{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6914119359534207,
  "eval_steps": 100,
  "global_step": 3800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009097525473071324,
      "grad_norm": 1.0602493286132812,
      "learning_rate": 1.2121212121212122e-06,
      "loss": 1.7156932830810547,
      "step": 5
    },
    {
      "epoch": 0.001819505094614265,
      "grad_norm": 1.1577719449996948,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 1.6629371643066406,
      "step": 10
    },
    {
      "epoch": 0.0027292576419213972,
      "grad_norm": 1.0288419723510742,
      "learning_rate": 4.242424242424243e-06,
      "loss": 1.6706295013427734,
      "step": 15
    },
    {
      "epoch": 0.00363901018922853,
      "grad_norm": 2.129403829574585,
      "learning_rate": 5.7575757575757586e-06,
      "loss": 1.7363752365112304,
      "step": 20
    },
    {
      "epoch": 0.004548762736535662,
      "grad_norm": 1.9468326568603516,
      "learning_rate": 7.272727272727272e-06,
      "loss": 1.7111135482788087,
      "step": 25
    },
    {
      "epoch": 0.0054585152838427945,
      "grad_norm": 1.1269357204437256,
      "learning_rate": 8.787878787878788e-06,
      "loss": 1.6924203872680663,
      "step": 30
    },
    {
      "epoch": 0.006368267831149927,
      "grad_norm": 1.4021248817443848,
      "learning_rate": 1.0303030303030304e-05,
      "loss": 1.658310317993164,
      "step": 35
    },
    {
      "epoch": 0.00727802037845706,
      "grad_norm": 1.313381314277649,
      "learning_rate": 1.1818181818181819e-05,
      "loss": 1.5383296012878418,
      "step": 40
    },
    {
      "epoch": 0.008187772925764192,
      "grad_norm": 2.4359891414642334,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 1.4302565574645996,
      "step": 45
    },
    {
      "epoch": 0.009097525473071324,
      "grad_norm": 1.6459542512893677,
      "learning_rate": 1.484848484848485e-05,
      "loss": 1.2602953910827637,
      "step": 50
    },
    {
      "epoch": 0.010007278020378457,
      "grad_norm": 0.7953159213066101,
      "learning_rate": 1.6363636363636366e-05,
      "loss": 1.204326343536377,
      "step": 55
    },
    {
      "epoch": 0.010917030567685589,
      "grad_norm": 0.5824465155601501,
      "learning_rate": 1.787878787878788e-05,
      "loss": 1.068561840057373,
      "step": 60
    },
    {
      "epoch": 0.011826783114992722,
      "grad_norm": 0.39265626668930054,
      "learning_rate": 1.9393939393939395e-05,
      "loss": 0.9570062637329102,
      "step": 65
    },
    {
      "epoch": 0.012736535662299854,
      "grad_norm": 0.3387283384799957,
      "learning_rate": 2.090909090909091e-05,
      "loss": 0.9454713821411133,
      "step": 70
    },
    {
      "epoch": 0.013646288209606987,
      "grad_norm": 0.3182811141014099,
      "learning_rate": 2.2424242424242424e-05,
      "loss": 0.8901592254638672,
      "step": 75
    },
    {
      "epoch": 0.01455604075691412,
      "grad_norm": 0.2735312879085541,
      "learning_rate": 2.393939393939394e-05,
      "loss": 0.8491583824157715,
      "step": 80
    },
    {
      "epoch": 0.015465793304221253,
      "grad_norm": 0.2376435250043869,
      "learning_rate": 2.5454545454545454e-05,
      "loss": 0.8109179496765136,
      "step": 85
    },
    {
      "epoch": 0.016375545851528384,
      "grad_norm": 0.2161586880683899,
      "learning_rate": 2.696969696969697e-05,
      "loss": 0.76962308883667,
      "step": 90
    },
    {
      "epoch": 0.017285298398835518,
      "grad_norm": 0.19587980210781097,
      "learning_rate": 2.8484848484848486e-05,
      "loss": 0.7301986694335938,
      "step": 95
    },
    {
      "epoch": 0.018195050946142648,
      "grad_norm": 0.20971694588661194,
      "learning_rate": 3e-05,
      "loss": 0.7269618034362793,
      "step": 100
    },
    {
      "epoch": 0.018195050946142648,
      "eval_loss": 2.605874538421631,
      "eval_runtime": 1120.0905,
      "eval_samples_per_second": 33.935,
      "eval_steps_per_second": 8.484,
      "step": 100
    },
    {
      "epoch": 0.01910480349344978,
      "grad_norm": 0.10413152724504471,
      "learning_rate": 3.151515151515151e-05,
      "loss": 0.3250573635101318,
      "step": 105
    },
    {
      "epoch": 0.020014556040756915,
      "grad_norm": 0.09383206814527512,
      "learning_rate": 3.303030303030303e-05,
      "loss": 0.3277724742889404,
      "step": 110
    },
    {
      "epoch": 0.020924308588064048,
      "grad_norm": 0.1195850670337677,
      "learning_rate": 3.454545454545455e-05,
      "loss": 0.3215961217880249,
      "step": 115
    },
    {
      "epoch": 0.021834061135371178,
      "grad_norm": 0.0715397521853447,
      "learning_rate": 3.606060606060606e-05,
      "loss": 0.3120795965194702,
      "step": 120
    },
    {
      "epoch": 0.02274381368267831,
      "grad_norm": 0.068007692694664,
      "learning_rate": 3.757575757575758e-05,
      "loss": 0.2964257955551147,
      "step": 125
    },
    {
      "epoch": 0.023653566229985445,
      "grad_norm": 0.09345484524965286,
      "learning_rate": 3.909090909090909e-05,
      "loss": 0.30776252746582033,
      "step": 130
    },
    {
      "epoch": 0.024563318777292575,
      "grad_norm": 0.05577846243977547,
      "learning_rate": 4.0606060606060606e-05,
      "loss": 0.3180255889892578,
      "step": 135
    },
    {
      "epoch": 0.025473071324599708,
      "grad_norm": 0.05919989198446274,
      "learning_rate": 4.212121212121212e-05,
      "loss": 0.31608285903930666,
      "step": 140
    },
    {
      "epoch": 0.02638282387190684,
      "grad_norm": 0.05644674599170685,
      "learning_rate": 4.3636363636363636e-05,
      "loss": 0.2993780136108398,
      "step": 145
    },
    {
      "epoch": 0.027292576419213975,
      "grad_norm": 0.059986088424921036,
      "learning_rate": 4.515151515151516e-05,
      "loss": 0.2931638479232788,
      "step": 150
    },
    {
      "epoch": 0.028202328966521105,
      "grad_norm": 0.05941484495997429,
      "learning_rate": 4.666666666666667e-05,
      "loss": 0.29284651279449464,
      "step": 155
    },
    {
      "epoch": 0.02911208151382824,
      "grad_norm": 0.0579044483602047,
      "learning_rate": 4.8181818181818186e-05,
      "loss": 0.2927037000656128,
      "step": 160
    },
    {
      "epoch": 0.030021834061135372,
      "grad_norm": 0.061985693871974945,
      "learning_rate": 4.9696969696969694e-05,
      "loss": 0.28671720027923586,
      "step": 165
    },
    {
      "epoch": 0.030931586608442505,
      "grad_norm": 0.05715535953640938,
      "learning_rate": 4.999993064772809e-05,
      "loss": 0.2817929744720459,
      "step": 170
    },
    {
      "epoch": 0.03184133915574964,
      "grad_norm": 0.06549780815839767,
      "learning_rate": 4.999964890478288e-05,
      "loss": 0.27853829860687257,
      "step": 175
    },
    {
      "epoch": 0.03275109170305677,
      "grad_norm": 0.05948757752776146,
      "learning_rate": 4.999915043908795e-05,
      "loss": 0.27522289752960205,
      "step": 180
    },
    {
      "epoch": 0.0336608442503639,
      "grad_norm": 0.06262889504432678,
      "learning_rate": 4.9998435254964515e-05,
      "loss": 0.270997428894043,
      "step": 185
    },
    {
      "epoch": 0.034570596797671035,
      "grad_norm": 0.06916829943656921,
      "learning_rate": 4.999750335861253e-05,
      "loss": 0.2788438558578491,
      "step": 190
    },
    {
      "epoch": 0.035480349344978165,
      "grad_norm": 0.06128217652440071,
      "learning_rate": 4.9996354758110624e-05,
      "loss": 0.25649352073669435,
      "step": 195
    },
    {
      "epoch": 0.036390101892285295,
      "grad_norm": 0.06704027950763702,
      "learning_rate": 4.999498946341606e-05,
      "loss": 0.25619523525238036,
      "step": 200
    },
    {
      "epoch": 0.03729985443959243,
      "grad_norm": 0.061678580939769745,
      "learning_rate": 4.999340748636462e-05,
      "loss": 0.24956226348876953,
      "step": 205
    },
    {
      "epoch": 0.03820960698689956,
      "grad_norm": 0.07328873127698898,
      "learning_rate": 4.999160884067051e-05,
      "loss": 0.26169676780700685,
      "step": 210
    },
    {
      "epoch": 0.0391193595342067,
      "grad_norm": 0.08287990838289261,
      "learning_rate": 4.9989593541926246e-05,
      "loss": 0.2574604034423828,
      "step": 215
    },
    {
      "epoch": 0.04002911208151383,
      "grad_norm": 0.06787359714508057,
      "learning_rate": 4.9987361607602525e-05,
      "loss": 0.25351409912109374,
      "step": 220
    },
    {
      "epoch": 0.04093886462882096,
      "grad_norm": 0.06695502996444702,
      "learning_rate": 4.998491305704805e-05,
      "loss": 0.24522039890289307,
      "step": 225
    },
    {
      "epoch": 0.041848617176128096,
      "grad_norm": 0.08872214704751968,
      "learning_rate": 4.9982247911489375e-05,
      "loss": 0.2581867933273315,
      "step": 230
    },
    {
      "epoch": 0.042758369723435226,
      "grad_norm": 0.07637131959199905,
      "learning_rate": 4.9979366194030743e-05,
      "loss": 0.25569658279418944,
      "step": 235
    },
    {
      "epoch": 0.043668122270742356,
      "grad_norm": 0.08158119022846222,
      "learning_rate": 4.997626792965385e-05,
      "loss": 0.2529409646987915,
      "step": 240
    },
    {
      "epoch": 0.04457787481804949,
