{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9990766389658357,
  "eval_steps": 500,
  "global_step": 541,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018467220683287165,
      "grad_norm": 0.13621516525745392,
      "learning_rate": 3.636363636363636e-06,
      "loss": 0.7363,
      "step": 1
    },
    {
      "epoch": 0.009233610341643583,
      "grad_norm": 0.13796468079090118,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.7817,
      "step": 5
    },
    {
      "epoch": 0.018467220683287166,
      "grad_norm": 0.12183558940887451,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.7779,
      "step": 10
    },
    {
      "epoch": 0.027700831024930747,
      "grad_norm": 0.16904406249523163,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 0.7869,
      "step": 15
    },
    {
      "epoch": 0.03693444136657433,
      "grad_norm": 0.1359681636095047,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.777,
      "step": 20
    },
    {
      "epoch": 0.046168051708217916,
      "grad_norm": 0.11777453124523163,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.7807,
      "step": 25
    },
    {
      "epoch": 0.055401662049861494,
      "grad_norm": 0.12384524196386337,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.7494,
      "step": 30
    },
    {
      "epoch": 0.06463527239150507,
      "grad_norm": 0.11038655042648315,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.7475,
      "step": 35
    },
    {
      "epoch": 0.07386888273314866,
      "grad_norm": 0.12827804684638977,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.7571,
      "step": 40
    },
    {
      "epoch": 0.08310249307479224,
      "grad_norm": 0.1219051405787468,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.7498,
      "step": 45
    },
    {
      "epoch": 0.09233610341643583,
      "grad_norm": 0.114303357899189,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.7459,
      "step": 50
    },
    {
      "epoch": 0.10156971375807941,
      "grad_norm": 0.12260652333498001,
      "learning_rate": 0.0002,
      "loss": 0.7285,
      "step": 55
    },
    {
      "epoch": 0.11080332409972299,
      "grad_norm": 0.1140127182006836,
      "learning_rate": 0.00019994777247895855,
      "loss": 0.7382,
      "step": 60
    },
    {
      "epoch": 0.12003693444136658,
      "grad_norm": 0.11311746388673782,
      "learning_rate": 0.00019979114447011323,
      "loss": 0.7759,
      "step": 65
    },
    {
      "epoch": 0.12927054478301014,
      "grad_norm": 0.1240229681134224,
      "learning_rate": 0.00019953027957931658,
      "loss": 0.7489,
      "step": 70
    },
    {
      "epoch": 0.13850415512465375,
      "grad_norm": 0.10431641340255737,
      "learning_rate": 0.00019916545029310012,
      "loss": 0.7401,
      "step": 75
    },
    {
      "epoch": 0.14773776546629733,
      "grad_norm": 0.10815250873565674,
      "learning_rate": 0.00019869703769404828,
      "loss": 0.7429,
      "step": 80
    },
    {
      "epoch": 0.1569713758079409,
      "grad_norm": 0.10247638076543808,
      "learning_rate": 0.00019812553106273847,
      "loss": 0.7496,
      "step": 85
    },
    {
      "epoch": 0.16620498614958448,
      "grad_norm": 0.1005801111459732,
      "learning_rate": 0.00019745152736666302,
      "loss": 0.7354,
      "step": 90
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 0.11037640273571014,
      "learning_rate": 0.0001966757306366662,
      "loss": 0.765,
      "step": 95
    },
    {
      "epoch": 0.18467220683287167,
      "grad_norm": 0.1104218140244484,
      "learning_rate": 0.0001957989512315489,
      "loss": 0.7395,
      "step": 100
    },
    {
      "epoch": 0.19390581717451524,
      "grad_norm": 0.10845394432544708,
      "learning_rate": 0.00019482210499160765,
      "loss": 0.7378,
      "step": 105
    },
    {
      "epoch": 0.20313942751615882,
      "grad_norm": 0.103615403175354,
