{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 733,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0068212824010914054,
      "grad_norm": 1.8668294015888436,
      "learning_rate": 5.405405405405406e-06,
      "loss": 0.8522,
      "num_tokens": 3759146.0,
      "step": 5
    },
    {
      "epoch": 0.013642564802182811,
      "grad_norm": 1.7247561733323398,
      "learning_rate": 1.2162162162162164e-05,
      "loss": 0.8047,
      "num_tokens": 7668808.0,
      "step": 10
    },
    {
      "epoch": 0.020463847203274217,
      "grad_norm": 0.6872174146885504,
      "learning_rate": 1.891891891891892e-05,
      "loss": 0.7189,
      "num_tokens": 11368873.0,
      "step": 15
    },
    {
      "epoch": 0.027285129604365622,
      "grad_norm": 0.5588637904556512,
      "learning_rate": 2.5675675675675675e-05,
      "loss": 0.6772,
      "num_tokens": 15118063.0,
      "step": 20
    },
    {
      "epoch": 0.034106412005457026,
      "grad_norm": 0.48706663235585207,
      "learning_rate": 3.2432432432432436e-05,
      "loss": 0.6547,
      "num_tokens": 18906839.0,
      "step": 25
    },
    {
      "epoch": 0.040927694406548434,
      "grad_norm": 0.41592123514427665,
      "learning_rate": 3.918918918918919e-05,
      "loss": 0.6323,
      "num_tokens": 22641755.0,
      "step": 30
    },
    {
      "epoch": 0.047748976807639835,
      "grad_norm": 0.3867404332753348,
      "learning_rate": 4.594594594594595e-05,
      "loss": 0.6278,
      "num_tokens": 26636629.0,
      "step": 35
    },
    {
      "epoch": 0.054570259208731244,
      "grad_norm": 0.3950136717548598,
      "learning_rate": 4.999908316574644e-05,
      "loss": 0.5973,
      "num_tokens": 30417967.0,
      "step": 40
    },
    {
      "epoch": 0.061391541609822645,
      "grad_norm": 0.3834643196131725,
      "learning_rate": 4.998876963847189e-05,
      "loss": 0.6004,
      "num_tokens": 34231333.0,
      "step": 45
    },
    {
      "epoch": 0.06821282401091405,
      "grad_norm": 0.39680969782340475,
      "learning_rate": 4.996700181165029e-05,
      "loss": 0.6002,
      "num_tokens": 37961424.0,
      "step": 50
    },
    {
      "epoch": 0.07503410641200546,
      "grad_norm": 0.3896173679223876,
      "learning_rate": 4.993379077238036e-05,
      "loss": 0.6008,
      "num_tokens": 41826860.0,
      "step": 55
    },
    {
      "epoch": 0.08185538881309687,
      "grad_norm": 0.4410876468603876,
      "learning_rate": 4.9889153436180295e-05,
      "loss": 0.5886,
      "num_tokens": 45543403.0,
      "step": 60
    },
    {
      "epoch": 0.08867667121418826,
      "grad_norm": 0.4175155873268927,
      "learning_rate": 4.983311253837213e-05,
      "loss": 0.5925,
      "num_tokens": 49369486.0,
      "step": 65
    },
    {
      "epoch": 0.09549795361527967,
      "grad_norm": 0.3764686151294453,
      "learning_rate": 4.9765696622501846e-05,
      "loss": 0.5819,
      "num_tokens": 53010874.0,
      "step": 70
    },
    {
      "epoch": 0.10231923601637108,
      "grad_norm": 0.4049946590100178,
      "learning_rate": 4.968694002580118e-05,
      "loss": 0.5841,
      "num_tokens": 56909889.0,
      "step": 75
    },
    {
      "epoch": 0.10914051841746249,
      "grad_norm": 0.446913495697233,
      "learning_rate": 4.959688286169851e-05,
      "loss": 0.5677,
      "num_tokens": 60650570.0,
      "step": 80
    },
    {
      "epoch": 0.11596180081855388,
      "grad_norm": 0.4622857509436459,
      "learning_rate": 4.9495570999387685e-05,
      "loss": 0.5616,
      "num_tokens": 64564660.0,
      "step": 85
    },
    {
      "epoch": 0.12278308321964529,
      "grad_norm": 0.4804240442830647,
      "learning_rate": 4.9383056040465276e-05,
      "loss": 0.5796,
      "num_tokens": 68426882.0,
      "step": 90
    },
    {
      "epoch": 0.1296043656207367,