      "grad_norm": 0.07529161125421524,
      "learning_rate": 4.997295314521766e-05,
      "loss": 0.24049024581909179,
      "step": 245
    },
    {
      "epoch": 0.04548762736535662,
      "grad_norm": 0.08860139548778534,
      "learning_rate": 4.996942186945813e-05,
      "loss": 0.2490522861480713,
      "step": 250
    },
    {
      "epoch": 0.04639737991266375,
      "grad_norm": 0.0850321501493454,
      "learning_rate": 4.9965674132988005e-05,
      "loss": 0.24180831909179687,
      "step": 255
    },
    {
      "epoch": 0.04730713245997089,
      "grad_norm": 0.07556115090847015,
      "learning_rate": 4.996170996829653e-05,
      "loss": 0.2509631872177124,
      "step": 260
    },
    {
      "epoch": 0.04821688500727802,
      "grad_norm": 0.07971206307411194,
      "learning_rate": 4.995752940974918e-05,
      "loss": 0.24398891925811766,
      "step": 265
    },
    {
      "epoch": 0.04912663755458515,
      "grad_norm": 0.09149336814880371,
      "learning_rate": 4.9953132493587344e-05,
      "loss": 0.2300492286682129,
      "step": 270
    },
    {
      "epoch": 0.050036390101892286,
      "grad_norm": 0.08265820890665054,
      "learning_rate": 4.9948519257928034e-05,
      "loss": 0.24246792793273925,
      "step": 275
    },
    {
      "epoch": 0.050946142649199416,
      "grad_norm": 0.10328587144613266,
      "learning_rate": 4.9943689742763534e-05,
      "loss": 0.2367171049118042,
      "step": 280
    },
    {
      "epoch": 0.05185589519650655,
      "grad_norm": 0.0836917981505394,
      "learning_rate": 4.993864398996105e-05,
      "loss": 0.23215813636779786,
      "step": 285
    },
    {
      "epoch": 0.05276564774381368,
      "grad_norm": 0.09475161135196686,
      "learning_rate": 4.99333820432624e-05,
      "loss": 0.2350748062133789,
      "step": 290
    },
    {
      "epoch": 0.05367540029112081,
      "grad_norm": 0.08040128648281097,
      "learning_rate": 4.992790394828355e-05,
      "loss": 0.23253886699676513,
      "step": 295
    },
    {
      "epoch": 0.05458515283842795,
      "grad_norm": 0.08852150291204453,
      "learning_rate": 4.992220975251428e-05,
      "loss": 0.23856515884399415,
      "step": 300
    },
    {
      "epoch": 0.05549490538573508,
      "grad_norm": 0.09565229713916779,
      "learning_rate": 4.991629950531775e-05,
      "loss": 0.23311660289764405,
      "step": 305
    },
    {
      "epoch": 0.05640465793304221,
      "grad_norm": 0.08158160001039505,
      "learning_rate": 4.991017325793009e-05,
      "loss": 0.22467944622039795,
      "step": 310
    },
    {
      "epoch": 0.05731441048034935,
      "grad_norm": 0.07746429741382599,
      "learning_rate": 4.990383106345994e-05,
      "loss": 0.229844069480896,
      "step": 315
    },
    {
      "epoch": 0.05822416302765648,
      "grad_norm": 0.08564355969429016,
      "learning_rate": 4.989727297688797e-05,
      "loss": 0.22414517402648926,
      "step": 320
    },
    {
      "epoch": 0.05913391557496361,
      "grad_norm": 0.07517435401678085,
      "learning_rate": 4.9890499055066435e-05,
      "loss": 0.2236532211303711,
      "step": 325
    },
    {
      "epoch": 0.060043668122270744,
      "grad_norm": 0.111734539270401,
      "learning_rate": 4.988350935671869e-05,
      "loss": 0.21474847793579102,
      "step": 330
    },
    {
      "epoch": 0.060953420669577874,
      "grad_norm": 0.09906989336013794,
      "learning_rate": 4.987630394243866e-05,
      "loss": 0.23321933746337892,
      "step": 335
    },
    {
      "epoch": 0.06186317321688501,
      "grad_norm": 0.10131457448005676,
      "learning_rate": 4.98688828746903e-05,
      "loss": 0.2310662031173706,
      "step": 340
    },
    {
      "epoch": 0.06277292576419213,
      "grad_norm": 0.09203507006168365,
      "learning_rate": 4.986124621780708e-05,
      "loss": 0.22021169662475587,
      "step": 345
    },
    {
      "epoch": 0.06368267831149928,
      "grad_norm": 0.09505912661552429,
      "learning_rate": 4.9853394037991416e-05,
      "loss": 0.2197155237197876,
      "step": 350
    },
    {
      "epoch": 0.06459243085880641,
      "grad_norm": 0.09038657695055008,
      "learning_rate": 4.984532640331412e-05,
      "loss": 0.22066287994384765,
      "step": 355
    },
    {
      "epoch": 0.06550218340611354,
      "grad_norm": 0.09707064181566238,
      "learning_rate": 4.9837043383713753e-05,
      "loss": 0.22455451488494874,
      "step": 360
    },
    {
      "epoch": 0.06641193595342067,
      "grad_norm": 0.10367228090763092,
      "learning_rate": 4.98285450509961e-05,
      "loss": 0.21993820667266845,
      "step": 365
    },
    {
      "epoch": 0.0673216885007278,
      "grad_norm": 0.12229471653699875,
      "learning_rate": 4.9819831478833456e-05,
      "loss": 0.2168867588043213,
      "step": 370
    },
    {
      "epoch": 0.06823144104803494,
      "grad_norm": 0.0964592918753624,
      "learning_rate": 4.981090274276406e-05,
      "loss": 0.21579203605651856,
      "step": 375
    },
    {
      "epoch": 0.06914119359534207,
      "grad_norm": 0.09400496631860733,
      "learning_rate": 4.980175892019141e-05,
      "loss": 0.20972180366516113,
      "step": 380
    },
    {
      "epoch": 0.0700509461426492,
      "grad_norm": 0.08158645778894424,
      "learning_rate": 4.9792400090383594e-05,
      "loss": 0.22148358821868896,
      "step": 385
    },
    {
      "epoch": 0.07096069868995633,
      "grad_norm": 0.10916394740343094,
      "learning_rate": 4.978282633447261e-05,
      "loss": 0.2214418649673462,
      "step": 390
    },
    {
      "epoch": 0.07187045123726346,
      "grad_norm": 0.11138810962438583,
      "learning_rate": 4.9773037735453636e-05,
      "loss": 0.21814754009246826,
      "step": 395
    },
    {
      "epoch": 0.07278020378457059,
      "grad_norm": 0.10914396494626999,
      "learning_rate": 4.9763034378184365e-05,
      "loss": 0.21310818195343018,
      "step": 400
    },
    {
      "epoch": 0.07368995633187773,
      "grad_norm": 0.1043366864323616,
      "learning_rate": 4.975281634938421e-05,
      "loss": 0.21266789436340333,
      "step": 405
    },
    {
      "epoch": 0.07459970887918486,
      "grad_norm": 0.1036868542432785,
      "learning_rate": 4.9742383737633594e-05,
      "loss": 0.21606721878051757,
      "step": 410
    },
    {
      "epoch": 0.075509461426492,
      "grad_norm": 0.11640442907810211,
      "learning_rate": 4.9731736633373144e-05,
      "loss": 0.21532948017120362,
      "step": 415
    },
    {
      "epoch": 0.07641921397379912,
      "grad_norm": 0.11219926178455353,
      "learning_rate": 4.9720875128902956e-05,
      "loss": 0.2191627025604248,
      "step": 420
    },
    {
      "epoch": 0.07732896652110625,
      "grad_norm": 0.12103637307882309,
      "learning_rate": 4.970979931838176e-05,
      "loss": 0.20938868522644044,
      "step": 425
    },
    {
      "epoch": 0.0782387190684134,
      "grad_norm": 0.13274189829826355,
      "learning_rate": 4.96985092978261e-05,
      "loss": 0.21792960166931152,
      "step": 430
    },
    {
      "epoch": 0.07914847161572053,
      "grad_norm": 0.11164513230323792,
      "learning_rate": 4.968700516510954e-05,
      "loss": 0.2022618055343628,
      "step": 435
    },
    {
      "epoch": 0.08005822416302766,
      "grad_norm": 0.09532847255468369,
      "learning_rate": 4.967528701996174e-05,
      "loss": 0.21255812644958497,
      "step": 440
    },
    {
      "epoch": 0.08096797671033479,
      "grad_norm": 0.10279258340597153,
      "learning_rate": 4.96633549639677e-05,
      "loss": 0.20683050155639648,
      "step": 445
    },
    {
      "epoch": 0.08187772925764192,
      "grad_norm": 0.1257462352514267,
      "learning_rate": 4.965120910056677e-05,
      "loss": 0.21419920921325683,
      "step": 450
    },
    {
      "epoch": 0.08278748180494905,
      "grad_norm": 0.11663137376308441,
      "learning_rate": 4.963884953505186e-05,
      "loss": 0.2072287082672119,
      "step": 455
    },
    {
      "epoch": 0.08369723435225619,
      "grad_norm": 0.10488224029541016,
      "learning_rate": 4.96262763745684e-05,
      "loss": 0.1982678532600403,
      "step": 460
    },
    {
      "epoch": 0.08460698689956332,
      "grad_norm": 0.11801692098379135,
      "learning_rate": 4.961348972811354e-05,
      "loss": 0.20662031173706055,
      "step": 465
    },
    {
      "epoch": 0.08551673944687045,
      "grad_norm": 0.11318827420473099,
      "learning_rate": 4.96004897065351e-05,
      "loss": 0.20947303771972656,
      "step": 470
    },
    {
      "epoch": 0.08642649199417758,
      "grad_norm": 0.13409486413002014,
      "learning_rate": 4.95872764225307e-05,
      "loss": 0.19670876264572143,
      "step": 475
    },
    {
      "epoch": 0.08733624454148471,
      "grad_norm": 0.14440792798995972,
      "learning_rate": 4.957384999064672e-05,
      "loss": 0.19842848777770997,
      "step": 480
    },
    {
      "epoch": 0.08824599708879186,
      "grad_norm": 0.12246996909379959,
      "learning_rate": 4.956021052727731e-05,
      "loss": 0.20318071842193602,
      "step": 485
    },
    {
      "epoch": 0.08915574963609899,
      "grad_norm": 0.13437233865261078,
      "learning_rate": 4.954635815066342e-05,
      "loss": 0.21675212383270265,
      "step": 490
    },
    {