      "learning_rate": 0.0001937462122819935,
      "loss": 0.7344,
      "step": 110
    },
    {
      "epoch": 0.2123730378578024,
      "grad_norm": 0.10229409486055374,
      "learning_rate": 0.00019257239692688907,
      "loss": 0.7396,
      "step": 115
    },
    {
      "epoch": 0.22160664819944598,
      "grad_norm": 0.11397738009691238,
      "learning_rate": 0.00019130188503561741,
      "loss": 0.7587,
      "step": 120
    },
    {
      "epoch": 0.23084025854108955,
      "grad_norm": 0.1019892767071724,
      "learning_rate": 0.00018993600372190932,
      "loss": 0.7524,
      "step": 125
    },
    {
      "epoch": 0.24007386888273316,
      "grad_norm": 0.11047018319368362,
      "learning_rate": 0.00018847617971766577,
      "loss": 0.7447,
      "step": 130
    },
    {
      "epoch": 0.24930747922437674,
      "grad_norm": 0.10999737679958344,
      "learning_rate": 0.00018692393788266479,
      "loss": 0.7598,
      "step": 135
    },
    {
      "epoch": 0.2585410895660203,
      "grad_norm": 0.10835966467857361,
      "learning_rate": 0.0001852808996117683,
      "loss": 0.7502,
      "step": 140
    },
    {
      "epoch": 0.2677746999076639,
      "grad_norm": 0.1028084084391594,
      "learning_rate": 0.00018354878114129367,
      "loss": 0.7594,
      "step": 145
    },
    {
      "epoch": 0.2770083102493075,
      "grad_norm": 0.10460478812456131,
      "learning_rate": 0.00018172939175631808,
      "loss": 0.7532,
      "step": 150
    },
    {
      "epoch": 0.28624192059095105,
      "grad_norm": 0.10527301579713821,
      "learning_rate": 0.0001798246319007893,
      "loss": 0.7564,
      "step": 155
    },
    {
      "epoch": 0.29547553093259465,
      "grad_norm": 0.11887970566749573,
      "learning_rate": 0.00017783649119241602,
      "loss": 0.7409,
      "step": 160
    },
    {
      "epoch": 0.3047091412742382,
      "grad_norm": 0.10338354855775833,
      "learning_rate": 0.0001757670463444118,
      "loss": 0.7439,
      "step": 165
    },
    {
      "epoch": 0.3139427516158818,
      "grad_norm": 0.1198032796382904,
      "learning_rate": 0.00017361845899626355,
      "loss": 0.727,
      "step": 170
    },
    {
      "epoch": 0.3231763619575254,
      "grad_norm": 0.10385128110647202,
      "learning_rate": 0.00017139297345578994,
      "loss": 0.7352,
      "step": 175
    },
    {
      "epoch": 0.33240997229916897,
      "grad_norm": 0.11350072920322418,
      "learning_rate": 0.0001690929143548488,
      "loss": 0.7421,
      "step": 180
    },
    {
      "epoch": 0.34164358264081257,
      "grad_norm": 0.10703606903553009,
      "learning_rate": 0.00016672068422114196,
      "loss": 0.7344,
      "step": 185
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 0.10089576244354248,
      "learning_rate": 0.00016427876096865394,
      "loss": 0.743,
      "step": 190
    },
    {
      "epoch": 0.3601108033240997,
      "grad_norm": 0.10272319614887238,
      "learning_rate": 0.00016176969530934572,
      "loss": 0.7419,
      "step": 195
    },
    {
      "epoch": 0.36934441366574333,
      "grad_norm": 0.10321817547082901,
      "learning_rate": 0.0001591961080888076,
      "loss": 0.7502,
      "step": 200
    },
    {
      "epoch": 0.3785780240073869,
      "grad_norm": 0.10779888927936554,
      "learning_rate": 0.00015656068754865387,
      "loss": 0.7417,
      "step": 205
    },
    {
      "epoch": 0.3878116343490305,
      "grad_norm": 0.10841017961502075,
      "learning_rate": 0.0001538661865185188,
      "loss": 0.7356,
      "step": 210
    },
    {
      "epoch": 0.39704524469067404,
      "grad_norm": 0.1070384755730629,
      "learning_rate": 0.00015111541954058734,
      "loss": 0.7553,
      "step": 215
    },
    {
      "epoch": 0.40627885503231764,
      "grad_norm": 0.09864313900470734,
      "learning_rate": 0.00014831125992966385,
      "loss": 0.75,
      "step": 220