      "grad_norm": 0.35820565417638384,
      "learning_rate": 4.925939529264815e-05,
      "loss": 0.575,
      "num_tokens": 72252819.0,
      "step": 95
    },
    {
      "epoch": 0.1364256480218281,
      "grad_norm": 0.38001556309086676,
      "learning_rate": 4.9124651740584684e-05,
      "loss": 0.5613,
      "num_tokens": 76160914.0,
      "step": 100
    },
    {
      "epoch": 0.1432469304229195,
      "grad_norm": 0.3927183537086537,
      "learning_rate": 4.897889401377447e-05,
      "loss": 0.563,
      "num_tokens": 80152955.0,
      "step": 105
    },
    {
      "epoch": 0.15006821282401092,
      "grad_norm": 0.3272034222934781,
      "learning_rate": 4.882219635161306e-05,
      "loss": 0.5667,
      "num_tokens": 83901702.0,
      "step": 110
    },
    {
      "epoch": 0.15688949522510232,
      "grad_norm": 0.41975494955869247,
      "learning_rate": 4.865463856557922e-05,
      "loss": 0.5655,
      "num_tokens": 87691018.0,
      "step": 115
    },
    {
      "epoch": 0.16371077762619374,
      "grad_norm": 0.36316853341182537,
      "learning_rate": 4.847630599858426e-05,
      "loss": 0.5546,
      "num_tokens": 91542428.0,
      "step": 120
    },
    {
      "epoch": 0.17053206002728513,
      "grad_norm": 0.34879469561207194,
      "learning_rate": 4.8287289481503954e-05,
      "loss": 0.5616,
      "num_tokens": 95438170.0,
      "step": 125
    },
    {
      "epoch": 0.17735334242837653,
      "grad_norm": 0.4026771690396351,
      "learning_rate": 4.8087685286915276e-05,
      "loss": 0.5572,
      "num_tokens": 99383692.0,
      "step": 130
    },
    {
      "epoch": 0.18417462482946795,
      "grad_norm": 0.3893249591588555,
      "learning_rate": 4.787759508006147e-05,
      "loss": 0.5568,
      "num_tokens": 103223537.0,
      "step": 135
    },
    {
      "epoch": 0.19099590723055934,
      "grad_norm": 0.4315296747644332,
      "learning_rate": 4.765712586707048e-05,
      "loss": 0.5695,
      "num_tokens": 106901687.0,
      "step": 140
    },
    {
      "epoch": 0.19781718963165076,
      "grad_norm": 0.39972341830792835,
      "learning_rate": 4.7426389940453065e-05,
      "loss": 0.5419,
      "num_tokens": 110840758.0,
      "step": 145
    },
    {
      "epoch": 0.20463847203274216,
      "grad_norm": 0.4054705248088257,
      "learning_rate": 4.718550482190837e-05,
      "loss": 0.5578,
      "num_tokens": 114521504.0,
      "step": 150
    },
    {
      "epoch": 0.21145975443383355,
      "grad_norm": 0.3452594231320418,
      "learning_rate": 4.6934593202466127e-05,
      "loss": 0.5425,
      "num_tokens": 118445759.0,
      "step": 155
    },
    {
      "epoch": 0.21828103683492497,
      "grad_norm": 0.3579220823187385,
      "learning_rate": 4.6673782879995896e-05,
      "loss": 0.5511,
      "num_tokens": 122311693.0,
      "step": 160
    },
    {
      "epoch": 0.22510231923601637,
      "grad_norm": 0.339431264329542,
      "learning_rate": 4.640320669411526e-05,
      "loss": 0.554,
      "num_tokens": 126094524.0,
      "step": 165
    },
    {
      "epoch": 0.23192360163710776,
      "grad_norm": 0.34913345943773244,
      "learning_rate": 4.612300245853004e-05,
      "loss": 0.5473,
      "num_tokens": 129971056.0,
      "step": 170
    },
    {
      "epoch": 0.23874488403819918,
      "grad_norm": 0.43872271001871566,
      "learning_rate": 4.5833312890841085e-05,
      "loss": 0.562,
      "num_tokens": 133765982.0,
      "step": 175
    },
    {
      "epoch": 0.24556616643929058,
      "grad_norm": 0.38820616445153877,
      "learning_rate": 4.553428553985329e-05,
      "loss": 0.5418,
      "num_tokens": 137522281.0,
      "step": 180
    },
    {
      "epoch": 0.252387448840382,
      "grad_norm": 0.3850943617783079,
      "learning_rate": 4.522607271042399e-05,
      "loss": 0.5367,
