{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 200,
  "global_step": 812,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012315270935960591,
      "grad_norm": 53.61643111350721,
      "learning_rate": 1.2195121951219514e-07,
      "loss": 4.2831,
      "step": 1
    },
    {
      "epoch": 0.006157635467980296,
      "grad_norm": 48.00417504001698,
      "learning_rate": 6.097560975609757e-07,
      "loss": 4.1517,
      "step": 5
    },
    {
      "epoch": 0.012315270935960592,
      "grad_norm": 48.656126717388894,
      "learning_rate": 1.2195121951219514e-06,
      "loss": 4.1506,
      "step": 10
    },
    {
      "epoch": 0.01847290640394089,
      "grad_norm": 52.06244750805184,
      "learning_rate": 1.8292682926829268e-06,
      "loss": 4.0921,
      "step": 15
    },
    {
      "epoch": 0.024630541871921183,
      "grad_norm": 41.842979233989844,
      "learning_rate": 2.4390243902439027e-06,
      "loss": 3.832,
      "step": 20
    },
    {
      "epoch": 0.03078817733990148,
      "grad_norm": 26.054139160186445,
      "learning_rate": 3.0487804878048782e-06,
      "loss": 3.4798,
      "step": 25
    },
    {
      "epoch": 0.03694581280788178,
      "grad_norm": 22.768708360256497,
      "learning_rate": 3.6585365853658537e-06,
      "loss": 3.1223,
      "step": 30
    },
    {
      "epoch": 0.04310344827586207,
      "grad_norm": 11.807556286649826,
      "learning_rate": 4.268292682926829e-06,
      "loss": 2.774,
      "step": 35
    },
    {
      "epoch": 0.04926108374384237,
      "grad_norm": 10.768737194323332,
      "learning_rate": 4.8780487804878055e-06,
      "loss": 2.4807,
      "step": 40
    },
    {
      "epoch": 0.05541871921182266,
      "grad_norm": 7.978916355789078,
      "learning_rate": 4.999667943970417e-06,
      "loss": 2.3202,
      "step": 45
    },
    {
      "epoch": 0.06157635467980296,
      "grad_norm": 6.323820375851387,
      "learning_rate": 4.9983191175272635e-06,
      "loss": 2.1276,
      "step": 50
    },
    {
      "epoch": 0.06773399014778325,
      "grad_norm": 5.180335911696107,
      "learning_rate": 4.995933326588439e-06,
      "loss": 1.9964,
      "step": 55
    },
    {
      "epoch": 0.07389162561576355,
      "grad_norm": 4.28298322285663,
      "learning_rate": 4.992511561411944e-06,
      "loss": 1.8959,
      "step": 60
    },
    {
      "epoch": 0.08004926108374384,
      "grad_norm": 3.8950053865689425,
      "learning_rate": 4.988055242252294e-06,
      "loss": 1.7978,
      "step": 65
    },
    {
      "epoch": 0.08620689655172414,
      "grad_norm": 3.5678308957701725,
      "learning_rate": 4.982566218771011e-06,
      "loss": 1.7083,
      "step": 70
    },
    {
      "epoch": 0.09236453201970443,
      "grad_norm": 3.280549835228229,
      "learning_rate": 4.976046769268905e-06,
      "loss": 1.6391,
      "step": 75
    },
    {
      "epoch": 0.09852216748768473,
      "grad_norm": 3.0095284508920943,
      "learning_rate": 4.968499599740427e-06,
      "loss": 1.6052,
      "step": 80
    },
    {
      "epoch": 0.10467980295566502,
      "grad_norm": 2.728976091948925,
      "learning_rate": 4.959927842750501e-06,
      "loss": 1.5852,
      "step": 85
    },
    {
      "epoch": 0.11083743842364532,
      "grad_norm": 2.773190869191402,
      "learning_rate": 4.9503350561343165e-06,
      "loss": 1.5389,
      "step": 90
    },
    {
      "epoch": 0.11699507389162561,
      "grad_norm": 2.495284943078218,
      "learning_rate": 4.939725221520586e-06,
      "loss": 1.529,
      "step": 95
    },
    {
      "epoch": 0.12315270935960591,
      "grad_norm": 2.2585070403096448,
      "learning_rate": 4.928102742678918e-06,