      "epoch": 0.09006550218340612,
      "grad_norm": 0.11109672486782074,
      "learning_rate": 4.9532292980891744e-05,
      "loss": 0.2100757837295532,
      "step": 495
    },
    {
      "epoch": 0.09097525473071325,
      "grad_norm": 0.1388893872499466,
      "learning_rate": 4.9518015139893675e-05,
      "loss": 0.20303285121917725,
      "step": 500
    },
    {
      "epoch": 0.09188500727802038,
      "grad_norm": 0.13239721953868866,
      "learning_rate": 4.950352475144427e-05,
      "loss": 0.2152268409729004,
      "step": 505
    },
    {
      "epoch": 0.0927947598253275,
      "grad_norm": 0.12834979593753815,
      "learning_rate": 4.948882194116119e-05,
      "loss": 0.20799248218536376,
      "step": 510
    },
    {
      "epoch": 0.09370451237263465,
      "grad_norm": 0.11886704713106155,
      "learning_rate": 4.947390683650354e-05,
      "loss": 0.20394976139068605,
      "step": 515
    },
    {
      "epoch": 0.09461426491994178,
      "grad_norm": 0.11398876458406448,
      "learning_rate": 4.945877956677083e-05,
      "loss": 0.2091092586517334,
      "step": 520
    },
    {
      "epoch": 0.09552401746724891,
      "grad_norm": 0.1422540694475174,
      "learning_rate": 4.944344026310186e-05,
      "loss": 0.19564238786697388,
      "step": 525
    },
    {
      "epoch": 0.09643377001455604,
      "grad_norm": 0.11359584331512451,
      "learning_rate": 4.9427889058473535e-05,
      "loss": 0.20493624210357667,
      "step": 530
    },
    {
      "epoch": 0.09734352256186317,
      "grad_norm": 0.11703553050756454,
      "learning_rate": 4.941212608769974e-05,
      "loss": 0.2098615884780884,
      "step": 535
    },
    {
      "epoch": 0.0982532751091703,
      "grad_norm": 0.14552047848701477,
      "learning_rate": 4.939615148743017e-05,
      "loss": 0.20382182598114013,
      "step": 540
    },
    {
      "epoch": 0.09916302765647744,
      "grad_norm": 0.13178016245365143,
      "learning_rate": 4.937996539614914e-05,
      "loss": 0.19901862144470214,
      "step": 545
    },
    {
      "epoch": 0.10007278020378457,
      "grad_norm": 0.635392427444458,
      "learning_rate": 4.936356795417439e-05,
      "loss": 0.20694944858551026,
      "step": 550
    },
    {
      "epoch": 0.1009825327510917,
      "grad_norm": 0.15019077062606812,
      "learning_rate": 4.934695930365586e-05,
      "loss": 0.19313746690750122,
      "step": 555
    },
    {
      "epoch": 0.10189228529839883,
      "grad_norm": 0.12941956520080566,
      "learning_rate": 4.9330139588574474e-05,
      "loss": 0.19671722650527954,
      "step": 560
    },
    {
      "epoch": 0.10280203784570596,
      "grad_norm": 0.13818831741809845,
      "learning_rate": 4.931310895474088e-05,
      "loss": 0.20026786327362062,
      "step": 565
    },
    {
      "epoch": 0.1037117903930131,
      "grad_norm": 0.12011194974184036,
      "learning_rate": 4.929586754979417e-05,
      "loss": 0.1932437539100647,
      "step": 570
    },
    {
      "epoch": 0.10462154294032024,
      "grad_norm": 0.1345364898443222,
      "learning_rate": 4.9278415523200644e-05,
      "loss": 0.20245940685272218,
      "step": 575
    },
    {
      "epoch": 0.10553129548762737,
      "grad_norm": 0.13281017541885376,
      "learning_rate": 4.926075302625247e-05,
      "loss": 0.19864981174468993,
      "step": 580
    },
    {
      "epoch": 0.1064410480349345,
      "grad_norm": 0.13465586304664612,
      "learning_rate": 4.924288021206639e-05,
      "loss": 0.19573183059692384,
      "step": 585
    },
    {
      "epoch": 0.10735080058224163,
      "grad_norm": 0.15225961804389954,
      "learning_rate": 4.9224797235582396e-05,
      "loss": 0.19946801662445068,
      "step": 590
    },
    {
      "epoch": 0.10826055312954876,
      "grad_norm": 0.12816746532917023,
      "learning_rate": 4.92065042535624e-05,
      "loss": 0.19851526021957397,
      "step": 595
    },
    {
      "epoch": 0.1091703056768559,
      "grad_norm": 0.13802853226661682,
      "learning_rate": 4.9188001424588824e-05,
      "loss": 0.19321763515472412,
      "step": 600
    },
    {
      "epoch": 0.11008005822416303,
      "grad_norm": 0.17504797875881195,
      "learning_rate": 4.9169288909063295e-05,
      "loss": 0.2032616138458252,
      "step": 605
    },
    {
      "epoch": 0.11098981077147016,
      "grad_norm": 0.13544194400310516,
      "learning_rate": 4.91503668692052e-05,
      "loss": 0.2011256456375122,
      "step": 610
    },
    {
      "epoch": 0.11189956331877729,
      "grad_norm": 1.3976134061813354,
      "learning_rate": 4.91312354690503e-05,
      "loss": 0.19916868209838867,
      "step": 615
    },
    {
      "epoch": 0.11280931586608442,
      "grad_norm": 0.1465059071779251,
      "learning_rate": 4.91118948744493e-05,
      "loss": 0.19487457275390624,
      "step": 620
    },
    {
      "epoch": 0.11371906841339156,
      "grad_norm": 0.12103168666362762,
      "learning_rate": 4.909234525306645e-05,
      "loss": 0.1907251238822937,
      "step": 625
    },
    {
      "epoch": 0.1146288209606987,
      "grad_norm": 0.12660574913024902,
      "learning_rate": 4.907258677437802e-05,
      "loss": 0.19327253103256226,
      "step": 630
    },
    {
      "epoch": 0.11553857350800582,
      "grad_norm": 0.1347813606262207,
      "learning_rate": 4.90526196096709e-05,
      "loss": 0.19637736082077026,
      "step": 635
    },
    {
      "epoch": 0.11644832605531295,
      "grad_norm": 0.14953652024269104,
      "learning_rate": 4.903244393204107e-05,
      "loss": 0.20325069427490233,
      "step": 640
    },
    {
      "epoch": 0.11735807860262008,
      "grad_norm": 0.13936272263526917,
      "learning_rate": 4.901205991639213e-05,
      "loss": 0.1930275321006775,
      "step": 645
    },
    {
      "epoch": 0.11826783114992721,
      "grad_norm": 0.1448420137166977,
      "learning_rate": 4.899146773943374e-05,
      "loss": 0.20026936531066894,
      "step": 650
    },
    {
      "epoch": 0.11917758369723436,
      "grad_norm": 0.1312534064054489,
      "learning_rate": 4.897066757968014e-05,
      "loss": 0.19062033891677857,
      "step": 655
    },
    {
      "epoch": 0.12008733624454149,
      "grad_norm": 0.13644742965698242,
      "learning_rate": 4.894965961744859e-05,
      "loss": 0.18719595670700073,
      "step": 660
    },
    {
      "epoch": 0.12099708879184862,
      "grad_norm": 0.14276087284088135,
      "learning_rate": 4.892844403485777e-05,
      "loss": 0.19784307479858398,
      "step": 665
    },
    {
      "epoch": 0.12190684133915575,
      "grad_norm": 0.14735399186611176,
      "learning_rate": 4.890702101582623e-05,
      "loss": 0.19163782596588136,
      "step": 670
    },
    {
      "epoch": 0.12281659388646288,
      "grad_norm": 0.15742065012454987,
      "learning_rate": 4.888539074607082e-05,
      "loss": 0.19312986135482788,
      "step": 675
    },
    {
      "epoch": 0.12372634643377002,
      "grad_norm": 0.12917031347751617,
      "learning_rate": 4.8863553413105025e-05,
      "loss": 0.20066320896148682,
      "step": 680
    },
    {
      "epoch": 0.12463609898107715,
      "grad_norm": 0.1484801322221756,
      "learning_rate": 4.884150920623737e-05,
      "loss": 0.20096096992492676,
      "step": 685
    },
    {
      "epoch": 0.12554585152838427,
      "grad_norm": 0.1455296128988266,
      "learning_rate": 4.88192583165698e-05,
      "loss": 0.20518505573272705,
      "step": 690
    },
    {
      "epoch": 0.12645560407569142,
      "grad_norm": 0.14517490565776825,
      "learning_rate": 4.879680093699598e-05,
      "loss": 0.18859238624572755,
      "step": 695
    },
    {
      "epoch": 0.12736535662299855,
      "grad_norm": 0.18778090178966522,
      "learning_rate": 4.877413726219964e-05,
      "loss": 0.197074818611145,
      "step": 700
    },
    {
      "epoch": 0.12827510917030568,
      "grad_norm": 0.13497677445411682,
      "learning_rate": 4.87512674886529e-05,
      "loss": 0.18713107109069824,
      "step": 705
    },
    {
      "epoch": 0.12918486171761281,
      "grad_norm": 0.12657155096530914,
      "learning_rate": 4.872819181461455e-05,
      "loss": 0.1858484387397766,
      "step": 710
    },
    {
      "epoch": 0.13009461426491994,
      "grad_norm": 0.11458148807287216,
      "learning_rate": 4.870491044012834e-05,
      "loss": 0.18732179403305055,
      "step": 715
    },
    {
      "epoch": 0.13100436681222707,
      "grad_norm": 0.13000249862670898,
      "learning_rate": 4.8681423567021244e-05,
      "loss": 0.1872936010360718,
      "step": 720
    },
    {
      "epoch": 0.1319141193595342,
      "grad_norm": 0.14580890536308289,
      "learning_rate": 4.865773139890172e-05,
      "loss": 0.19280019998550416,
      "step": 725
    },
    {
      "epoch": 0.13282387190684133,
      "grad_norm": 0.1507277935743332,
      "learning_rate": 4.8633834141157913e-05,
      "loss": 0.1898929238319397,
      "step": 730
    },
    {
      "epoch": 0.13373362445414846,
      "grad_norm": 0.1418737769126892,
      "learning_rate": 4.860973200095592e-05,
      "loss": 0.17926375865936278,
      "step": 735
    },
    {
      "epoch": 0.1346433770014556,
      "grad_norm": 0.17151866853237152,
      "learning_rate": 4.858542518723794e-05,
      "loss": 0.18963592052459716,
      "step": 740
    },
    {