      "num_tokens": 141196084.0,
      "step": 185
    },
    {
      "epoch": 0.2592087312414734,
      "grad_norm": 0.43093540895662497,
      "learning_rate": 4.490883138588882e-05,
      "loss": 0.548,
      "num_tokens": 145136704.0,
      "step": 190
    },
    {
      "epoch": 0.2660300136425648,
      "grad_norm": 0.31524529627859765,
      "learning_rate": 4.458272314810479e-05,
      "loss": 0.5358,
      "num_tokens": 148940122.0,
      "step": 195
    },
    {
      "epoch": 0.2728512960436562,
      "grad_norm": 0.2904592177300161,
      "learning_rate": 4.4247914095151086e-05,
      "loss": 0.5457,
      "num_tokens": 152809678.0,
      "step": 200
    },
    {
      "epoch": 0.27967257844474763,
      "grad_norm": 0.3751845422333264,
      "learning_rate": 4.390457475672966e-05,
      "loss": 0.5394,
      "num_tokens": 156683573.0,
      "step": 205
    },
    {
      "epoch": 0.286493860845839,
      "grad_norm": 0.342531691115598,
      "learning_rate": 4.35528800073086e-05,
      "loss": 0.5408,
      "num_tokens": 160433326.0,
      "step": 210
    },
    {
      "epoch": 0.2933151432469304,
      "grad_norm": 0.34186298656605696,
      "learning_rate": 4.31930089770526e-05,
      "loss": 0.5443,
      "num_tokens": 164374316.0,
      "step": 215
    },
    {
      "epoch": 0.30013642564802184,
      "grad_norm": 0.34482043458760203,
      "learning_rate": 4.282514496058582e-05,
      "loss": 0.5238,
      "num_tokens": 168223299.0,
      "step": 220
    },
    {
      "epoch": 0.3069577080491132,
      "grad_norm": 0.2983303840923811,
      "learning_rate": 4.24494753236337e-05,
      "loss": 0.5365,
      "num_tokens": 172132000.0,
      "step": 225
    },
    {
      "epoch": 0.31377899045020463,
      "grad_norm": 0.3212490155633752,
      "learning_rate": 4.2066191407591125e-05,
      "loss": 0.5321,
      "num_tokens": 176086331.0,
      "step": 230
    },
    {
      "epoch": 0.32060027285129605,
      "grad_norm": 0.2893257104319784,
      "learning_rate": 4.1675488432065785e-05,
      "loss": 0.5244,
      "num_tokens": 179917640.0,
      "step": 235
    },
    {
      "epoch": 0.3274215552523875,
      "grad_norm": 0.2812328798873313,
      "learning_rate": 4.127756539544609e-05,
      "loss": 0.5369,
      "num_tokens": 183746129.0,
      "step": 240
    },
    {
      "epoch": 0.33424283765347884,
      "grad_norm": 0.36334234919110503,
      "learning_rate": 4.087262497354452e-05,
      "loss": 0.5454,
      "num_tokens": 187699370.0,
      "step": 245
    },
    {
      "epoch": 0.34106412005457026,
      "grad_norm": 0.3002376113285202,
      "learning_rate": 4.046087341636789e-05,
      "loss": 0.5279,
      "num_tokens": 191512142.0,
      "step": 250
    },
    {
      "epoch": 0.3478854024556617,
      "grad_norm": 0.304509691483118,
      "learning_rate": 4.0042520443067176e-05,
      "loss": 0.5292,
      "num_tokens": 195367749.0,
      "step": 255
    },
    {
      "epoch": 0.35470668485675305,
      "grad_norm": 0.31090228382258317,
      "learning_rate": 3.961777913512035e-05,
      "loss": 0.5182,
      "num_tokens": 199215371.0,
      "step": 260
    },
    {
      "epoch": 0.3615279672578445,
      "grad_norm": 0.294458994836171,
      "learning_rate": 3.9186865827802724e-05,
      "loss": 0.5377,
      "num_tokens": 202903048.0,
      "step": 265
    },
    {
      "epoch": 0.3683492496589359,
      "grad_norm": 0.307801938345619,
      "learning_rate": 3.875e-05,
      "loss": 0.5265,
      "num_tokens": 206761213.0,
      "step": 270
    },
    {
      "epoch": 0.37517053206002726,
      "grad_norm": 0.28539346006440874,
      "learning_rate": 3.830740416242014e-05,
      "loss": 0.5224,
      "num_tokens": 210585632.0,
      "step": 275
    },
    {
      "epoch": 0.3819918144611187,
      "grad_norm": 0.3027425175055548,