    },
    {
      "epoch": 0.4155124653739612,
      "grad_norm": 0.10148273408412933,
      "learning_rate": 0.00014545663677185006,
      "loss": 0.738,
      "step": 225
    },
    {
      "epoch": 0.4247460757156048,
      "grad_norm": 0.10425528883934021,
      "learning_rate": 0.00014255453186496673,
      "loss": 0.7385,
      "step": 230
    },
    {
      "epoch": 0.4339796860572484,
      "grad_norm": 0.09917706996202469,
      "learning_rate": 0.0001396079766039157,
      "loss": 0.7261,
      "step": 235
    },
    {
      "epoch": 0.44321329639889195,
      "grad_norm": 0.11001438647508621,
      "learning_rate": 0.0001366200488142348,
      "loss": 0.7349,
      "step": 240
    },
    {
      "epoch": 0.45244690674053556,
      "grad_norm": 0.10055994987487793,
      "learning_rate": 0.00013359386953715421,
      "loss": 0.7318,
      "step": 245
    },
    {
      "epoch": 0.4616805170821791,
      "grad_norm": 0.10037145018577576,
      "learning_rate": 0.00013053259976951133,
      "loss": 0.7312,
      "step": 250
    },
    {
      "epoch": 0.4709141274238227,
      "grad_norm": 0.11422228813171387,
      "learning_rate": 0.00012743943716193016,
      "loss": 0.7426,
      "step": 255
    },
    {
      "epoch": 0.4801477377654663,
      "grad_norm": 0.10170543938875198,
      "learning_rate": 0.00012431761267871417,
      "loss": 0.7212,
      "step": 260
    },
    {
      "epoch": 0.48938134810710987,
      "grad_norm": 0.1071636751294136,
      "learning_rate": 0.0001211703872229411,
      "loss": 0.7518,
      "step": 265
    },
    {
      "epoch": 0.4986149584487535,
      "grad_norm": 0.11060360074043274,
      "learning_rate": 0.00011800104823028515,
      "loss": 0.7526,
      "step": 270
    },
    {
      "epoch": 0.5078485687903971,
      "grad_norm": 0.10358710587024689,
      "learning_rate": 0.0001148129062351249,
      "loss": 0.7198,
      "step": 275
    },
    {
      "epoch": 0.5170821791320406,
      "grad_norm": 0.10385197401046753,
      "learning_rate": 0.00011160929141252303,
      "loss": 0.7221,
      "step": 280
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.10536545515060425,
      "learning_rate": 0.00010839355009969068,
      "loss": 0.7248,
      "step": 285
    },
    {
      "epoch": 0.5355493998153278,
      "grad_norm": 0.10879741609096527,
      "learning_rate": 0.00010516904130056946,
      "loss": 0.7398,
      "step": 290
    },
    {
      "epoch": 0.5447830101569714,
      "grad_norm": 0.10238393396139145,
      "learning_rate": 0.00010193913317718244,
      "loss": 0.7545,
      "step": 295
    },
    {
      "epoch": 0.554016620498615,
      "grad_norm": 0.11232389509677887,
      "learning_rate": 9.870719953141917e-05,
      "loss": 0.7324,
      "step": 300
    },
    {
      "epoch": 0.5632502308402585,
      "grad_norm": 0.09757301956415176,
      "learning_rate": 9.547661628092937e-05,
      "loss": 0.7303,
      "step": 305
    },
    {
      "epoch": 0.5724838411819021,
      "grad_norm": 0.10265171527862549,
      "learning_rate": 9.225075793280692e-05,
      "loss": 0.7366,
      "step": 310
    },
    {
      "epoch": 0.5817174515235457,
      "grad_norm": 0.10101115703582764,
      "learning_rate": 8.903299405874684e-05,
      "loss": 0.7156,
      "step": 315
    },
    {
      "epoch": 0.5909510618651893,
      "grad_norm": 0.10101660341024399,
      "learning_rate": 8.582668577535797e-05,
      "loss": 0.7329,
      "step": 320
    },
    {
      "epoch": 0.6001846722068329,
      "grad_norm": 0.10654629021883011,
      "learning_rate": 8.263518223330697e-05,
      "loss": 0.76,
      "step": 325
    },
    {
      "epoch": 0.6094182825484764,
      "grad_norm": 0.10585548728704453,
      "learning_rate": 7.94618171189618e-05,
      "loss": 0.706,
      "step": 330
    },
    {
      "epoch": 0.61865189289012,
      "grad_norm": 0.10175392776727676,