      "loss": 1.5012,
      "step": 100
    },
    {
      "epoch": 0.12931034482758622,
      "grad_norm": 2.3030504202779203,
      "learning_rate": 4.915472443691962e-06,
      "loss": 1.5228,
      "step": 105
    },
    {
      "epoch": 0.1354679802955665,
      "grad_norm": 2.139871025358791,
      "learning_rate": 4.901839566953105e-06,
      "loss": 1.4999,
      "step": 110
    },
    {
      "epoch": 0.1416256157635468,
      "grad_norm": 2.041219388782717,
      "learning_rate": 4.887209770990537e-06,
      "loss": 1.4933,
      "step": 115
    },
    {
      "epoch": 0.1477832512315271,
      "grad_norm": 1.943568456417746,
      "learning_rate": 4.871589128118593e-06,
      "loss": 1.4794,
      "step": 120
    },
    {
      "epoch": 0.1539408866995074,
      "grad_norm": 1.9973156144136615,
      "learning_rate": 4.854984121917349e-06,
      "loss": 1.4658,
      "step": 125
    },
    {
      "epoch": 0.16009852216748768,
      "grad_norm": 2.0438506441497934,
      "learning_rate": 4.83740164454152e-06,
      "loss": 1.4371,
      "step": 130
    },
    {
      "epoch": 0.16625615763546797,
      "grad_norm": 1.856918766416631,
      "learning_rate": 4.8188489938597635e-06,
      "loss": 1.4343,
      "step": 135
    },
    {
      "epoch": 0.1724137931034483,
      "grad_norm": 1.815968456698851,
      "learning_rate": 4.799333870425594e-06,
      "loss": 1.436,
      "step": 140
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 1.833214631845253,
      "learning_rate": 4.778864374281147e-06,
      "loss": 1.4358,
      "step": 145
    },
    {
      "epoch": 0.18472906403940886,
      "grad_norm": 1.7361805528112662,
      "learning_rate": 4.757449001595149e-06,
      "loss": 1.4141,
      "step": 150
    },
    {
      "epoch": 0.19088669950738915,
      "grad_norm": 1.663939988626721,
      "learning_rate": 4.735096641136443e-06,
      "loss": 1.4235,
      "step": 155
    },
    {
      "epoch": 0.19704433497536947,
      "grad_norm": 1.6174000907070356,
      "learning_rate": 4.711816570584583e-06,
      "loss": 1.4094,
      "step": 160
    },
    {
      "epoch": 0.20320197044334976,
      "grad_norm": 1.5393337213532907,
      "learning_rate": 4.687618452678986e-06,
      "loss": 1.423,
      "step": 165
    },
    {
      "epoch": 0.20935960591133004,
      "grad_norm": 1.6022576546137135,
      "learning_rate": 4.662512331208277e-06,
      "loss": 1.4229,
      "step": 170
    },
    {
      "epoch": 0.21551724137931033,
      "grad_norm": 1.4720779248871585,
      "learning_rate": 4.636508626841458e-06,
      "loss": 1.3835,
      "step": 175
    },
    {
      "epoch": 0.22167487684729065,
      "grad_norm": 1.4933242533565454,
      "learning_rate": 4.609618132802661e-06,
      "loss": 1.42,
      "step": 180
    },
    {
      "epoch": 0.22783251231527094,
      "grad_norm": 1.513300883824977,
      "learning_rate": 4.581852010391253e-06,
      "loss": 1.3995,
      "step": 185
    },
    {
      "epoch": 0.23399014778325122,
      "grad_norm": 1.4476120919655675,
      "learning_rate": 4.55322178434918e-06,
      "loss": 1.381,
      "step": 190
    },
    {
      "epoch": 0.24014778325123154,
      "grad_norm": 1.3952114387215153,
      "learning_rate": 4.523739338077443e-06,
      "loss": 1.3886,
      "step": 195
    },
    {
      "epoch": 0.24630541871921183,
      "grad_norm": 1.3697029918579813,
      "learning_rate": 4.493416908703725e-06,
      "loss": 1.3939,
      "step": 200
    },
    {
      "epoch": 0.24630541871921183,
      "eval_loss": 1.3920977115631104,
      "eval_runtime": 145.3824,
      "eval_samples_per_second": 158.96,
      "eval_steps_per_second": 2.49,
