 1.6100751460105244e-05,
      "loss": 0.7517,
      "step": 255
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.5652587482524394,
      "learning_rate": 1.5901955475540087e-05,
      "loss": 0.7433,
      "step": 260
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.6293727832821757,
      "learning_rate": 1.5699513805738942e-05,
      "loss": 0.7546,
      "step": 265
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.5899236848402083,
      "learning_rate": 1.549355150054501e-05,
      "loss": 0.7586,
      "step": 270
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.5858156410561468,
      "learning_rate": 1.5284195784526196e-05,
      "loss": 0.7435,
      "step": 275
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.6461462712535574,
      "learning_rate": 1.5071575978387505e-05,
      "loss": 0.7557,
      "step": 280
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.5896422662231582,
      "learning_rate": 1.4855823419088576e-05,
      "loss": 0.7523,
      "step": 285
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.6152912876368505,
      "learning_rate": 1.4637071378715807e-05,
      "loss": 0.7466,
      "step": 290
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.5476828784032306,
      "learning_rate": 1.4415454982159121e-05,
      "loss": 0.7575,
      "step": 295
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.5963972160682588,
      "learning_rate": 1.419111112364422e-05,
      "loss": 0.765,
      "step": 300
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.5892250766623344,
      "learning_rate": 1.3964178382171942e-05,
      "loss": 0.7509,
      "step": 305
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.5821016231570963,
      "learning_rate": 1.3734796935916888e-05,
      "loss": 0.7248,
      "step": 310
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.5652243248281746,
      "learning_rate": 1.3503108475638244e-05,
      "loss": 0.7288,
      "step": 315
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.6281159930375059,
      "learning_rate": 1.326925611715627e-05,
      "loss": 0.7559,
      "step": 320
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.5888656609358633,
      "learning_rate": 1.3033384312948487e-05,
      "loss": 0.7448,
      "step": 325
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.6165686859395609,
      "learning_rate": 1.2795638762920254e-05,
      "loss": 0.742,
      "step": 330
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.6381549925910247,
      "learning_rate": 1.2556166324404747e-05,
      "loss": 0.7099,
      "step": 335
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.5545610243561243,
      "learning_rate": 1.2315114921448012e-05,
      "loss": 0.7361,
      "step": 340
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.5706928669226053,
      "learning_rate": 1.2072633453435092e-05,
      "loss": 0.7258,
      "step": 345
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.6107785989730811,
      "learning_rate": 1.1828871703113686e-05,
      "loss": 0.7525,
      "step": 350
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.6008084503226107,
      "learning_rate": 1.158398024407215e-05,
      "loss": 0.7443,
      "step": 355
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.5731046479253954,
      "learning_rate": 1.1338110347728973e-05,
      "loss": 0.7488,
      "step": 360
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.6378170263505424,
      "learning_rate": 1.1091413889891211e-05,
      "loss": 0.7451,
      "step": 365
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.6479687798024056,
      "learning_rate": 1.0844043256939585e-05,
      "loss": 0.7513,
      "step": 370
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.6131548915096868,
      "learning_rate": 1.05961512516982e-05,
      "loss": 0.7547,
      "step": 375
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.6034495628166195,
      "learning_rate": 1.0347890999046998e-05,
      "loss": 0.7292,
      "step": 380
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.5595982017393247,
      "learning_rate": 1.00994158513353e-05,
      "loss": 0.7291,
      "step": 385
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.5908657324990593,
      "learning_rate": 9.850879293654829e-06,
      "loss": 0.7319,
      "step": 390
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.5686261006528736,
      "learning_rate": 9.602434849030747e-06,
      "loss": 0.7522,
      "step": 395
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.5931803289250058,
      "learning_rate": 9.354235983589229e-06,
      "loss": 0.7285,
      "step": 400
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.576733249565169,
      "learning_rate": 9.106436011760229e-06,
      "loss": 0.7102,
      "step": 405
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.6419706570687358,