      "epoch": 0.13555312954876272,
      "grad_norm": 0.11162743717432022,
      "learning_rate": 4.8560913910720535e-05,
      "loss": 0.19466646909713745,
      "step": 745
    },
    {
      "epoch": 0.13646288209606988,
      "grad_norm": 0.15628376603126526,
      "learning_rate": 4.8536198383892725e-05,
      "loss": 0.19494034051895143,
      "step": 750
    },
    {
      "epoch": 0.137372634643377,
      "grad_norm": 0.18209289014339447,
      "learning_rate": 4.851127882101421e-05,
      "loss": 0.18747550249099731,
      "step": 755
    },
    {
      "epoch": 0.13828238719068414,
      "grad_norm": 0.14559614658355713,
      "learning_rate": 4.8486155438113454e-05,
      "loss": 0.1897158980369568,
      "step": 760
    },
    {
      "epoch": 0.13919213973799127,
      "grad_norm": 0.3198587894439697,
      "learning_rate": 4.846082845298586e-05,
      "loss": 0.18571001291275024,
      "step": 765
    },
    {
      "epoch": 0.1401018922852984,
      "grad_norm": 0.1486678421497345,
      "learning_rate": 4.843529808519189e-05,
      "loss": 0.19561930894851684,
      "step": 770
    },
    {
      "epoch": 0.14101164483260553,
      "grad_norm": 0.15318170189857483,
      "learning_rate": 4.840956455605509e-05,
      "loss": 0.187040114402771,
      "step": 775
    },
    {
      "epoch": 0.14192139737991266,
      "grad_norm": 0.13754244148731232,
      "learning_rate": 4.838362808866025e-05,
      "loss": 0.18345539569854735,
      "step": 780
    },
    {
      "epoch": 0.1428311499272198,
      "grad_norm": 0.12943248450756073,
      "learning_rate": 4.835748890785143e-05,
      "loss": 0.1921079397201538,
      "step": 785
    },
    {
      "epoch": 0.14374090247452692,
      "grad_norm": 0.110458143055439,
      "learning_rate": 4.833114724023001e-05,
      "loss": 0.17927205562591553,
      "step": 790
    },
    {
      "epoch": 0.14465065502183405,
      "grad_norm": 0.2421770840883255,
      "learning_rate": 4.830460331415275e-05,
      "loss": 0.18317567110061644,
      "step": 795
    },
    {
      "epoch": 0.14556040756914118,
      "grad_norm": 0.14752762019634247,
      "learning_rate": 4.8277857359729787e-05,
      "loss": 0.1843916058540344,
      "step": 800
    },
    {
      "epoch": 0.14647016011644834,
      "grad_norm": 0.15043556690216064,
      "learning_rate": 4.8250909608822644e-05,
      "loss": 0.18354393243789674,
      "step": 805
    },
    {
      "epoch": 0.14737991266375547,
      "grad_norm": 0.1381794661283493,
      "learning_rate": 4.822376029504223e-05,
      "loss": 0.1789781332015991,
      "step": 810
    },
    {
      "epoch": 0.1482896652110626,
      "grad_norm": 0.18386174738407135,
      "learning_rate": 4.819640965374681e-05,
      "loss": 0.19494292736053467,
      "step": 815
    },
    {
      "epoch": 0.14919941775836973,
      "grad_norm": 0.13829593360424042,
      "learning_rate": 4.816885792203996e-05,
      "loss": 0.18486063480377196,
      "step": 820
    },
    {
      "epoch": 0.15010917030567686,
      "grad_norm": 0.15033291280269623,
      "learning_rate": 4.814110533876852e-05,
      "loss": 0.18061509132385253,
      "step": 825
    },
    {
      "epoch": 0.151018922852984,
      "grad_norm": 0.17150473594665527,
      "learning_rate": 4.811315214452051e-05,
      "loss": 0.18464866876602173,
      "step": 830
    },
    {
      "epoch": 0.15192867540029112,
      "grad_norm": 0.15317125618457794,
      "learning_rate": 4.808499858162307e-05,
      "loss": 0.1837708592414856,
      "step": 835
    },
    {
      "epoch": 0.15283842794759825,
      "grad_norm": 0.2671392560005188,
      "learning_rate": 4.805664489414031e-05,
      "loss": 0.19338636398315429,
      "step": 840
    },
    {
      "epoch": 0.15374818049490538,
      "grad_norm": 0.14047028124332428,
      "learning_rate": 4.802809132787125e-05,
      "loss": 0.17069108486175538,
      "step": 845
    },
    {
      "epoch": 0.1546579330422125,
      "grad_norm": 0.1520431935787201,
      "learning_rate": 4.799933813034768e-05,
      "loss": 0.18607735633850098,
      "step": 850
    },
    {
      "epoch": 0.15556768558951964,
      "grad_norm": 0.17239463329315186,
      "learning_rate": 4.797038555083197e-05,
      "loss": 0.18069062232971192,
      "step": 855
    },
    {
      "epoch": 0.1564774381368268,
      "grad_norm": 0.1377955675125122,
      "learning_rate": 4.794123384031495e-05,
      "loss": 0.18870222568511963,
      "step": 860
    },
    {
      "epoch": 0.15738719068413393,
      "grad_norm": 0.15901461243629456,
      "learning_rate": 4.791188325151373e-05,
      "loss": 0.18128334283828734,
      "step": 865
    },
    {
      "epoch": 0.15829694323144106,
      "grad_norm": 0.14634132385253906,
      "learning_rate": 4.7882334038869495e-05,
      "loss": 0.1866163969039917,
      "step": 870
    },
    {
      "epoch": 0.1592066957787482,
      "grad_norm": 0.15361061692237854,
      "learning_rate": 4.785258645854529e-05,
      "loss": 0.17850807905197144,
      "step": 875
    },
    {
      "epoch": 0.16011644832605532,
      "grad_norm": 0.13751649856567383,
      "learning_rate": 4.782264076842385e-05,
      "loss": 0.17731113433837892,
      "step": 880
    },
    {
      "epoch": 0.16102620087336245,
      "grad_norm": 0.17909638583660126,
      "learning_rate": 4.7792497228105314e-05,
      "loss": 0.18344542980194092,
      "step": 885
    },
    {
      "epoch": 0.16193595342066958,
      "grad_norm": 0.16038304567337036,
      "learning_rate": 4.776215609890498e-05,
      "loss": 0.18868647813796996,
      "step": 890
    },
    {
      "epoch": 0.1628457059679767,
      "grad_norm": 0.1653951108455658,
      "learning_rate": 4.773161764385107e-05,
      "loss": 0.18614152669906617,
      "step": 895
    },
    {
      "epoch": 0.16375545851528384,
      "grad_norm": 0.16193026304244995,
      "learning_rate": 4.770088212768241e-05,
      "loss": 0.18564575910568237,
      "step": 900
    },
    {
      "epoch": 0.16466521106259097,
      "grad_norm": 0.16048531234264374,
      "learning_rate": 4.7669949816846173e-05,
      "loss": 0.18330031633377075,
      "step": 905
    },
    {
      "epoch": 0.1655749636098981,
      "grad_norm": 0.1440177708864212,
      "learning_rate": 4.7638820979495534e-05,
      "loss": 0.17712442874908446,
      "step": 910
    },
    {
      "epoch": 0.16648471615720525,
      "grad_norm": 0.19635969400405884,
      "learning_rate": 4.760749588548738e-05,
      "loss": 0.18679027557373046,
      "step": 915
    },
    {
      "epoch": 0.16739446870451238,
      "grad_norm": 0.15576541423797607,
      "learning_rate": 4.757597480637995e-05,
      "loss": 0.19283764362335204,
      "step": 920
    },
    {
      "epoch": 0.1683042212518195,
      "grad_norm": 0.1550331562757492,
      "learning_rate": 4.7544258015430463e-05,
      "loss": 0.18269542455673218,
      "step": 925
    },
    {
      "epoch": 0.16921397379912664,
      "grad_norm": 0.18369626998901367,
      "learning_rate": 4.75123457875928e-05,
      "loss": 0.1697891116142273,
      "step": 930
    },
    {
      "epoch": 0.17012372634643377,
      "grad_norm": 0.15266314148902893,
      "learning_rate": 4.7480238399515074e-05,
      "loss": 0.18523451089859008,
      "step": 935
    },
    {
      "epoch": 0.1710334788937409,
      "grad_norm": 0.16709664463996887,
      "learning_rate": 4.744793612953724e-05,
      "loss": 0.1803238034248352,
      "step": 940
    },
    {
      "epoch": 0.17194323144104803,
      "grad_norm": 0.14929179847240448,
      "learning_rate": 4.741543925768872e-05,
      "loss": 0.1861217737197876,
      "step": 945
    },
    {
      "epoch": 0.17285298398835516,
      "grad_norm": 0.1362280696630478,
      "learning_rate": 4.7382748065685915e-05,
      "loss": 0.17896100282669067,
      "step": 950
    },
    {
      "epoch": 0.1737627365356623,
      "grad_norm": 0.15290239453315735,
      "learning_rate": 4.734986283692982e-05,
      "loss": 0.18432788848876952,
      "step": 955
    },
    {
      "epoch": 0.17467248908296942,
      "grad_norm": 0.1287035197019577,
      "learning_rate": 4.73167838565035e-05,
      "loss": 0.18485682010650634,
      "step": 960
    },
    {
      "epoch": 0.17558224163027655,
      "grad_norm": 0.17969627678394318,
      "learning_rate": 4.728351141116971e-05,
      "loss": 0.17361557483673096,
      "step": 965
    },
    {
      "epoch": 0.1764919941775837,
      "grad_norm": 0.13751201331615448,
      "learning_rate": 4.7250045789368326e-05,
      "loss": 0.1731679320335388,
      "step": 970
    },
    {
      "epoch": 0.17740174672489084,
      "grad_norm": 0.1603265255689621,
      "learning_rate": 4.721638728121388e-05,
      "loss": 0.17308170795440675,
      "step": 975
    },
    {
      "epoch": 0.17831149927219797,
      "grad_norm": 0.1592789888381958,
      "learning_rate": 4.718253617849306e-05,
      "loss": 0.17534757852554322,
      "step": 980
    },
    {
      "epoch": 0.1792212518195051,
      "grad_norm": 0.12727224826812744,
      "learning_rate": 4.714849277466214e-05,
      "loss": 0.17817609310150145,
      "step": 985
    },
    {
      "epoch": 0.18013100436681223,
      "grad_norm": 0.15401554107666016,
      "learning_rate": 4.711425736484447e-05,
      "loss": 0.1733405351638794,
      "step": 990
    },
    {