      "step": 200
    },
    {
      "epoch": 0.2524630541871921,
      "grad_norm": 1.2995335774783041,
      "learning_rate": 4.462267082003183e-06,
      "loss": 1.3624,
      "step": 205
    },
    {
      "epoch": 0.25862068965517243,
      "grad_norm": 1.3420631400831042,
      "learning_rate": 4.430302787174535e-06,
      "loss": 1.3932,
      "step": 210
    },
    {
      "epoch": 0.2647783251231527,
      "grad_norm": 1.249545343253794,
      "learning_rate": 4.397537291473607e-06,
      "loss": 1.36,
      "step": 215
    },
    {
      "epoch": 0.270935960591133,
      "grad_norm": 1.2639981922437173,
      "learning_rate": 4.36398419470656e-06,
      "loss": 1.3546,
      "step": 220
    },
    {
      "epoch": 0.2770935960591133,
      "grad_norm": 1.3038810090775859,
      "learning_rate": 4.329657423585088e-06,
      "loss": 1.3748,
      "step": 225
    },
    {
      "epoch": 0.2832512315270936,
      "grad_norm": 1.2680995555961931,
      "learning_rate": 4.2945712259459245e-06,
      "loss": 1.3566,
      "step": 230
    },
    {
      "epoch": 0.2894088669950739,
      "grad_norm": 1.1649048616562434,
      "learning_rate": 4.258740164837079e-06,
      "loss": 1.3858,
      "step": 235
    },
    {
      "epoch": 0.2955665024630542,
      "grad_norm": 1.1320815166399936,
      "learning_rate": 4.222179112473211e-06,
      "loss": 1.3447,
      "step": 240
    },
    {
      "epoch": 0.3017241379310345,
      "grad_norm": 1.1611812170906886,
      "learning_rate": 4.184903244062709e-06,
      "loss": 1.3779,
      "step": 245
    },
    {
      "epoch": 0.3078817733990148,
      "grad_norm": 1.1257135240111318,
      "learning_rate": 4.146928031508988e-06,
      "loss": 1.3279,
      "step": 250
    },
    {
      "epoch": 0.31403940886699505,
      "grad_norm": 1.1200758606679568,
      "learning_rate": 4.108269236988648e-06,
      "loss": 1.3651,
      "step": 255
    },
    {
      "epoch": 0.32019704433497537,
      "grad_norm": 0.9671290050907145,
      "learning_rate": 4.068942906409148e-06,
      "loss": 1.3496,
      "step": 260
    },
    {
      "epoch": 0.3263546798029557,
      "grad_norm": 1.0185962333371894,
      "learning_rate": 4.028965362748714e-06,
      "loss": 1.3436,
      "step": 265
    },
    {
      "epoch": 0.33251231527093594,
      "grad_norm": 0.978818844718456,
      "learning_rate": 3.988353199281242e-06,
      "loss": 1.3178,
      "step": 270
    },
    {
      "epoch": 0.33866995073891626,
      "grad_norm": 0.973392817512532,
      "learning_rate": 3.9471232726890185e-06,
      "loss": 1.3292,
      "step": 275
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 1.0993106332736733,
      "learning_rate": 3.905292696066095e-06,
      "loss": 1.3295,
      "step": 280
    },
    {
      "epoch": 0.35098522167487683,
      "grad_norm": 1.0275184655442997,
      "learning_rate": 3.862878831815253e-06,
      "loss": 1.3583,
      "step": 285
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.9854194583937018,
      "learning_rate": 3.8198992844414736e-06,
      "loss": 1.2935,
      "step": 290
    },
    {
      "epoch": 0.3633004926108374,
      "grad_norm": 0.9611577984967152,
      "learning_rate": 3.7763718932449322e-06,
      "loss": 1.3332,
      "step": 295
    },
    {
      "epoch": 0.3694581280788177,
      "grad_norm": 1.0605919781420619,
      "learning_rate": 3.7323147249165255e-06,
      "loss": 1.3076,
      "step": 300
    },
    {
      "epoch": 0.37561576354679804,
      "grad_norm": 0.9263868172490802,
      "learning_rate": 3.6877460660390257e-06,
      "loss": 1.309,
      "step": 305
    },
    {
      "epoch": 0.3817733990147783,