      "learning_rate": 3.7859303744261064e-05,
      "loss": 0.5282,
      "num_tokens": 214261738.0,
      "step": 280
    },
    {
      "epoch": 0.3888130968622101,
      "grad_norm": 0.277979061330346,
      "learning_rate": 3.740592697839185e-05,
      "loss": 0.533,
      "num_tokens": 218144024.0,
      "step": 285
    },
    {
      "epoch": 0.3956343792633015,
      "grad_norm": 0.2666174933047264,
      "learning_rate": 3.694750478510596e-05,
      "loss": 0.5285,
      "num_tokens": 222057295.0,
      "step": 290
    },
    {
      "epoch": 0.4024556616643929,
      "grad_norm": 0.26713129985891826,
      "learning_rate": 3.648427065450555e-05,
      "loss": 0.5197,
      "num_tokens": 225828573.0,
      "step": 295
    },
    {
      "epoch": 0.4092769440654843,
      "grad_norm": 0.2837840653374091,
      "learning_rate": 3.601646052757707e-05,
      "loss": 0.519,
      "num_tokens": 229710487.0,
      "step": 300
    },
    {
      "epoch": 0.41609822646657574,
      "grad_norm": 0.3141969043403706,
      "learning_rate": 3.55443126760184e-05,
      "loss": 0.5344,
      "num_tokens": 233617525.0,
      "step": 305
    },
    {
      "epoch": 0.4229195088676671,
      "grad_norm": 0.3386995775152564,
      "learning_rate": 3.506806758087894e-05,
      "loss": 0.532,
      "num_tokens": 237394471.0,
      "step": 310
    },
    {
      "epoch": 0.4297407912687585,
      "grad_norm": 0.3127602717198287,
      "learning_rate": 3.458796781007437e-05,
      "loss": 0.5267,
      "num_tokens": 241114261.0,
      "step": 315
    },
    {
      "epoch": 0.43656207366984995,
      "grad_norm": 0.2844786515151641,
      "learning_rate": 3.410425789483854e-05,
      "loss": 0.527,
      "num_tokens": 244967987.0,
      "step": 320
    },
    {
      "epoch": 0.4433833560709413,
      "grad_norm": 0.28761389844710167,
      "learning_rate": 3.3617184205175304e-05,
      "loss": 0.5335,
      "num_tokens": 248751095.0,
      "step": 325
    },
    {
      "epoch": 0.45020463847203274,
      "grad_norm": 0.3411941605718103,
      "learning_rate": 3.312699482437392e-05,
      "loss": 0.5207,
      "num_tokens": 252607265.0,
      "step": 330
    },
    {
      "epoch": 0.45702592087312416,
      "grad_norm": 0.29578624804206416,
      "learning_rate": 3.263393942265168e-05,
      "loss": 0.5274,
      "num_tokens": 256417909.0,
      "step": 335
    },
    {
      "epoch": 0.4638472032742155,
      "grad_norm": 0.25727525654305566,
      "learning_rate": 3.213826912998838e-05,
      "loss": 0.5199,
      "num_tokens": 260456429.0,
      "step": 340
    },
    {
      "epoch": 0.47066848567530695,
      "grad_norm": 0.26795472413546734,
      "learning_rate": 3.164023640821719e-05,
      "loss": 0.5132,
      "num_tokens": 264287905.0,
      "step": 345
    },
    {
      "epoch": 0.47748976807639837,
      "grad_norm": 0.2755134604375614,
      "learning_rate": 3.114009492243721e-05,
      "loss": 0.5216,
      "num_tokens": 268098790.0,
      "step": 350
    },
    {
      "epoch": 0.4843110504774898,
      "grad_norm": 0.284559174162564,
      "learning_rate": 3.063809941181321e-05,
      "loss": 0.5312,
      "num_tokens": 271974065.0,
      "step": 355
    },
    {
      "epoch": 0.49113233287858116,
      "grad_norm": 0.2826715777966556,
      "learning_rate": 3.0134505559828203e-05,
      "loss": 0.5349,
      "num_tokens": 275852045.0,
      "step": 360
    },
    {
      "epoch": 0.4979536152796726,
      "grad_norm": 0.28035063155455164,
      "learning_rate": 2.9629569864055125e-05,
      "loss": 0.5129,
      "num_tokens": 279504484.0,
      "step": 365
    },
    {
      "epoch": 0.504774897680764,
      "grad_norm": 0.2703017488821357,
      "learning_rate": 2.9123549505513868e-05,
      "loss": 0.515,
      "num_tokens": 283461546.0,
      "step": 370