      "learning_rate": 7.630990517218808e-05,
      "loss": 0.7423,
      "step": 335
    },
    {
      "epoch": 0.6278855032317636,
      "grad_norm": 0.10401345789432526,
      "learning_rate": 7.318273872393625e-05,
      "loss": 0.7446,
      "step": 340
    },
    {
      "epoch": 0.6371191135734072,
      "grad_norm": 0.10385286062955856,
      "learning_rate": 7.008358425723585e-05,
      "loss": 0.757,
      "step": 345
    },
    {
      "epoch": 0.6463527239150508,
      "grad_norm": 0.10788547992706299,
      "learning_rate": 6.701567899518924e-05,
      "loss": 0.7305,
      "step": 350
    },
    {
      "epoch": 0.6555863342566943,
      "grad_norm": 0.10447971522808075,
      "learning_rate": 6.398222751952899e-05,
      "loss": 0.7178,
      "step": 355
    },
    {
      "epoch": 0.6648199445983379,
      "grad_norm": 0.10098852962255478,
      "learning_rate": 6.098639842327052e-05,
      "loss": 0.742,
      "step": 360
    },
    {
      "epoch": 0.6740535549399815,
      "grad_norm": 0.10096322745084763,
      "learning_rate": 5.80313210009571e-05,
      "loss": 0.7331,
      "step": 365
    },
    {
      "epoch": 0.6832871652816251,
      "grad_norm": 0.10325752198696136,
      "learning_rate": 5.5120081979953785e-05,
      "loss": 0.738,
      "step": 370
    },
    {
      "epoch": 0.6925207756232687,
      "grad_norm": 0.10698148608207703,
      "learning_rate": 5.22557222962051e-05,
      "loss": 0.7532,
      "step": 375
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 0.10292143374681473,
      "learning_rate": 4.9441233917824106e-05,
      "loss": 0.7339,
      "step": 380
    },
    {
      "epoch": 0.7109879963065558,
      "grad_norm": 0.10220400989055634,
      "learning_rate": 4.66795567198309e-05,
      "loss": 0.7346,
      "step": 385
    },
    {
      "epoch": 0.7202216066481995,
      "grad_norm": 0.10404420644044876,
      "learning_rate": 4.397357541330476e-05,
      "loss": 0.7575,
      "step": 390
    },
    {
      "epoch": 0.7294552169898431,
      "grad_norm": 0.10498429834842682,
      "learning_rate": 4.132611653215822e-05,
      "loss": 0.737,
      "step": 395
    },
    {
      "epoch": 0.7386888273314867,
      "grad_norm": 0.10577254742383957,
      "learning_rate": 3.873994548067972e-05,
      "loss": 0.7277,
      "step": 400
    },
    {
      "epoch": 0.7479224376731302,
      "grad_norm": 0.11322159320116043,
      "learning_rate": 3.621776364492939e-05,
      "loss": 0.7447,
      "step": 405
    },
    {
      "epoch": 0.7571560480147738,
      "grad_norm": 0.1056286096572876,
      "learning_rate": 3.376220557100523e-05,
      "loss": 0.7347,
      "step": 410
    },
    {
      "epoch": 0.7663896583564174,
      "grad_norm": 0.10042563825845718,
      "learning_rate": 3.137583621312665e-05,
      "loss": 0.7374,
      "step": 415
    },
    {
      "epoch": 0.775623268698061,
      "grad_norm": 0.10892172902822495,
      "learning_rate": 2.906114825441072e-05,
      "loss": 0.7288,
      "step": 420
    },
    {
      "epoch": 0.7848568790397045,
      "grad_norm": 0.1068541631102562,
      "learning_rate": 2.6820559503138797e-05,
      "loss": 0.7474,
      "step": 425
    },
    {
      "epoch": 0.7940904893813481,
      "grad_norm": 0.10999409854412079,
      "learning_rate": 2.465641036723393e-05,
      "loss": 0.7451,
      "step": 430
    },
    {
      "epoch": 0.8033240997229917,
      "grad_norm": 0.10453728586435318,
      "learning_rate": 2.2570961409586754e-05,
      "loss": 0.7427,
      "step": 435
    },
    {
      "epoch": 0.8125577100646353,
      "grad_norm": 0.10310923308134079,
      "learning_rate": 2.0566390986783646e-05,
      "loss": 0.7474,
      "step": 440
    },
    {
      "epoch": 0.8217913204062789,
      "grad_norm": 0.10431590676307678,
      "learning_rate": 1.864479297370325e-05,
      "loss": 0.7319,
      "step": 445
    },
    {
      "epoch": 0.8310249307479224,