      "grad_norm": 0.9572326588734382,
      "learning_rate": 3.6426844154969654e-06,
      "loss": 1.3042,
      "step": 310
    },
    {
      "epoch": 0.3879310344827586,
      "grad_norm": 0.9676601659166285,
      "learning_rate": 3.597148476798393e-06,
      "loss": 1.3091,
      "step": 315
    },
    {
      "epoch": 0.39408866995073893,
      "grad_norm": 0.9053200553500108,
      "learning_rate": 3.5511571503117125e-06,
      "loss": 1.3234,
      "step": 320
    },
    {
      "epoch": 0.4002463054187192,
      "grad_norm": 0.8972007834782274,
      "learning_rate": 3.504729525420798e-06,
      "loss": 1.2932,
      "step": 325
    },
    {
      "epoch": 0.4064039408866995,
      "grad_norm": 0.8726544346292117,
      "learning_rate": 3.4578848726016646e-06,
      "loss": 1.3175,
      "step": 330
    },
    {
      "epoch": 0.4125615763546798,
      "grad_norm": 0.9041763575954129,
      "learning_rate": 3.410642635423967e-06,
      "loss": 1.3192,
      "step": 335
    },
    {
      "epoch": 0.4187192118226601,
      "grad_norm": 0.8556502970513064,
      "learning_rate": 3.3630224224806616e-06,
      "loss": 1.3183,
      "step": 340
    },
    {
      "epoch": 0.4248768472906404,
      "grad_norm": 0.8626177859113207,
      "learning_rate": 3.3150439992491667e-06,
      "loss": 1.3105,
      "step": 345
    },
    {
      "epoch": 0.43103448275862066,
      "grad_norm": 0.7967188042404322,
      "learning_rate": 3.2667272798874038e-06,
      "loss": 1.2897,
      "step": 350
    },
    {
      "epoch": 0.437192118226601,
      "grad_norm": 0.8856403226277132,
      "learning_rate": 3.2180923189681367e-06,
      "loss": 1.2776,
      "step": 355
    },
    {
      "epoch": 0.4433497536945813,
      "grad_norm": 0.9102748822081079,
      "learning_rate": 3.169159303155017e-06,
      "loss": 1.3281,
      "step": 360
    },
    {
      "epoch": 0.44950738916256155,
      "grad_norm": 0.8702706004067514,
      "learning_rate": 3.119948542823812e-06,
      "loss": 1.2999,
      "step": 365
    },
    {
      "epoch": 0.45566502463054187,
      "grad_norm": 0.8391791004394836,
      "learning_rate": 3.0704804636322818e-06,
      "loss": 1.3013,
      "step": 370
    },
    {
      "epoch": 0.4618226600985222,
      "grad_norm": 0.9450784930448292,
      "learning_rate": 3.0207755980422036e-06,
      "loss": 1.3009,
      "step": 375
    },
    {
      "epoch": 0.46798029556650245,
      "grad_norm": 0.8364655680922604,
      "learning_rate": 2.970854576797073e-06,
      "loss": 1.3081,
      "step": 380
    },
    {
      "epoch": 0.47413793103448276,
      "grad_norm": 0.8637495993307496,
      "learning_rate": 2.920738120359e-06,
      "loss": 1.2983,
      "step": 385
    },
    {
      "epoch": 0.4802955665024631,
      "grad_norm": 0.8350897912388913,
      "learning_rate": 2.8704470303083808e-06,
      "loss": 1.3022,
      "step": 390
    },
    {
      "epoch": 0.48645320197044334,
      "grad_norm": 0.8003999962290238,
      "learning_rate": 2.820002180709888e-06,
      "loss": 1.2976,
      "step": 395
    },
    {
      "epoch": 0.49261083743842365,
      "grad_norm": 0.8205844355868652,
      "learning_rate": 2.769424509448379e-06,
      "loss": 1.2806,
      "step": 400
    },
    {
      "epoch": 0.49261083743842365,
      "eval_loss": 1.3155713081359863,
      "eval_runtime": 145.3401,
      "eval_samples_per_second": 159.006,
      "eval_steps_per_second": 2.491,
      "step": 400
    },
    {
      "epoch": 0.4987684729064039,
      "grad_norm": 0.7401769827680776,
      "learning_rate": 2.7187350095383197e-06,
      "loss": 1.2898,
      "step": 405
    },
    {
      "epoch": 0.5049261083743842,