    },
    {
      "epoch": 0.5115961800818554,
      "grad_norm": 0.2628579990890393,
      "learning_rate": 2.8616702217680134e-05,
      "loss": 0.523,
      "num_tokens": 287371918.0,
      "step": 375
    },
    {
      "epoch": 0.5184174624829468,
      "grad_norm": 0.27329779308736485,
      "learning_rate": 2.810928615521303e-05,
      "loss": 0.5096,
      "num_tokens": 291057738.0,
      "step": 380
    },
    {
      "epoch": 0.5252387448840382,
      "grad_norm": 0.2799338468541636,
      "learning_rate": 2.7601559762468022e-05,
      "loss": 0.5188,
      "num_tokens": 294881963.0,
      "step": 385
    },
    {
      "epoch": 0.5320600272851296,
      "grad_norm": 0.27380554160394205,
      "learning_rate": 2.7093781641862387e-05,
      "loss": 0.5213,
      "num_tokens": 298677895.0,
      "step": 390
    },
    {
      "epoch": 0.538881309686221,
      "grad_norm": 0.2686509612309849,
      "learning_rate": 2.658621042216021e-05,
      "loss": 0.5056,
      "num_tokens": 302387985.0,
      "step": 395
    },
    {
      "epoch": 0.5457025920873124,
      "grad_norm": 0.2842485971285363,
      "learning_rate": 2.6079104626743845e-05,
      "loss": 0.5272,
      "num_tokens": 306130593.0,
      "step": 400
    },
    {
      "epoch": 0.5525238744884038,
      "grad_norm": 0.28769823956802704,
      "learning_rate": 2.5572722541939113e-05,
      "loss": 0.5251,
      "num_tokens": 309952008.0,
      "step": 405
    },
    {
      "epoch": 0.5593451568894953,
      "grad_norm": 0.3105490408472939,
      "learning_rate": 2.5067322085461315e-05,
      "loss": 0.5105,
      "num_tokens": 313725489.0,
      "step": 410
    },
    {
      "epoch": 0.5661664392905866,
      "grad_norm": 0.3152229637314721,
      "learning_rate": 2.4563160675048846e-05,
      "loss": 0.5156,
      "num_tokens": 317525148.0,
      "step": 415
    },
    {
      "epoch": 0.572987721691678,
      "grad_norm": 0.27095198422631994,
      "learning_rate": 2.406049509735156e-05,
      "loss": 0.5154,
      "num_tokens": 321410101.0,
      "step": 420
    },
    {
      "epoch": 0.5798090040927695,
      "grad_norm": 0.28829256667797254,
      "learning_rate": 2.355958137714056e-05,
      "loss": 0.5108,
      "num_tokens": 325102278.0,
      "step": 425
    },
    {
      "epoch": 0.5866302864938608,
      "grad_norm": 0.270087706114446,
      "learning_rate": 2.3060674646906004e-05,
      "loss": 0.5155,
      "num_tokens": 328831071.0,
      "step": 430
    },
    {
      "epoch": 0.5934515688949522,
      "grad_norm": 0.3056808295329074,
      "learning_rate": 2.2564029016909416e-05,
      "loss": 0.5049,
      "num_tokens": 332767044.0,
      "step": 435
    },
    {
      "epoch": 0.6002728512960437,
      "grad_norm": 0.2692565018339337,
      "learning_rate": 2.2069897445756627e-05,
      "loss": 0.5027,
      "num_tokens": 336595638.0,
      "step": 440
    },
    {
      "epoch": 0.607094133697135,
      "grad_norm": 0.26184698283909275,
      "learning_rate": 2.1578531611557322e-05,
      "loss": 0.5157,
      "num_tokens": 340358925.0,
      "step": 445
    },
    {
      "epoch": 0.6139154160982264,
      "grad_norm": 0.23620479720611628,
      "learning_rate": 2.109018178373675e-05,
      "loss": 0.5146,
      "num_tokens": 344239058.0,
      "step": 450
    },
    {
      "epoch": 0.6207366984993179,
      "grad_norm": 0.25416857859214803,
      "learning_rate": 2.0605096695564973e-05,
      "loss": 0.5181,
      "num_tokens": 348080585.0,
      "step": 455
    },
    {
      "epoch": 0.6275579809004093,
      "grad_norm": 0.24514832467763423,
      "learning_rate": 2.0123523417468466e-05,
      "loss": 0.5114,
      "num_tokens": 351817695.0,
      "step": 460
    },
    {
      "epoch": 0.6343792633015006,
      "grad_norm": 0.24280253507668187,