      "epoch": 0.18104075691411936,
      "grad_norm": 0.13253968954086304,
      "learning_rate": 4.7079830245827906e-05,
      "loss": 0.17846795320510864,
      "step": 995
    },
    {
      "epoch": 0.1819505094614265,
      "grad_norm": 0.21846213936805725,
      "learning_rate": 4.7045211716062245e-05,
      "loss": 0.18021599054336548,
      "step": 1000
    },
    {
      "epoch": 0.18286026200873362,
      "grad_norm": 0.16867990791797638,
      "learning_rate": 4.7010402075656595e-05,
      "loss": 0.18232386112213134,
      "step": 1005
    },
    {
      "epoch": 0.18377001455604075,
      "grad_norm": 0.17180582880973816,
      "learning_rate": 4.697540162637686e-05,
      "loss": 0.1816317319869995,
      "step": 1010
    },
    {
      "epoch": 0.18467976710334788,
      "grad_norm": 0.16480213403701782,
      "learning_rate": 4.694021067164303e-05,
      "loss": 0.17718446254730225,
      "step": 1015
    },
    {
      "epoch": 0.185589519650655,
      "grad_norm": 0.15015918016433716,
      "learning_rate": 4.6904829516526605e-05,
      "loss": 0.17412011623382567,
      "step": 1020
    },
    {
      "epoch": 0.18649927219796217,
      "grad_norm": 0.14445139467716217,
      "learning_rate": 4.686925846774795e-05,
      "loss": 0.1778018832206726,
      "step": 1025
    },
    {
      "epoch": 0.1874090247452693,
      "grad_norm": 0.1701960265636444,
      "learning_rate": 4.683349783367362e-05,
      "loss": 0.16901081800460815,
      "step": 1030
    },
    {
      "epoch": 0.18831877729257643,
      "grad_norm": 0.15894867479801178,
      "learning_rate": 4.679754792431368e-05,
      "loss": 0.17055928707122803,
      "step": 1035
    },
    {
      "epoch": 0.18922852983988356,
      "grad_norm": 0.1511942446231842,
      "learning_rate": 4.676140905131903e-05,
      "loss": 0.17339680194854737,
      "step": 1040
    },
    {
      "epoch": 0.1901382823871907,
      "grad_norm": 0.14735209941864014,
      "learning_rate": 4.672508152797872e-05,
      "loss": 0.17802717685699462,
      "step": 1045
    },
    {
      "epoch": 0.19104803493449782,
      "grad_norm": 0.17367291450500488,
      "learning_rate": 4.66885656692172e-05,
      "loss": 0.1732744097709656,
      "step": 1050
    },
    {
      "epoch": 0.19195778748180495,
      "grad_norm": 0.147227481007576,
      "learning_rate": 4.665186179159159e-05,
      "loss": 0.17040517330169677,
      "step": 1055
    },
    {
      "epoch": 0.19286754002911208,
      "grad_norm": 0.1709655076265335,
      "learning_rate": 4.6614970213289e-05,
      "loss": 0.17794088125228882,
      "step": 1060
    },
    {
      "epoch": 0.1937772925764192,
      "grad_norm": 0.1588088721036911,
      "learning_rate": 4.657789125412366e-05,
      "loss": 0.17180380821228028,
      "step": 1065
    },
    {
      "epoch": 0.19468704512372634,
      "grad_norm": 0.14827021956443787,
      "learning_rate": 4.654062523553428e-05,
      "loss": 0.182997989654541,
      "step": 1070
    },
    {
      "epoch": 0.19559679767103347,
      "grad_norm": 0.16230466961860657,
      "learning_rate": 4.6503172480581126e-05,
      "loss": 0.17346880435943604,
      "step": 1075
    },
    {
      "epoch": 0.1965065502183406,
      "grad_norm": 0.1637624353170395,
      "learning_rate": 4.646553331394333e-05,
      "loss": 0.17263576984405518,
      "step": 1080
    },
    {
      "epoch": 0.19741630276564776,
      "grad_norm": 0.15977843105793,
      "learning_rate": 4.642770806191603e-05,
      "loss": 0.17284308671951293,
      "step": 1085
    },
    {
      "epoch": 0.19832605531295489,
      "grad_norm": 0.15394869446754456,
      "learning_rate": 4.6389697052407534e-05,
      "loss": 0.17797101736068727,
      "step": 1090
    },
    {
      "epoch": 0.19923580786026202,
      "grad_norm": 0.15995225310325623,
      "learning_rate": 4.6351500614936485e-05,
      "loss": 0.18137198686599731,
      "step": 1095
    },
    {
      "epoch": 0.20014556040756915,
      "grad_norm": 0.1779479682445526,
      "learning_rate": 4.6313119080629006e-05,
      "loss": 0.17998344898223878,
      "step": 1100
    },
    {
      "epoch": 0.20105531295487628,
      "grad_norm": 0.14362832903862,
      "learning_rate": 4.627455278221584e-05,
      "loss": 0.18196423053741456,
      "step": 1105
    },
    {
      "epoch": 0.2019650655021834,
      "grad_norm": 0.15951639413833618,
      "learning_rate": 4.623580205402947e-05,
      "loss": 0.17423888444900512,
      "step": 1110
    },
    {
      "epoch": 0.20287481804949054,
      "grad_norm": 0.17273563146591187,
      "learning_rate": 4.619686723200115e-05,
      "loss": 0.17392473220825194,
      "step": 1115
    },
    {
      "epoch": 0.20378457059679767,
      "grad_norm": 0.1655360758304596,
      "learning_rate": 4.615774865365813e-05,
      "loss": 0.17528389692306517,
      "step": 1120
    },
    {
      "epoch": 0.2046943231441048,
      "grad_norm": 0.15920691192150116,
      "learning_rate": 4.611844665812058e-05,
      "loss": 0.1806849241256714,
      "step": 1125
    },
    {
      "epoch": 0.20560407569141192,
      "grad_norm": 0.16114577651023865,
      "learning_rate": 4.607896158609875e-05,
      "loss": 0.17217352390289306,
      "step": 1130
    },
    {
      "epoch": 0.20651382823871905,
      "grad_norm": 0.1499422937631607,
      "learning_rate": 4.603929377988999e-05,
      "loss": 0.17806737422943114,
      "step": 1135
    },
    {
      "epoch": 0.2074235807860262,
      "grad_norm": 0.17605191469192505,
      "learning_rate": 4.5999443583375765e-05,
      "loss": 0.17842113971710205,
      "step": 1140
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 0.16117210686206818,
      "learning_rate": 4.595941134201871e-05,
      "loss": 0.18379683494567872,
      "step": 1145
    },
    {
      "epoch": 0.20924308588064047,
      "grad_norm": 0.21199050545692444,
      "learning_rate": 4.591919740285957e-05,
      "loss": 0.16286123991012574,
      "step": 1150
    },
    {
      "epoch": 0.2101528384279476,
      "grad_norm": 0.15100529789924622,
      "learning_rate": 4.587880211451427e-05,
      "loss": 0.17995200157165528,
      "step": 1155
    },
    {
      "epoch": 0.21106259097525473,
      "grad_norm": 0.16618172824382782,
      "learning_rate": 4.583822582717085e-05,
      "loss": 0.16960303783416747,
      "step": 1160
    },
    {
      "epoch": 0.21197234352256186,
      "grad_norm": 0.14743569493293762,
      "learning_rate": 4.579746889258643e-05,
      "loss": 0.17762668132781984,
      "step": 1165
    },
    {
      "epoch": 0.212882096069869,
      "grad_norm": 0.1697179079055786,
      "learning_rate": 4.575653166408417e-05,
      "loss": 0.16656005382537842,
      "step": 1170
    },
    {
      "epoch": 0.21379184861717612,
      "grad_norm": 0.14886513352394104,
      "learning_rate": 4.57154144965502e-05,
      "loss": 0.17091882228851318,
      "step": 1175
    },
    {
      "epoch": 0.21470160116448325,
      "grad_norm": 0.18197473883628845,
      "learning_rate": 4.5674117746430556e-05,
      "loss": 0.1770920753479004,
      "step": 1180
    },
    {
      "epoch": 0.21561135371179038,
      "grad_norm": 0.17323088645935059,
      "learning_rate": 4.563264177172807e-05,
      "loss": 0.1734643578529358,
      "step": 1185
    },
    {
      "epoch": 0.2165211062590975,
      "grad_norm": 0.1521984338760376,
      "learning_rate": 4.559098693199929e-05,
      "loss": 0.17515116930007935,
      "step": 1190
    },
    {
      "epoch": 0.21743085880640467,
      "grad_norm": 0.1842304915189743,
      "learning_rate": 4.554915358835134e-05,
      "loss": 0.16798022985458375,
      "step": 1195
    },
    {
      "epoch": 0.2183406113537118,
      "grad_norm": 0.14753451943397522,
      "learning_rate": 4.5507142103438794e-05,
      "loss": 0.1755476713180542,
      "step": 1200
    },
    {
      "epoch": 0.21925036390101893,
      "grad_norm": 0.17096194624900818,
      "learning_rate": 4.546495284146057e-05,
      "loss": 0.1792473554611206,
      "step": 1205
    },
    {
      "epoch": 0.22016011644832606,
      "grad_norm": 0.1579233556985855,
      "learning_rate": 4.542258616815669e-05,
      "loss": 0.17230144739151002,
      "step": 1210
    },
    {
      "epoch": 0.2210698689956332,
      "grad_norm": 0.177297905087471,
      "learning_rate": 4.5380042450805216e-05,
      "loss": 0.1807127833366394,
      "step": 1215
    },
    {
      "epoch": 0.22197962154294032,
      "grad_norm": 0.14331696927547455,
      "learning_rate": 4.533732205821897e-05,
      "loss": 0.17201389074325563,
      "step": 1220
    },
    {
      "epoch": 0.22288937409024745,
      "grad_norm": 0.14473360776901245,
      "learning_rate": 4.529442536074239e-05,
      "loss": 0.17036900520324708,
      "step": 1225
    },
    {
      "epoch": 0.22379912663755458,
      "grad_norm": 0.1820901483297348,
      "learning_rate": 4.5251352730248314e-05,
      "loss": 0.17704882621765136,
      "step": 1230
    },
    {
      "epoch": 0.2247088791848617,
      "grad_norm": 0.1948976367712021,
      "learning_rate": 4.5208104540134746e-05,
      "loss": 0.1706973433494568,
      "step": 1235
    },
    {
      "epoch": 0.22561863173216884,
      "grad_norm": 0.16660070419311523,
      "learning_rate": 4.51646811653216e-05,
      "loss": 0.17636821269989014,