      "grad_norm": 0.7932407776274949,
      "learning_rate": 2.6679547204103174e-06,
      "loss": 1.2932,
      "step": 410
    },
    {
      "epoch": 0.5110837438423645,
      "grad_norm": 0.746144620956253,
      "learning_rate": 2.617104719178395e-06,
      "loss": 1.2883,
      "step": 415
    },
    {
      "epoch": 0.5172413793103449,
      "grad_norm": 0.8276505969533728,
      "learning_rate": 2.566206111891621e-06,
      "loss": 1.3198,
      "step": 420
    },
    {
      "epoch": 0.5233990147783252,
      "grad_norm": 0.7534012683391147,
      "learning_rate": 2.5152800247737293e-06,
      "loss": 1.3157,
      "step": 425
    },
    {
      "epoch": 0.5295566502463054,
      "grad_norm": 0.7409765493416938,
      "learning_rate": 2.4643475954543657e-06,
      "loss": 1.2899,
      "step": 430
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 0.7291610138959701,
      "learning_rate": 2.413429964195603e-06,
      "loss": 1.3,
      "step": 435
    },
    {
      "epoch": 0.541871921182266,
      "grad_norm": 0.8169273699015402,
      "learning_rate": 2.362548265117355e-06,
      "loss": 1.309,
      "step": 440
    },
    {
      "epoch": 0.5480295566502463,
      "grad_norm": 0.7758419122658194,
      "learning_rate": 2.3117236174253556e-06,
      "loss": 1.2992,
      "step": 445
    },
    {
      "epoch": 0.5541871921182266,
      "grad_norm": 0.8040315305923249,
      "learning_rate": 2.260977116645306e-06,
      "loss": 1.2885,
      "step": 450
    },
    {
      "epoch": 0.5603448275862069,
      "grad_norm": 0.7548655355086679,
      "learning_rate": 2.2103298258668755e-06,
      "loss": 1.3115,
      "step": 455
    },
    {
      "epoch": 0.5665024630541872,
      "grad_norm": 0.7357816983542891,
      "learning_rate": 2.1598027670011427e-06,
      "loss": 1.3013,
      "step": 460
    },
    {
      "epoch": 0.5726600985221675,
      "grad_norm": 0.7152977794562079,
      "learning_rate": 2.109416912055145e-06,
      "loss": 1.2661,
      "step": 465
    },
    {
      "epoch": 0.5788177339901478,
      "grad_norm": 0.7449902853108209,
      "learning_rate": 2.0591931744271343e-06,
      "loss": 1.29,
      "step": 470
    },
    {
      "epoch": 0.5849753694581281,
      "grad_norm": 0.6971165726597337,
      "learning_rate": 2.009152400226159e-06,
      "loss": 1.3252,
      "step": 475
    },
    {
      "epoch": 0.5911330049261084,
      "grad_norm": 0.707778592285853,
      "learning_rate": 1.959315359619575e-06,
      "loss": 1.3133,
      "step": 480
    },
    {
      "epoch": 0.5972906403940886,
      "grad_norm": 0.7260676752365064,
      "learning_rate": 1.909702738212082e-06,
      "loss": 1.2915,
      "step": 485
    },
    {
      "epoch": 0.603448275862069,
      "grad_norm": 0.7872640671088219,
      "learning_rate": 1.860335128459853e-06,
      "loss": 1.2664,
      "step": 490
    },
    {
      "epoch": 0.6096059113300493,
      "grad_norm": 0.7299570473994874,
      "learning_rate": 1.8112330211233345e-06,
      "loss": 1.3039,
      "step": 495
    },
    {
      "epoch": 0.6157635467980296,
      "grad_norm": 0.6628505663907466,
      "learning_rate": 1.7624167967622435e-06,
      "loss": 1.2999,
      "step": 500
    },
    {
      "epoch": 0.6219211822660099,
      "grad_norm": 0.7138940590397398,
      "learning_rate": 1.7139067172763182e-06,
      "loss": 1.2828,
      "step": 505
    },
    {
      "epoch": 0.6280788177339901,
      "grad_norm": 0.7291370506888436,
      "learning_rate": 1.6657229174953165e-06,
      "loss": 1.2994,
      "step": 510
    },
    {
      "epoch": 0.6342364532019704,
      "grad_norm": 0.7164829111988928,
      "learning_rate": 1.6178853968217507e-06,