      "learning_rate": 1.9645707231188742e-05,
      "loss": 0.5058,
      "num_tokens": 355639183.0,
      "step": 465
    },
    {
      "epoch": 0.6412005457025921,
      "grad_norm": 0.23500875387840528,
      "learning_rate": 1.9171891504851925e-05,
      "loss": 0.5244,
      "num_tokens": 359437581.0,
      "step": 470
    },
    {
      "epoch": 0.6480218281036835,
      "grad_norm": 0.2527982888228135,
      "learning_rate": 1.8702317569013094e-05,
      "loss": 0.5005,
      "num_tokens": 363189983.0,
      "step": 475
    },
    {
      "epoch": 0.654843110504775,
      "grad_norm": 0.22972404549026726,
      "learning_rate": 1.8237224593738327e-05,
      "loss": 0.5026,
      "num_tokens": 366863209.0,
      "step": 480
    },
    {
      "epoch": 0.6616643929058663,
      "grad_norm": 0.2257095506043247,
      "learning_rate": 1.7776849466787223e-05,
      "loss": 0.517,
      "num_tokens": 370725860.0,
      "step": 485
    },
    {
      "epoch": 0.6684856753069577,
      "grad_norm": 0.23299272252976405,
      "learning_rate": 1.7321426672957896e-05,
      "loss": 0.5025,
      "num_tokens": 374566515.0,
      "step": 490
    },
    {
      "epoch": 0.6753069577080492,
      "grad_norm": 0.2553261303731692,
      "learning_rate": 1.6871188174655787e-05,
      "loss": 0.4957,
      "num_tokens": 378330489.0,
      "step": 495
    },
    {
      "epoch": 0.6821282401091405,
      "grad_norm": 0.2350930551306658,
      "learning_rate": 1.6426363293747334e-05,
      "loss": 0.5,
      "num_tokens": 382103468.0,
      "step": 500
    },
    {
      "epoch": 0.6889495225102319,
      "grad_norm": 0.24017067646649592,
      "learning_rate": 1.598717859475846e-05,
      "loss": 0.5086,
      "num_tokens": 385837297.0,
      "step": 505
    },
    {
      "epoch": 0.6957708049113234,
      "grad_norm": 0.24082986222057906,
      "learning_rate": 1.5553857769477553e-05,
      "loss": 0.5055,
      "num_tokens": 389586680.0,
      "step": 510
    },
    {
      "epoch": 0.7025920873124147,
      "grad_norm": 0.22863149957641887,
      "learning_rate": 1.5126621523021518e-05,
      "loss": 0.51,
      "num_tokens": 393428760.0,
      "step": 515
    },
    {
      "epoch": 0.7094133697135061,
      "grad_norm": 0.2622703448542487,
      "learning_rate": 1.4705687461423209e-05,
      "loss": 0.5221,
      "num_tokens": 397158700.0,
      "step": 520
    },
    {
      "epoch": 0.7162346521145976,
      "grad_norm": 0.24484237745692367,
      "learning_rate": 1.4291269980797139e-05,
      "loss": 0.5064,
      "num_tokens": 400923938.0,
      "step": 525
    },
    {
      "epoch": 0.723055934515689,
      "grad_norm": 0.22718569377185907,
      "learning_rate": 1.3883580158140291e-05,
      "loss": 0.5004,
      "num_tokens": 404685655.0,
      "step": 530
    },
    {
      "epoch": 0.7298772169167803,
      "grad_norm": 0.21525244113290895,
      "learning_rate": 1.3482825643823293e-05,
      "loss": 0.5061,
      "num_tokens": 408582799.0,
      "step": 535
    },
    {
      "epoch": 0.7366984993178718,
      "grad_norm": 0.22015694564703406,
      "learning_rate": 1.3089210555827086e-05,
      "loss": 0.5118,
      "num_tokens": 412386009.0,
      "step": 540
    },
    {
      "epoch": 0.7435197817189632,
      "grad_norm": 0.21495348315883733,
      "learning_rate": 1.270293537577855e-05,
      "loss": 0.5148,
      "num_tokens": 416372039.0,
      "step": 545
    },
    {
      "epoch": 0.7503410641200545,
      "grad_norm": 0.21838158349042594,
      "learning_rate": 1.232419684683844e-05,
      "loss": 0.4994,
      "num_tokens": 420051975.0,
      "step": 550
    },
    {
      "epoch": 0.757162346521146,
      "grad_norm": 0.2258119025998525,
      "learning_rate": 1.1953187873493303e-05,
      "loss": 0.5,
      "num_tokens": 423685709.0,
      "step": 555
    },