      "step": 1240
    },
    {
      "epoch": 0.22652838427947597,
      "grad_norm": 0.1699984073638916,
      "learning_rate": 4.512108298224751e-05,
      "loss": 0.16986632347106934,
      "step": 1245
    },
    {
      "epoch": 0.22743813682678313,
      "grad_norm": 0.17601042985916138,
      "learning_rate": 4.50773103688665e-05,
      "loss": 0.17507898807525635,
      "step": 1250
    },
    {
      "epoch": 0.22834788937409026,
      "grad_norm": 0.17557238042354584,
      "learning_rate": 4.503336370464476e-05,
      "loss": 0.17702863216400147,
      "step": 1255
    },
    {
      "epoch": 0.2292576419213974,
      "grad_norm": 0.1800651252269745,
      "learning_rate": 4.498924337055729e-05,
      "loss": 0.16419180631637573,
      "step": 1260
    },
    {
      "epoch": 0.23016739446870452,
      "grad_norm": 0.2022479772567749,
      "learning_rate": 4.494494974908468e-05,
      "loss": 0.17482060194015503,
      "step": 1265
    },
    {
      "epoch": 0.23107714701601165,
      "grad_norm": 0.14180205762386322,
      "learning_rate": 4.490048322420973e-05,
      "loss": 0.1723136067390442,
      "step": 1270
    },
    {
      "epoch": 0.23198689956331878,
      "grad_norm": 0.18607310950756073,
      "learning_rate": 4.485584418141419e-05,
      "loss": 0.17096419334411622,
      "step": 1275
    },
    {
      "epoch": 0.2328966521106259,
      "grad_norm": 0.15958310663700104,
      "learning_rate": 4.481103300767529e-05,
      "loss": 0.1656244158744812,
      "step": 1280
    },
    {
      "epoch": 0.23380640465793304,
      "grad_norm": 0.17552383244037628,
      "learning_rate": 4.476605009146255e-05,
      "loss": 0.17677626609802247,
      "step": 1285
    },
    {
      "epoch": 0.23471615720524017,
      "grad_norm": 0.15299823880195618,
      "learning_rate": 4.472089582273429e-05,
      "loss": 0.1778991103172302,
      "step": 1290
    },
    {
      "epoch": 0.2356259097525473,
      "grad_norm": 0.14613987505435944,
      "learning_rate": 4.46755705929343e-05,
      "loss": 0.17071452140808105,
      "step": 1295
    },
    {
      "epoch": 0.23653566229985443,
      "grad_norm": 0.17781122028827667,
      "learning_rate": 4.463007479498843e-05,
      "loss": 0.16955430507659913,
      "step": 1300
    },
    {
      "epoch": 0.23744541484716158,
      "grad_norm": 0.16326487064361572,
      "learning_rate": 4.458440882330119e-05,
      "loss": 0.1777693510055542,
      "step": 1305
    },
    {
      "epoch": 0.23835516739446871,
      "grad_norm": 0.17701926827430725,
      "learning_rate": 4.4538573073752365e-05,
      "loss": 0.16323351860046387,
      "step": 1310
    },
    {
      "epoch": 0.23926491994177584,
      "grad_norm": 0.13104717433452606,
      "learning_rate": 4.449256794369349e-05,
      "loss": 0.17653456926345826,
      "step": 1315
    },
    {
      "epoch": 0.24017467248908297,
      "grad_norm": 0.1796836256980896,
      "learning_rate": 4.444639383194452e-05,
      "loss": 0.17189600467681884,
      "step": 1320
    },
    {
      "epoch": 0.2410844250363901,
      "grad_norm": 0.14919696748256683,
      "learning_rate": 4.440005113879029e-05,
      "loss": 0.17003334760665895,
      "step": 1325
    },
    {
      "epoch": 0.24199417758369723,
      "grad_norm": 0.1728784441947937,
      "learning_rate": 4.4353540265977064e-05,
      "loss": 0.17397408485412597,
      "step": 1330
    },
    {
      "epoch": 0.24290393013100436,
      "grad_norm": 0.14591015875339508,
      "learning_rate": 4.43068616167091e-05,
      "loss": 0.16498478651046752,
      "step": 1335
    },
    {
      "epoch": 0.2438136826783115,
      "grad_norm": 0.18417201936244965,
      "learning_rate": 4.4260015595645055e-05,
      "loss": 0.16841750144958495,
      "step": 1340
    },
    {
      "epoch": 0.24472343522561862,
      "grad_norm": 0.16264279186725616,
      "learning_rate": 4.4213002608894605e-05,
      "loss": 0.16907373666763306,
      "step": 1345
    },
    {
      "epoch": 0.24563318777292575,
      "grad_norm": 0.15248481929302216,
      "learning_rate": 4.416582306401481e-05,
      "loss": 0.15931472778320313,
      "step": 1350
    },
    {
      "epoch": 0.24654294032023288,
      "grad_norm": 0.1488373875617981,
      "learning_rate": 4.4118477370006636e-05,
      "loss": 0.1701716423034668,
      "step": 1355
    },
    {
      "epoch": 0.24745269286754004,
      "grad_norm": 0.14679782092571259,
      "learning_rate": 4.407096593731142e-05,
      "loss": 0.157412326335907,
      "step": 1360
    },
    {
      "epoch": 0.24836244541484717,
      "grad_norm": 0.17139530181884766,
      "learning_rate": 4.402328917780728e-05,
      "loss": 0.17303754091262818,
      "step": 1365
    },
    {
      "epoch": 0.2492721979621543,
      "grad_norm": 0.1534871757030487,
      "learning_rate": 4.397544750480554e-05,
      "loss": 0.1786255121231079,
      "step": 1370
    },
    {
      "epoch": 0.2501819505094614,
      "grad_norm": 0.1876252293586731,
      "learning_rate": 4.39274413330472e-05,
      "loss": 0.16442898511886597,
      "step": 1375
    },
    {
      "epoch": 0.25109170305676853,
      "grad_norm": 0.16165752708911896,
      "learning_rate": 4.387927107869928e-05,
      "loss": 0.1780426025390625,
      "step": 1380
    },
    {
      "epoch": 0.25200145560407566,
      "grad_norm": 0.17242255806922913,
      "learning_rate": 4.383093715935124e-05,
      "loss": 0.15959256887435913,
      "step": 1385
    },
    {
      "epoch": 0.25291120815138285,
      "grad_norm": 0.1627114862203598,
      "learning_rate": 4.378243999401137e-05,
      "loss": 0.17606115341186523,
      "step": 1390
    },
    {
      "epoch": 0.25382096069869,
      "grad_norm": 0.15911224484443665,
      "learning_rate": 4.373378000310312e-05,
      "loss": 0.16798585653305054,
      "step": 1395
    },
    {
      "epoch": 0.2547307132459971,
      "grad_norm": 0.15542249381542206,
      "learning_rate": 4.3684957608461505e-05,
      "loss": 0.1695417881011963,
      "step": 1400
    },
    {
      "epoch": 0.25564046579330424,
      "grad_norm": 0.1475304812192917,
      "learning_rate": 4.363597323332941e-05,
      "loss": 0.16340878009796142,
      "step": 1405
    },
    {
      "epoch": 0.25655021834061137,
      "grad_norm": 0.16943927109241486,
      "learning_rate": 4.358682730235395e-05,
      "loss": 0.17240238189697266,
      "step": 1410
    },
    {
      "epoch": 0.2574599708879185,
      "grad_norm": 0.1816391944885254,
      "learning_rate": 4.3537520241582744e-05,
      "loss": 0.16558437347412108,
      "step": 1415
    },
    {
      "epoch": 0.25836972343522563,
      "grad_norm": 0.23851341009140015,
      "learning_rate": 4.348805247846027e-05,
      "loss": 0.16796000003814698,
      "step": 1420
    },
    {
      "epoch": 0.25927947598253276,
      "grad_norm": 0.15415243804454803,
      "learning_rate": 4.343842444182414e-05,
      "loss": 0.1746017098426819,
      "step": 1425
    },
    {
      "epoch": 0.2601892285298399,
      "grad_norm": 0.15651032328605652,
      "learning_rate": 4.338863656190139e-05,
      "loss": 0.1649057984352112,
      "step": 1430
    },
    {
      "epoch": 0.261098981077147,
      "grad_norm": 0.16601966321468353,
      "learning_rate": 4.333868927030471e-05,
      "loss": 0.15888988971710205,
      "step": 1435
    },
    {
      "epoch": 0.26200873362445415,
      "grad_norm": 0.1549467295408249,
      "learning_rate": 4.328858300002876e-05,
      "loss": 0.16357985734939576,
      "step": 1440
    },
    {
      "epoch": 0.2629184861717613,
      "grad_norm": 0.16332370042800903,
      "learning_rate": 4.32383181854464e-05,
      "loss": 0.16749982833862304,
      "step": 1445
    },
    {
      "epoch": 0.2638282387190684,
      "grad_norm": 0.14827077090740204,
      "learning_rate": 4.3187895262304894e-05,
      "loss": 0.16886214017868043,
      "step": 1450
    },
    {
      "epoch": 0.26473799126637554,
      "grad_norm": 0.1557198166847229,
      "learning_rate": 4.313731466772216e-05,
      "loss": 0.17512214183807373,
      "step": 1455
    },
    {
      "epoch": 0.26564774381368267,
      "grad_norm": 0.17263570427894592,
      "learning_rate": 4.308657684018299e-05,
      "loss": 0.16248074769973755,
      "step": 1460
    },
    {
      "epoch": 0.2665574963609898,
      "grad_norm": 0.17135761678218842,
      "learning_rate": 4.303568221953521e-05,
      "loss": 0.16605921983718872,
      "step": 1465
    },
    {
      "epoch": 0.26746724890829693,
      "grad_norm": 0.14322632551193237,
      "learning_rate": 4.2984631246985897e-05,
      "loss": 0.1610772728919983,
      "step": 1470
    },
    {
      "epoch": 0.26837700145560406,
      "grad_norm": 0.18852312862873077,
      "learning_rate": 4.2933424365097564e-05,
      "loss": 0.1686462163925171,
      "step": 1475
    },
    {
      "epoch": 0.2692867540029112,
      "grad_norm": 0.1780245155096054,
      "learning_rate": 4.2882062017784294e-05,
      "loss": 0.16953932046890258,
      "step": 1480
    },
    {
      "epoch": 0.2701965065502183,
      "grad_norm": 0.180568665266037,
      "learning_rate": 4.2830544650307895e-05,
      "loss": 0.16442664861679077,
      "step": 1485
    },
    {
      "epoch": 0.27110625909752545,
      "grad_norm": 0.16876435279846191,
      "learning_rate": 4.277887270927407e-05,