      "loss": 1.2856,
      "step": 515
    },
    {
      "epoch": 0.6403940886699507,
      "grad_norm": 0.7191968032340825,
      "learning_rate": 1.5704140109298446e-06,
      "loss": 1.2698,
      "step": 520
    },
    {
      "epoch": 0.646551724137931,
      "grad_norm": 0.6251465309812664,
      "learning_rate": 1.5233284635241335e-06,
      "loss": 1.2933,
      "step": 525
    },
    {
      "epoch": 0.6527093596059114,
      "grad_norm": 0.6568883358981559,
      "learning_rate": 1.4766482981611538e-06,
      "loss": 1.329,
      "step": 530
    },
    {
      "epoch": 0.6588669950738916,
      "grad_norm": 0.6556665876586427,
      "learning_rate": 1.4303928901375975e-06,
      "loss": 1.3021,
      "step": 535
    },
    {
      "epoch": 0.6650246305418719,
      "grad_norm": 0.7081746689649916,
      "learning_rate": 1.3845814384483069e-06,
      "loss": 1.2891,
      "step": 540
    },
    {
      "epoch": 0.6711822660098522,
      "grad_norm": 0.701781476378995,
      "learning_rate": 1.3392329578174495e-06,
      "loss": 1.2794,
      "step": 545
    },
    {
      "epoch": 0.6773399014778325,
      "grad_norm": 0.6824594950934834,
      "learning_rate": 1.2943662708061677e-06,
      "loss": 1.2819,
      "step": 550
    },
    {
      "epoch": 0.6834975369458128,
      "grad_norm": 0.6822805531132496,
      "learning_rate": 1.2500000000000007e-06,
      "loss": 1.2888,
      "step": 555
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 0.7121381471617909,
      "learning_rate": 1.2061525602792994e-06,
      "loss": 1.298,
      "step": 560
    },
    {
      "epoch": 0.6958128078817734,
      "grad_norm": 0.7156140232396447,
      "learning_rate": 1.1628421511758623e-06,
      "loss": 1.2879,
      "step": 565
    },
    {
      "epoch": 0.7019704433497537,
      "grad_norm": 0.6633266964663513,
      "learning_rate": 1.1200867493189418e-06,
      "loss": 1.2756,
      "step": 570
    },
    {
      "epoch": 0.708128078817734,
      "grad_norm": 0.7027669823672923,
      "learning_rate": 1.0779041009737814e-06,
      "loss": 1.2593,
      "step": 575
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.6782260773686245,
      "learning_rate": 1.036311714675766e-06,
      "loss": 1.2915,
      "step": 580
    },
    {
      "epoch": 0.7204433497536946,
      "grad_norm": 0.6853410422742611,
      "learning_rate": 9.953268539632373e-07,
      "loss": 1.2555,
      "step": 585
    },
    {
      "epoch": 0.7266009852216748,
      "grad_norm": 0.6562363208181954,
      "learning_rate": 9.549665302120146e-07,
      "loss": 1.3124,
      "step": 590
    },
    {
      "epoch": 0.7327586206896551,
      "grad_norm": 0.6576311894970724,
      "learning_rate": 9.152474955745622e-07,
      "loss": 1.2861,
      "step": 595
    },
    {
      "epoch": 0.7389162561576355,
      "grad_norm": 0.6870118556621342,
      "learning_rate": 8.761862360267637e-07,
      "loss": 1.2827,
      "step": 600
    },
    {
      "epoch": 0.7389162561576355,
      "eval_loss": 1.2938079833984375,
      "eval_runtime": 145.3232,
      "eval_samples_per_second": 159.025,
      "eval_steps_per_second": 2.491,
      "step": 600
    },
    {
      "epoch": 0.7450738916256158,
      "grad_norm": 0.6499954525297986,
      "learning_rate": 8.377989645251719e-07,
      "loss": 1.2891,
      "step": 605
    },
    {
      "epoch": 0.7512315270935961,
      "grad_norm": 0.670520502123996,
      "learning_rate": 8.001016142775788e-07,
      "loss": 1.2926,
      "step": 610
    },
    {
      "epoch": 0.7573891625615764,
      "grad_norm": 0.6283287368331439,
      "learning_rate": 7.631098321297043e-07,
      "loss": 1.2568,