    {
      "epoch": 0.7639836289222374,
      "grad_norm": 0.22849400778538187,
      "learning_rate": 1.1590097423302684e-05,
      "loss": 0.4959,
      "num_tokens": 427405904.0,
      "step": 560
    },
    {
      "epoch": 0.7708049113233287,
      "grad_norm": 0.21958667856965727,
      "learning_rate": 1.1235110430651421e-05,
      "loss": 0.496,
      "num_tokens": 431288378.0,
      "step": 565
    },
    {
      "epoch": 0.7776261937244202,
      "grad_norm": 0.23913373520191775,
      "learning_rate": 1.0888407702556284e-05,
      "loss": 0.4998,
      "num_tokens": 435077995.0,
      "step": 570
    },
    {
      "epoch": 0.7844474761255116,
      "grad_norm": 0.2417353603062665,
      "learning_rate": 1.0550165826574766e-05,
      "loss": 0.4996,
      "num_tokens": 439006864.0,
      "step": 575
    },
    {
      "epoch": 0.791268758526603,
      "grad_norm": 0.23732321207266466,
      "learning_rate": 1.0220557080862985e-05,
      "loss": 0.5149,
      "num_tokens": 443045688.0,
      "step": 580
    },
    {
      "epoch": 0.7980900409276944,
      "grad_norm": 0.21571934880634502,
      "learning_rate": 9.899749346428556e-06,
      "loss": 0.502,
      "num_tokens": 446852018.0,
      "step": 585
    },
    {
      "epoch": 0.8049113233287858,
      "grad_norm": 0.21078457513071117,
      "learning_rate": 9.587906021623016e-06,
      "loss": 0.5161,
      "num_tokens": 450687287.0,
      "step": 590
    },
    {
      "epoch": 0.8117326057298773,
      "grad_norm": 0.23441605543875263,
      "learning_rate": 9.28518593891749e-06,
      "loss": 0.5013,
      "num_tokens": 454483896.0,
      "step": 595
    },
    {
      "epoch": 0.8185538881309686,
      "grad_norm": 0.22384719028240002,
      "learning_rate": 8.99174328400385e-06,
      "loss": 0.4997,
      "num_tokens": 458325861.0,
      "step": 600
    },
    {
      "epoch": 0.82537517053206,
      "grad_norm": 0.22941845619820603,
      "learning_rate": 8.707727517262697e-06,
      "loss": 0.5049,
      "num_tokens": 462055868.0,
      "step": 605
    },
    {
      "epoch": 0.8321964529331515,
      "grad_norm": 0.2138256278956969,
      "learning_rate": 8.433283297638053e-06,
      "loss": 0.4992,
      "num_tokens": 465973876.0,
      "step": 610
    },
    {
      "epoch": 0.8390177353342428,
      "grad_norm": 0.2181701942086996,
      "learning_rate": 8.168550408957632e-06,
      "loss": 0.4969,
      "num_tokens": 469791498.0,
      "step": 615
    },
    {
      "epoch": 0.8458390177353342,
      "grad_norm": 0.23101261117117852,
      "learning_rate": 7.91366368873613e-06,
      "loss": 0.4944,
      "num_tokens": 473570581.0,
      "step": 620
    },
    {
      "epoch": 0.8526603001364257,
      "grad_norm": 0.2269150903338963,
      "learning_rate": 7.66875295949791e-06,
      "loss": 0.5104,
      "num_tokens": 477401353.0,
      "step": 625
    },
    {
      "epoch": 0.859481582537517,
      "grad_norm": 0.20575953421081028,
      "learning_rate": 7.4339429626539e-06,
      "loss": 0.5102,
      "num_tokens": 481348892.0,
      "step": 630
    },
    {
      "epoch": 0.8663028649386084,
      "grad_norm": 0.23001645269035356,
      "learning_rate": 7.2093532949665715e-06,
      "loss": 0.508,
      "num_tokens": 485171910.0,
      "step": 635
    },
    {
      "epoch": 0.8731241473396999,
      "grad_norm": 0.20665497327246388,
      "learning_rate": 6.995098347635173e-06,
      "loss": 0.4933,
      "num_tokens": 489059548.0,
      "step": 640
    },
    {
      "epoch": 0.8799454297407913,
      "grad_norm": 0.2107190957471263,
      "learning_rate": 6.791287248032431e-06,
      "loss": 0.4966,
      "num_tokens": 492893029.0,
      "step": 645
    },
    {
      "epoch": 0.8867667121418826,
      "grad_norm": 0.21555765697326154,
      "learning_rate": 6.598023804122194e-06,