      "grad_norm": 0.10921698808670044,
      "learning_rate": 1.6808174576358848e-05,
      "loss": 0.7478,
      "step": 450
    },
    {
      "epoch": 0.840258541089566,
      "grad_norm": 0.11102822422981262,
      "learning_rate": 1.505845423527027e-05,
      "loss": 0.7585,
      "step": 455
    },
    {
      "epoch": 0.8494921514312096,
      "grad_norm": 0.10043223947286606,
      "learning_rate": 1.339745962155613e-05,
      "loss": 0.7337,
      "step": 460
    },
    {
      "epoch": 0.8587257617728532,
      "grad_norm": 0.10496434569358826,
      "learning_rate": 1.18269257278392e-05,
      "loss": 0.7407,
      "step": 465
    },
    {
      "epoch": 0.8679593721144968,
      "grad_norm": 0.10377249866724014,
      "learning_rate": 1.0348493055959062e-05,
      "loss": 0.7198,
      "step": 470
    },
    {
      "epoch": 0.8771929824561403,
      "grad_norm": 0.10728956758975983,
      "learning_rate": 8.963705903385345e-06,
      "loss": 0.7176,
      "step": 475
    },
    {
      "epoch": 0.8864265927977839,
      "grad_norm": 0.10525339096784592,
      "learning_rate": 7.674010750120964e-06,
      "loss": 0.7326,
      "step": 480
    },
    {
      "epoch": 0.8956602031394275,
      "grad_norm": 0.10717398673295975,
      "learning_rate": 6.480754747781037e-06,
      "loss": 0.7298,
      "step": 485
    },
    {
      "epoch": 0.9048938134810711,
      "grad_norm": 0.10121981054544449,
      "learning_rate": 5.385184312424974e-06,
      "loss": 0.7187,
      "step": 490
    },
    {
      "epoch": 0.9141274238227147,
      "grad_norm": 0.10384524613618851,
      "learning_rate": 4.3884438226120424e-06,
      "loss": 0.7348,
      "step": 495
    },
    {
      "epoch": 0.9233610341643582,
      "grad_norm": 0.09785287827253342,
      "learning_rate": 3.4915744240403558e-06,
      "loss": 0.7339,
      "step": 500
    },
    {
      "epoch": 0.9325946445060018,
      "grad_norm": 0.1057659238576889,
      "learning_rate": 2.6955129420176196e-06,
      "loss": 0.7295,
      "step": 505
    },
    {
      "epoch": 0.9418282548476454,
      "grad_norm": 0.1022268533706665,
      "learning_rate": 2.0010909028998827e-06,
      "loss": 0.7254,
      "step": 510
    },
    {
      "epoch": 0.951061865189289,
      "grad_norm": 0.10650717467069626,
      "learning_rate": 1.409033665520354e-06,
      "loss": 0.7362,
      "step": 515
    },
    {
      "epoch": 0.9602954755309326,
      "grad_norm": 0.10881408303976059,
      "learning_rate": 9.199596635154683e-07,
      "loss": 0.733,
      "step": 520
    },
    {
      "epoch": 0.9695290858725761,
      "grad_norm": 0.10430116206407547,
      "learning_rate": 5.343797593398536e-07,
      "loss": 0.7487,
      "step": 525
    },
    {
      "epoch": 0.9787626962142197,
      "grad_norm": 0.1005534678697586,
      "learning_rate": 2.5269671064467313e-07,
      "loss": 0.7265,
      "step": 530
    },
    {
      "epoch": 0.9879963065558633,
      "grad_norm": 0.10172731429338455,
      "learning_rate": 7.520474957699586e-08,
      "loss": 0.7208,
      "step": 535
    },
    {
      "epoch": 0.997229916897507,
      "grad_norm": 0.10914121568202972,
      "learning_rate": 2.0892754394208346e-09,
      "loss": 0.7491,
      "step": 540
    },
    {
      "epoch": 0.9990766389658357,
      "eval_loss": 0.9509617686271667,
      "eval_runtime": 131.3926,
      "eval_samples_per_second": 8.79,
      "eval_steps_per_second": 0.556,
      "step": 541
    },
    {
      "epoch": 0.9990766389658357,
      "step": 541,
      "total_flos": 2.228078290818564e+18,
      "train_loss": 0.7416185885392363,
      "train_runtime": 26509.2456,
      "train_samples_per_second": 3.921,
      "train_steps_per_second": 0.02
    }
  ],
  "logging_steps": 5,
  "max_steps": 541,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.228078290818564e+18,
  "train_batch_size": 24,
  "trial_name": null,
  "trial_params": null
}