      "step": 615
    },
    {
      "epoch": 0.7635467980295566,
      "grad_norm": 0.6284975248447452,
      "learning_rate": 7.26838972070737e-07,
      "loss": 1.2775,
      "step": 620
    },
    {
      "epoch": 0.7697044334975369,
      "grad_norm": 0.660893437889715,
      "learning_rate": 6.913040888604319e-07,
      "loss": 1.2773,
      "step": 625
    },
    {
      "epoch": 0.7758620689655172,
      "grad_norm": 0.6534843100770891,
      "learning_rate": 6.565199317804119e-07,
      "loss": 1.3018,
      "step": 630
    },
    {
      "epoch": 0.7820197044334976,
      "grad_norm": 0.5870111446293268,
      "learning_rate": 6.22500938512256e-07,
      "loss": 1.2605,
      "step": 635
    },
    {
      "epoch": 0.7881773399014779,
      "grad_norm": 0.6650501710983314,
      "learning_rate": 5.892612291449285e-07,
      "loss": 1.2832,
      "step": 640
    },
    {
      "epoch": 0.7943349753694581,
      "grad_norm": 0.6867995221706822,
      "learning_rate": 5.568146003140224e-07,
      "loss": 1.28,
      "step": 645
    },
    {
      "epoch": 0.8004926108374384,
      "grad_norm": 0.5896681713601163,
      "learning_rate": 5.251745194752622e-07,
      "loss": 1.2587,
      "step": 650
    },
    {
      "epoch": 0.8066502463054187,
      "grad_norm": 0.6717699104805078,
      "learning_rate": 4.943541193146359e-07,
      "loss": 1.2477,
      "step": 655
    },
    {
      "epoch": 0.812807881773399,
      "grad_norm": 0.7052198718541833,
      "learning_rate": 4.6436619229748043e-07,
      "loss": 1.2522,
      "step": 660
    },
    {
      "epoch": 0.8189655172413793,
      "grad_norm": 0.6158705019186339,
      "learning_rate": 4.352231853587763e-07,
      "loss": 1.256,
      "step": 665
    },
    {
      "epoch": 0.8251231527093597,
      "grad_norm": 0.6548358452202809,
      "learning_rate": 4.069371947368619e-07,
      "loss": 1.2963,
      "step": 670
    },
    {
      "epoch": 0.8312807881773399,
      "grad_norm": 0.6535540639408235,
      "learning_rate": 3.795199609527117e-07,
      "loss": 1.2823,
      "step": 675
    },
    {
      "epoch": 0.8374384236453202,
      "grad_norm": 0.6989573890022164,
      "learning_rate": 3.529828639368568e-07,
      "loss": 1.2919,
      "step": 680
    },
    {
      "epoch": 0.8435960591133005,
      "grad_norm": 0.6428403916541138,
      "learning_rate": 3.273369183059782e-07,
      "loss": 1.2985,
      "step": 685
    },
    {
      "epoch": 0.8497536945812808,
      "grad_norm": 0.6934651562859432,
      "learning_rate": 3.025927687911229e-07,
      "loss": 1.3011,
      "step": 690
    },
    {
      "epoch": 0.8559113300492611,
      "grad_norm": 0.6591962271180641,
      "learning_rate": 2.7876068581945195e-07,
      "loss": 1.265,
      "step": 695
    },
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 0.590195214936619,
      "learning_rate": 2.558505612513479e-07,
      "loss": 1.2809,
      "step": 700
    },
    {
      "epoch": 0.8682266009852216,
      "grad_norm": 0.6115453386704671,
      "learning_rate": 2.3387190427464817e-07,
      "loss": 1.2664,
      "step": 705
    },
    {
      "epoch": 0.874384236453202,
      "grad_norm": 0.7043010144385191,
      "learning_rate": 2.1283383745771853e-07,
      "loss": 1.2946,
      "step": 710
    },
    {
      "epoch": 0.8805418719211823,
      "grad_norm": 0.6609378479773281,
      "learning_rate": 1.9274509296299315e-07,
      "loss": 1.2976,
      "step": 715
    },
    {
      "epoch": 0.8866995073891626,
      "grad_norm": 0.6582696629201034,
      "learning_rate": 1.736140089225613e-07,
      "loss": 1.2638,
      "step": 720
    },
    {
      "epoch": 0.8928571428571429,