      "loss": 0.5038,
      "num_tokens": 496905674.0,
      "step": 650
    },
    {
      "epoch": 0.8935879945429741,
      "grad_norm": 0.20368978219391987,
      "learning_rate": 6.415406451586528e-06,
      "loss": 0.4993,
      "num_tokens": 500864542.0,
      "step": 655
    },
    {
      "epoch": 0.9004092769440655,
      "grad_norm": 0.20685793759893298,
      "learning_rate": 6.243528203689025e-06,
      "loss": 0.5032,
      "num_tokens": 504810366.0,
      "step": 660
    },
    {
      "epoch": 0.9072305593451568,
      "grad_norm": 0.2171382169840262,
      "learning_rate": 6.0824766039e-06,
      "loss": 0.4993,
      "num_tokens": 508607232.0,
      "step": 665
    },
    {
      "epoch": 0.9140518417462483,
      "grad_norm": 0.20991074132493198,
      "learning_rate": 5.932333681307571e-06,
      "loss": 0.5061,
      "num_tokens": 512474084.0,
      "step": 670
    },
    {
      "epoch": 0.9208731241473397,
      "grad_norm": 0.20428584534232572,
      "learning_rate": 5.793175908837471e-06,
      "loss": 0.4967,
      "num_tokens": 516216104.0,
      "step": 675
    },
    {
      "epoch": 0.927694406548431,
      "grad_norm": 0.2064710377018979,
      "learning_rate": 5.665074164302742e-06,
      "loss": 0.5064,
      "num_tokens": 519966345.0,
      "step": 680
    },
    {
      "epoch": 0.9345156889495225,
      "grad_norm": 0.19447312445035328,
      "learning_rate": 5.548093694303275e-06,
      "loss": 0.4918,
      "num_tokens": 523793837.0,
      "step": 685
    },
    {
      "epoch": 0.9413369713506139,
      "grad_norm": 0.2192489932913614,
      "learning_rate": 5.442294080993446e-06,
      "loss": 0.5059,
      "num_tokens": 527666864.0,
      "step": 690
    },
    {
      "epoch": 0.9481582537517054,
      "grad_norm": 0.20348081993445674,
      "learning_rate": 5.347729211734919e-06,
      "loss": 0.5033,
      "num_tokens": 531466359.0,
      "step": 695
    },
    {
      "epoch": 0.9549795361527967,
      "grad_norm": 0.20065081837919563,
      "learning_rate": 5.264447251649954e-06,
      "loss": 0.5057,
      "num_tokens": 535253217.0,
      "step": 700
    },
    {
      "epoch": 0.9618008185538881,
      "grad_norm": 0.20438831920445003,
      "learning_rate": 5.192490619089267e-06,
      "loss": 0.4899,
      "num_tokens": 539137436.0,
      "step": 705
    },
    {
      "epoch": 0.9686221009549796,
      "grad_norm": 0.20651528762536564,
      "learning_rate": 5.1318959640269095e-06,
      "loss": 0.5004,
      "num_tokens": 542824098.0,
      "step": 710
    },
    {
      "epoch": 0.975443383356071,
      "grad_norm": 0.21211108490688485,
      "learning_rate": 5.082694149393189e-06,
      "loss": 0.5113,
      "num_tokens": 546578047.0,
      "step": 715
    },
    {
      "epoch": 0.9822646657571623,
      "grad_norm": 0.20432801642340406,
      "learning_rate": 5.044910235355121e-06,
      "loss": 0.4974,
      "num_tokens": 550377811.0,
      "step": 720
    },
    {
      "epoch": 0.9890859481582538,
      "grad_norm": 0.19342130410850406,
      "learning_rate": 5.0185634665524255e-06,
      "loss": 0.4933,
      "num_tokens": 554224024.0,
      "step": 725
    },
    {
      "epoch": 0.9959072305593452,
      "grad_norm": 0.19321818042549108,
      "learning_rate": 5.003667262295572e-06,
      "loss": 0.5014,
      "num_tokens": 558001366.0,
      "step": 730
    },
    {
      "epoch": 1.0,
      "num_tokens": 560311272.0,
      "step": 733,
      "total_flos": 1147472759488512.0,
      "train_loss": 0.5344447073149323,
      "train_runtime": 5883.7745,
      "train_samples_per_second": 15.931,
      "train_steps_per_second": 0.125
    }
  ],
  "logging_steps": 5,
  "max_steps": 733,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1147472759488512.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}