      "learning_rate": 8.859188001573916e-06,
      "loss": 0.7511,
      "step": 410
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.5844726337209573,
      "learning_rate": 8.61264468010932e-06,
      "loss": 0.7022,
      "step": 415
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.6120657481180046,
      "learning_rate": 8.3669583391536e-06,
      "loss": 0.7274,
      "step": 420
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.5798319383539561,
      "learning_rate": 8.122280741130177e-06,
      "loss": 0.737,
      "step": 425
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.5911269901152743,
      "learning_rate": 7.878763025353875e-06,
      "loss": 0.7456,
      "step": 430
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.6030008166764901,
      "learning_rate": 7.636555614670953e-06,
      "loss": 0.7443,
      "step": 435
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.584933481934183,
      "learning_rate": 7.395808122541697e-06,
      "loss": 0.7457,
      "step": 440
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.6178817275024883,
      "learning_rate": 7.156669260622997e-06,
      "loss": 0.7272,
      "step": 445
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.576738068462372,
      "learning_rate": 6.9192867469079625e-06,
      "loss": 0.7355,
      "step": 450
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.610153251929595,
      "learning_rate": 6.683807214479323e-06,
      "loss": 0.7369,
      "step": 455
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.5755637011823521,
      "learning_rate": 6.450376120933008e-06,
      "loss": 0.725,
      "step": 460
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.6096210457693504,
      "learning_rate": 6.219137658527819e-06,
      "loss": 0.7485,
      "step": 465
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.5633088212735556,
      "learning_rate": 5.990234665116713e-06,
      "loss": 0.7322,
      "step": 470
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.616469990783489,
      "learning_rate": 5.7638085359147235e-06,
      "loss": 0.7234,
      "step": 475
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.6045801377903139,
      "learning_rate": 5.539999136157977e-06,
      "loss": 0.7093,
      "step": 480
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.5168220414675904,
      "learning_rate": 5.318944714707861e-06,
      "loss": 0.7209,
      "step": 485
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.5819546302447135,
      "learning_rate": 5.100781818653549e-06,
      "loss": 0.7088,
      "step": 490
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.6214693170980583,
      "learning_rate": 4.885645208965779e-06,
      "loss": 0.7295,
      "step": 495
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.5483651139224388,
      "learning_rate": 4.673667777253944e-06,
      "loss": 0.7452,
      "step": 500
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.6043244439563197,
      "learning_rate": 4.464980463677846e-06,
      "loss": 0.7359,
      "step": 505
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.5841849428722694,
      "learning_rate": 4.25971217606493e-06,
      "loss": 0.7364,
      "step": 510
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.5971777780370174,
      "learning_rate": 4.057989710282897e-06,
      "loss": 0.7287,
      "step": 515
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.5376730799298396,
      "learning_rate": 3.859937671916833e-06,
      "loss": 0.7383,
      "step": 520
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.6254203665305461,
      "learning_rate": 3.6656783992993885e-06,
      "loss": 0.7264,
      "step": 525
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.607374971442512,
      "learning_rate": 3.475331887941388e-06,
      "loss": 0.7384,
      "step": 530
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.5562789621862069,
      "learning_rate": 3.2890157164096315e-06,
      "loss": 0.7398,
      "step": 535
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.6391017139819878,
      "learning_rate": 3.1068449736977015e-06,
      "loss": 0.7341,
      "step": 540
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.5658442494663427,
      "learning_rate": 2.9289321881345257e-06,
      "loss": 0.7244,
      "step": 545
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.5722130325678222,
      "learning_rate": 2.755387257874764e-06,
      "loss": 0.7228,
      "step": 550
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.5879060164397627,
      "learning_rate": 2.5863173830138212e-06,
      "loss": 0.718,
      "step": 555
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.5854775512772113,
      "learning_rate": 2.4218269993694733e-06,
      "loss": 0.7286,
      "step": 560