      "grad_norm": 0.6835787335143644,
      "learning_rate": 1.554485259773017e-07,
      "loss": 1.2738,
      "step": 725
    },
    {
      "epoch": 0.8990147783251231,
      "grad_norm": 0.662487948050227,
      "learning_rate": 1.3825618398100232e-07,
      "loss": 1.28,
      "step": 730
    },
    {
      "epoch": 0.9051724137931034,
      "grad_norm": 0.687432804005716,
      "learning_rate": 1.2204411887083072e-07,
      "loss": 1.2783,
      "step": 735
    },
    {
      "epoch": 0.9113300492610837,
      "grad_norm": 0.7021729312071676,
      "learning_rate": 1.068190597054583e-07,
      "loss": 1.2964,
      "step": 740
    },
    {
      "epoch": 0.9174876847290641,
      "grad_norm": 0.6515658253201944,
      "learning_rate": 9.25873258720636e-08,
      "loss": 1.2762,
      "step": 745
    },
    {
      "epoch": 0.9236453201970444,
      "grad_norm": 0.6550075584930779,
      "learning_rate": 7.935482446337628e-08,
      "loss": 1.2812,
      "step": 750
    },
    {
      "epoch": 0.9298029556650246,
      "grad_norm": 0.6848726797074379,
      "learning_rate": 6.712704782585206e-08,
      "loss": 1.2735,
      "step": 755
    },
    {
      "epoch": 0.9359605911330049,
      "grad_norm": 0.6302612182103497,
      "learning_rate": 5.590907127999173e-08,
      "loss": 1.2659,
      "step": 760
    },
    {
      "epoch": 0.9421182266009852,
      "grad_norm": 0.6297453401962552,
      "learning_rate": 4.570555101375357e-08,
      "loss": 1.2616,
      "step": 765
    },
    {
      "epoch": 0.9482758620689655,
      "grad_norm": 0.6875738096430432,
      "learning_rate": 3.652072214993335e-08,
      "loss": 1.2823,
      "step": 770
    },
    {
      "epoch": 0.9544334975369458,
      "grad_norm": 0.6691771389169094,
      "learning_rate": 2.8358396988315272e-08,
      "loss": 1.2823,
      "step": 775
    },
    {
      "epoch": 0.9605911330049262,
      "grad_norm": 0.6162495535352837,
      "learning_rate": 2.122196342331767e-08,
      "loss": 1.2605,
      "step": 780
    },
    {
      "epoch": 0.9667487684729064,
      "grad_norm": 0.6765789960335756,
      "learning_rate": 1.511438353779898e-08,
      "loss": 1.2758,
      "step": 785
    },
    {
      "epoch": 0.9729064039408867,
      "grad_norm": 0.6926059474276152,
      "learning_rate": 1.0038192373600652e-08,
      "loss": 1.2591,
      "step": 790
    },
    {
      "epoch": 0.979064039408867,
      "grad_norm": 0.6413165173071386,
      "learning_rate": 5.995496879339924e-09,
      "loss": 1.2875,
      "step": 795
    },
    {
      "epoch": 0.9852216748768473,
      "grad_norm": 0.6372683334165604,
      "learning_rate": 2.9879750358896565e-09,
      "loss": 1.2807,
      "step": 800
    },
    {
      "epoch": 0.9852216748768473,
      "eval_loss": 1.2902166843414307,
      "eval_runtime": 145.3653,
      "eval_samples_per_second": 158.979,
      "eval_steps_per_second": 2.49,
      "step": 800
    },
    {
      "epoch": 0.9913793103448276,
      "grad_norm": 0.5963019194626616,
      "learning_rate": 1.0168751599085035e-09,
      "loss": 1.2782,
      "step": 805
    },
    {
      "epoch": 0.9975369458128078,
      "grad_norm": 0.6176142023053375,
      "learning_rate": 8.301538570676393e-11,
      "loss": 1.2582,
      "step": 810
    },
    {
      "epoch": 1.0,
      "step": 812,
      "total_flos": 277556883980288.0,
      "train_loss": 1.458759990231744,
      "train_runtime": 5428.2383,
      "train_samples_per_second": 38.293,
      "train_steps_per_second": 0.15
    }
  ],
  "logging_steps": 5,
  "max_steps": 812,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 277556883980288.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}