      "loss": 0.17128173112869263,
      "step": 1490
    },
    {
      "epoch": 0.2720160116448326,
      "grad_norm": 0.164053276181221,
      "learning_rate": 4.2727046642628513e-05,
      "loss": 0.16331382989883422,
      "step": 1495
    },
    {
      "epoch": 0.27292576419213976,
      "grad_norm": 0.14577528834342957,
      "learning_rate": 4.267506689965305e-05,
      "loss": 0.1638316035270691,
      "step": 1500
    },
    {
      "epoch": 0.2738355167394469,
      "grad_norm": 0.1648740917444229,
      "learning_rate": 4.262293393096171e-05,
      "loss": 0.15332664251327516,
      "step": 1505
    },
    {
      "epoch": 0.274745269286754,
      "grad_norm": 0.16445094347000122,
      "learning_rate": 4.257064818849685e-05,
      "loss": 0.1706634521484375,
      "step": 1510
    },
    {
      "epoch": 0.27565502183406115,
      "grad_norm": 0.1584935486316681,
      "learning_rate": 4.251821012552524e-05,
      "loss": 0.1684114694595337,
      "step": 1515
    },
    {
      "epoch": 0.2765647743813683,
      "grad_norm": 0.17215611040592194,
      "learning_rate": 4.24656201966341e-05,
      "loss": 0.15594131946563722,
      "step": 1520
    },
    {
      "epoch": 0.2774745269286754,
      "grad_norm": 0.15945589542388916,
      "learning_rate": 4.2412878857727214e-05,
      "loss": 0.1686659574508667,
      "step": 1525
    },
    {
      "epoch": 0.27838427947598254,
      "grad_norm": 0.16103951632976532,
      "learning_rate": 4.2359986566020906e-05,
      "loss": 0.17779340744018554,
      "step": 1530
    },
    {
      "epoch": 0.2792940320232897,
      "grad_norm": 0.1770307570695877,
      "learning_rate": 4.230694378004014e-05,
      "loss": 0.16786882877349854,
      "step": 1535
    },
    {
      "epoch": 0.2802037845705968,
      "grad_norm": 0.16225053369998932,
      "learning_rate": 4.2253750959614504e-05,
      "loss": 0.16558897495269775,
      "step": 1540
    },
    {
      "epoch": 0.28111353711790393,
      "grad_norm": 0.27213969826698303,
      "learning_rate": 4.220040856587425e-05,
      "loss": 0.1641119599342346,
      "step": 1545
    },
    {
      "epoch": 0.28202328966521106,
      "grad_norm": 0.1773071587085724,
      "learning_rate": 4.2146917061246284e-05,
      "loss": 0.16919140815734862,
      "step": 1550
    },
    {
      "epoch": 0.2829330422125182,
      "grad_norm": 0.15519705414772034,
      "learning_rate": 4.209327690945014e-05,
      "loss": 0.15501506328582765,
      "step": 1555
    },
    {
      "epoch": 0.2838427947598253,
      "grad_norm": 0.19921597838401794,
      "learning_rate": 4.203948857549402e-05,
      "loss": 0.1690821886062622,
      "step": 1560
    },
    {
      "epoch": 0.28475254730713245,
      "grad_norm": 0.15417630970478058,
      "learning_rate": 4.1985552525670696e-05,
      "loss": 0.1675640344619751,
      "step": 1565
    },
    {
      "epoch": 0.2856622998544396,
      "grad_norm": 0.1739572137594223,
      "learning_rate": 4.193146922755348e-05,
      "loss": 0.16738017797470092,
      "step": 1570
    },
    {
      "epoch": 0.2865720524017467,
      "grad_norm": 0.1384361982345581,
      "learning_rate": 4.187723914999221e-05,
      "loss": 0.16802358627319336,
      "step": 1575
    },
    {
      "epoch": 0.28748180494905384,
      "grad_norm": 0.1491454839706421,
      "learning_rate": 4.182286276310915e-05,
      "loss": 0.1619583249092102,
      "step": 1580
    },
    {
      "epoch": 0.288391557496361,
      "grad_norm": 0.15831919014453888,
      "learning_rate": 4.176834053829492e-05,
      "loss": 0.1625199794769287,
      "step": 1585
    },
    {
      "epoch": 0.2893013100436681,
      "grad_norm": 0.16265396773815155,
      "learning_rate": 4.1713672948204416e-05,
      "loss": 0.16718552112579346,
      "step": 1590
    },
    {
      "epoch": 0.29021106259097523,
      "grad_norm": 0.15153461694717407,
      "learning_rate": 4.1658860466752714e-05,
      "loss": 0.15979087352752686,
      "step": 1595
    },
    {
      "epoch": 0.29112081513828236,
      "grad_norm": 0.1620412915945053,
      "learning_rate": 4.160390356911096e-05,
      "loss": 0.16103557348251343,
      "step": 1600
    },
    {
      "epoch": 0.2920305676855895,
      "grad_norm": 0.16673807799816132,
      "learning_rate": 4.154880273170223e-05,
      "loss": 0.16394708156585694,
      "step": 1605
    },
    {
      "epoch": 0.2929403202328967,
      "grad_norm": 0.14834867417812347,
      "learning_rate": 4.149355843219744e-05,
      "loss": 0.15916435718536376,
      "step": 1610
    },
    {
      "epoch": 0.2938500727802038,
      "grad_norm": 0.16977964341640472,
      "learning_rate": 4.143817114951119e-05,
      "loss": 0.16538127660751342,
      "step": 1615
    },
    {
      "epoch": 0.29475982532751094,
      "grad_norm": 0.17986875772476196,
      "learning_rate": 4.138264136379756e-05,
      "loss": 0.15514618158340454,
      "step": 1620
    },
    {
      "epoch": 0.29566957787481807,
      "grad_norm": 0.15794920921325684,
      "learning_rate": 4.132696955644605e-05,
      "loss": 0.15992183685302735,
      "step": 1625
    },
    {
      "epoch": 0.2965793304221252,
      "grad_norm": 0.19955399632453918,
      "learning_rate": 4.127115621007731e-05,
      "loss": 0.16362056732177735,
      "step": 1630
    },
    {
      "epoch": 0.29748908296943233,
      "grad_norm": 0.1352023035287857,
      "learning_rate": 4.121520180853903e-05,
      "loss": 0.15631601810455323,
      "step": 1635
    },
    {
      "epoch": 0.29839883551673946,
      "grad_norm": 0.15340781211853027,
      "learning_rate": 4.1159106836901674e-05,
      "loss": 0.1571858048439026,
      "step": 1640
    },
    {
      "epoch": 0.2993085880640466,
      "grad_norm": 0.15311770141124725,
      "learning_rate": 4.110287178145433e-05,
      "loss": 0.16082344055175782,
      "step": 1645
    },
    {
      "epoch": 0.3002183406113537,
      "grad_norm": 0.17811627686023712,
      "learning_rate": 4.10464971297005e-05,
      "loss": 0.16117215156555176,
      "step": 1650
    },
    {
      "epoch": 0.30112809315866085,
      "grad_norm": 0.21060039103031158,
      "learning_rate": 4.0989983370353805e-05,
      "loss": 0.15838587284088135,
      "step": 1655
    },
    {
      "epoch": 0.302037845705968,
      "grad_norm": 0.155836820602417,
      "learning_rate": 4.093333099333383e-05,
      "loss": 0.16648870706558228,
      "step": 1660
    },
    {
      "epoch": 0.3029475982532751,
      "grad_norm": 0.13711698353290558,
      "learning_rate": 4.0876540489761826e-05,
      "loss": 0.16899349689483642,
      "step": 1665
    },
    {
      "epoch": 0.30385735080058224,
      "grad_norm": 0.15162716805934906,
      "learning_rate": 4.0819612351956485e-05,
      "loss": 0.16574090719223022,
      "step": 1670
    },
    {
      "epoch": 0.30476710334788937,
      "grad_norm": 0.15016348659992218,
      "learning_rate": 4.0762547073429615e-05,
      "loss": 0.1689780354499817,
      "step": 1675
    },
    {
      "epoch": 0.3056768558951965,
      "grad_norm": 0.15182986855506897,
      "learning_rate": 4.070534514888194e-05,
      "loss": 0.1593686819076538,
      "step": 1680
    },
    {
      "epoch": 0.3065866084425036,
      "grad_norm": 0.15648750960826874,
      "learning_rate": 4.0648007074198765e-05,
      "loss": 0.16436235904693602,
      "step": 1685
    },
    {
      "epoch": 0.30749636098981076,
      "grad_norm": 0.18339484930038452,
      "learning_rate": 4.0590533346445665e-05,
      "loss": 0.1678077220916748,
      "step": 1690
    },
    {
      "epoch": 0.3084061135371179,
      "grad_norm": 0.16426527500152588,
      "learning_rate": 4.053292446386422e-05,
      "loss": 0.1689227342605591,
      "step": 1695
    },
    {
      "epoch": 0.309315866084425,
      "grad_norm": 0.16129335761070251,
      "learning_rate": 4.047518092586766e-05,
      "loss": 0.16592445373535156,
      "step": 1700
    },
    {
      "epoch": 0.31022561863173215,
      "grad_norm": 0.15512363612651825,
      "learning_rate": 4.041730323303654e-05,
      "loss": 0.16142364740371704,
      "step": 1705
    },
    {
      "epoch": 0.3111353711790393,
      "grad_norm": 0.159842386841774,
      "learning_rate": 4.0359291887114425e-05,
      "loss": 0.1702875852584839,
      "step": 1710
    },
    {
      "epoch": 0.3120451237263464,
      "grad_norm": 0.19558854401111603,
      "learning_rate": 4.030114739100352e-05,
      "loss": 0.15966148376464845,
      "step": 1715
    },
    {
      "epoch": 0.3129548762736536,
      "grad_norm": 0.1577496975660324,
      "learning_rate": 4.024287024876029e-05,
      "loss": 0.1620358943939209,
      "step": 1720
    },
    {
      "epoch": 0.3138646288209607,
      "grad_norm": 0.1629355251789093,
      "learning_rate": 4.0184460965591144e-05,
      "loss": 0.16511552333831786,
      "step": 1725
    },
    {
      "epoch": 0.31477438136826785,
      "grad_norm": 0.17060767114162445,
      "learning_rate": 4.0125920047848e-05,
      "loss": 0.15672838687896729,
      "step": 1730
    },
    {
      "epoch": 0.315684133915575,
      "grad_norm": 0.22447620332241058,
      "learning_rate": 4.006724800302394e-05,
      "loss": 0.15339784622192382,
      "step": 1735
    },
    {
      "epoch": 0.3165938864628821,
      "grad_norm": 0.14572037756443024,