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.543757639434833,
      "learning_rate": 2.262017713971063e-06,
      "loss": 0.712,
      "step": 565
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.5347024748449094,
      "learning_rate": 2.106988242295981e-06,
      "loss": 0.7311,
      "step": 570
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.5422054679063607,
      "learning_rate": 1.9568343472923524e-06,
      "loss": 0.7156,
      "step": 575
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.6108858998011519,
      "learning_rate": 1.8116487802254868e-06,
      "loss": 0.7282,
      "step": 580
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.6037057135293289,
      "learning_rate": 1.6715212233846656e-06,
      "loss": 0.7159,
      "step": 585
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.561518631539835,
      "learning_rate": 1.5365382346857005e-06,
      "loss": 0.7349,
      "step": 590
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.5560148126465202,
      "learning_rate": 1.4067831942033904e-06,
      "loss": 0.7106,
      "step": 595
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.5895011500377241,
      "learning_rate": 1.2823362526669825e-06,
      "loss": 0.7074,
      "step": 600
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.5592384208209128,
      "learning_rate": 1.1632742819504406e-06,
      "loss": 0.7243,
      "step": 605
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.599779305605372,
      "learning_rate": 1.0496708275880497e-06,
      "loss": 0.7238,
      "step": 610
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.5909990735500785,
      "learning_rate": 9.415960633447674e-07,
      "loss": 0.7158,
      "step": 615
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.5695280113058802,
      "learning_rate": 8.391167478693241e-07,
      "loss": 0.721,
      "step": 620
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.5828076535860982,
      "learning_rate": 7.422961834568565e-07,
      "loss": 0.7097,
      "step": 625
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.5642901879945964,
      "learning_rate": 6.51194176946588e-07,
      "loss": 0.711,
      "step": 630
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.5948097987699422,
      "learning_rate": 5.658670027786561e-07,
      "loss": 0.713,
      "step": 635
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.6020151691331499,
      "learning_rate": 4.863673682329373e-07,
      "loss": 0.7395,
      "step": 640
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.5889825924322954,
      "learning_rate": 4.1274438087135273e-07,
      "loss": 0.7434,
      "step": 645
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.5306993928105772,
      "learning_rate": 3.450435182037104e-07,
      "loss": 0.6871,
      "step": 650
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.5664135818341235,
      "learning_rate": 2.8330659959589944e-07,
      "loss": 0.727,
      "step": 655
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.5686227351601807,
      "learning_rate": 2.275717604377292e-07,
      "loss": 0.7329,
      "step": 660
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.5396140909322422,
      "learning_rate": 1.7787342858638589e-07,
      "loss": 0.7136,
      "step": 665
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.5729429274266005,
      "learning_rate": 1.3424230310007946e-07,
      "loss": 0.739,
      "step": 670
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.5839067564756593,
      "learning_rate": 9.670533527498139e-08,
      "loss": 0.7209,
      "step": 675
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.5835981596712281,
      "learning_rate": 6.528571199719502e-08,
      "loss": 0.7322,
      "step": 680
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.5714383368277501,
      "learning_rate": 4.000284142003264e-08,
      "loss": 0.7112,
      "step": 685
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.5810188754832274,
      "learning_rate": 2.0872340975438555e-08,
      "loss": 0.7327,
      "step": 690
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.572576103364852,
      "learning_rate": 7.906027726981568e-09,
      "loss": 0.7149,
      "step": 695
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5576564322671743,
      "learning_rate": 1.111911070356131e-09,
      "loss": 0.7072,
      "step": 700
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.7502086162567139,
      "eval_runtime": 9.4869,
      "eval_samples_per_second": 52.704,
      "eval_steps_per_second": 1.687,
      "step": 703
    },
    {
      "epoch": 1.0,
      "step": 703,
      "total_flos": 101830592102400.0,
      "train_loss": 0.762717972100205,
      "train_runtime": 5850.9583,
      "train_samples_per_second": 15.382,
      "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
}