      "learning_rate": 4.000844533974878e-05,
      "loss": 0.16566959619522095,
      "step": 1740
    },
    {
      "epoch": 0.31750363901018924,
      "grad_norm": 0.15915483236312866,
      "learning_rate": 3.9949512567784684e-05,
      "loss": 0.16153957843780517,
      "step": 1745
    },
    {
      "epoch": 0.3184133915574964,
      "grad_norm": 0.1668540984392166,
      "learning_rate": 3.9890450198021704e-05,
      "loss": 0.1659809947013855,
      "step": 1750
    },
    {
      "epoch": 0.3193231441048035,
      "grad_norm": 0.16612035036087036,
      "learning_rate": 3.983125874247341e-05,
      "loss": 0.16941241025924683,
      "step": 1755
    },
    {
      "epoch": 0.32023289665211063,
      "grad_norm": 0.15163679420948029,
      "learning_rate": 3.9771938714272407e-05,
      "loss": 0.16053590774536133,
      "step": 1760
    },
    {
      "epoch": 0.32114264919941776,
      "grad_norm": 0.1797824203968048,
      "learning_rate": 3.97124906276659e-05,
      "loss": 0.1667110800743103,
      "step": 1765
    },
    {
      "epoch": 0.3220524017467249,
      "grad_norm": 0.15076608955860138,
      "learning_rate": 3.9652914998011237e-05,
      "loss": 0.1607860803604126,
      "step": 1770
    },
    {
      "epoch": 0.322962154294032,
      "grad_norm": 0.16523587703704834,
      "learning_rate": 3.959321234177144e-05,
      "loss": 0.16515827178955078,
      "step": 1775
    },
    {
      "epoch": 0.32387190684133915,
      "grad_norm": 0.22065149247646332,
      "learning_rate": 3.9533383176510746e-05,
      "loss": 0.1618957757949829,
      "step": 1780
    },
    {
      "epoch": 0.3247816593886463,
      "grad_norm": 0.16426463425159454,
      "learning_rate": 3.9473428020890066e-05,
      "loss": 0.15763382911682128,
      "step": 1785
    },
    {
      "epoch": 0.3256914119359534,
      "grad_norm": 0.16474904119968414,
      "learning_rate": 3.941334739466257e-05,
      "loss": 0.15135571956634522,
      "step": 1790
    },
    {
      "epoch": 0.32660116448326054,
      "grad_norm": 0.16746412217617035,
      "learning_rate": 3.935314181866909e-05,
      "loss": 0.15925389528274536,
      "step": 1795
    },
    {
      "epoch": 0.32751091703056767,
      "grad_norm": 0.17819371819496155,
      "learning_rate": 3.929281181483369e-05,
      "loss": 0.1598669171333313,
      "step": 1800
    },
    {
      "epoch": 0.3284206695778748,
      "grad_norm": 0.1816040277481079,
      "learning_rate": 3.923235790615907e-05,
      "loss": 0.1652522087097168,
      "step": 1805
    },
    {
      "epoch": 0.32933042212518193,
      "grad_norm": 0.14846695959568024,
      "learning_rate": 3.917178061672211e-05,
      "loss": 0.16665585041046144,
      "step": 1810
    },
    {
      "epoch": 0.33024017467248906,
      "grad_norm": 0.1734926551580429,
      "learning_rate": 3.911108047166924e-05,
      "loss": 0.16069791316986085,
      "step": 1815
    },
    {
      "epoch": 0.3311499272197962,
      "grad_norm": 0.16154922544956207,
      "learning_rate": 3.905025799721194e-05,
      "loss": 0.16114097833633423,
      "step": 1820
    },
    {
      "epoch": 0.3320596797671033,
      "grad_norm": 0.1538771390914917,
      "learning_rate": 3.898931372062217e-05,
      "loss": 0.1602831244468689,
      "step": 1825
    },
    {
      "epoch": 0.3329694323144105,
      "grad_norm": 0.14036566019058228,
      "learning_rate": 3.892824817022781e-05,
      "loss": 0.1502395749092102,
      "step": 1830
    },
    {
      "epoch": 0.33387918486171764,
      "grad_norm": 0.19212059676647186,
      "learning_rate": 3.886706187540804e-05,
      "loss": 0.16265250444412233,
      "step": 1835
    },
    {
      "epoch": 0.33478893740902477,
      "grad_norm": 0.17410333454608917,
      "learning_rate": 3.880575536658881e-05,
      "loss": 0.15689224004745483,
      "step": 1840
    },
    {
      "epoch": 0.3356986899563319,
      "grad_norm": 0.15165294706821442,
      "learning_rate": 3.874432917523817e-05,
      "loss": 0.15033140182495117,
      "step": 1845
    },
    {
      "epoch": 0.336608442503639,
      "grad_norm": 0.16166730225086212,
      "learning_rate": 3.8682783833861736e-05,
      "loss": 0.16896235942840576,
      "step": 1850
    },
    {
      "epoch": 0.33751819505094616,
      "grad_norm": 0.16497021913528442,
      "learning_rate": 3.8621119875998026e-05,
      "loss": 0.1600774645805359,
      "step": 1855
    },
    {
      "epoch": 0.3384279475982533,
      "grad_norm": 0.17264948785305023,
      "learning_rate": 3.855933783621384e-05,
      "loss": 0.16947593688964843,
      "step": 1860
    },
    {
      "epoch": 0.3393377001455604,
      "grad_norm": 0.16870704293251038,
      "learning_rate": 3.8497438250099636e-05,
      "loss": 0.16062095165252685,
      "step": 1865
    },
    {
      "epoch": 0.34024745269286755,
      "grad_norm": 0.16644036769866943,
      "learning_rate": 3.843542165426492e-05,
      "loss": 0.16015599966049193,
      "step": 1870
    },
    {
      "epoch": 0.3411572052401747,
      "grad_norm": 0.1626352220773697,
      "learning_rate": 3.837328858633349e-05,
      "loss": 0.17444703578948975,
      "step": 1875
    },
    {
      "epoch": 0.3420669577874818,
      "grad_norm": 0.1427375227212906,
      "learning_rate": 3.83110395849389e-05,
      "loss": 0.1589805006980896,
      "step": 1880
    },
    {
      "epoch": 0.34297671033478894,
      "grad_norm": 0.17840255796909332,
      "learning_rate": 3.824867518971973e-05,
      "loss": 0.15953952074050903,
      "step": 1885
    },
    {
      "epoch": 0.34388646288209607,
      "grad_norm": 0.16998249292373657,
      "learning_rate": 3.818619594131489e-05,
      "loss": 0.16027032136917113,
      "step": 1890
    },
    {
      "epoch": 0.3447962154294032,
      "grad_norm": 0.14950257539749146,
      "learning_rate": 3.812360238135897e-05,
      "loss": 0.15335670709609986,
      "step": 1895
    },
    {
      "epoch": 0.3457059679767103,
      "grad_norm": 0.1678011417388916,
      "learning_rate": 3.806089505247752e-05,
      "loss": 0.1560648798942566,
      "step": 1900
    },
    {
      "epoch": 0.34661572052401746,
      "grad_norm": 0.17944541573524475,
      "learning_rate": 3.799807449828238e-05,
      "loss": 0.16072254180908202,
      "step": 1905
    },
    {
      "epoch": 0.3475254730713246,
      "grad_norm": 0.166817307472229,
      "learning_rate": 3.793514126336691e-05,
      "loss": 0.1542820692062378,
      "step": 1910
    },
    {
      "epoch": 0.3484352256186317,
      "grad_norm": 0.16047626733779907,
      "learning_rate": 3.787209589330134e-05,
      "loss": 0.16092092990875245,
      "step": 1915
    },
    {
      "epoch": 0.34934497816593885,
      "grad_norm": 0.16478900611400604,
      "learning_rate": 3.7808938934627965e-05,
      "loss": 0.16765867471694945,
      "step": 1920
    },
    {
      "epoch": 0.350254730713246,
      "grad_norm": 0.15349514782428741,
      "learning_rate": 3.774567093485648e-05,
      "loss": 0.15890377759933472,
      "step": 1925
    },
    {
      "epoch": 0.3511644832605531,
      "grad_norm": 0.1515921950340271,
      "learning_rate": 3.768229244245917e-05,
      "loss": 0.16668319702148438,
      "step": 1930
    },
    {
      "epoch": 0.35207423580786024,
      "grad_norm": 0.16310466825962067,
      "learning_rate": 3.7618804006866195e-05,
      "loss": 0.15182652473449706,
      "step": 1935
    },
    {
      "epoch": 0.3529839883551674,
      "grad_norm": 0.17294517159461975,
      "learning_rate": 3.755520617846084e-05,
      "loss": 0.16287628412246705,
      "step": 1940
    },
    {
      "epoch": 0.35389374090247455,
      "grad_norm": 0.1482895463705063,
      "learning_rate": 3.749149950857467e-05,
      "loss": 0.15321952104568481,
      "step": 1945
    },
    {
      "epoch": 0.3548034934497817,
      "grad_norm": 0.2236029952764511,
      "learning_rate": 3.7427684549482847e-05,
      "loss": 0.15403482913970948,
      "step": 1950
    },
    {
      "epoch": 0.3557132459970888,
      "grad_norm": 0.20185327529907227,
      "learning_rate": 3.736376185439927e-05,
      "loss": 0.1633884072303772,
      "step": 1955
    },
    {
      "epoch": 0.35662299854439594,
      "grad_norm": 0.13906247913837433,
      "learning_rate": 3.7299731977471816e-05,
      "loss": 0.15925350189208984,
      "step": 1960
    },
    {
      "epoch": 0.35753275109170307,
      "grad_norm": 0.18665002286434174,
      "learning_rate": 3.723559547377751e-05,
      "loss": 0.1612026572227478,
      "step": 1965
    },
    {
      "epoch": 0.3584425036390102,
      "grad_norm": 0.16913433372974396,
      "learning_rate": 3.717135289931774e-05,
      "loss": 0.15479494333267213,
      "step": 1970
    },
    {
      "epoch": 0.35935225618631733,
      "grad_norm": 0.1620066910982132,
      "learning_rate": 3.7107004811013434e-05,
      "loss": 0.1604058027267456,
      "step": 1975
    },
    {
      "epoch": 0.36026200873362446,
      "grad_norm": 0.16838301718235016,
      "learning_rate": 3.704255176670021e-05,
      "loss": 0.15335073471069335,
      "step": 1980
    },
    {
      "epoch": 0.3611717612809316,
      "grad_norm": 0.3054695427417755,
      "learning_rate": 3.6977994325123535e-05,
      "loss": 0.16558053493499755,
      "step": 1985
    },
    {
      "epoch": 0.3620815138282387,
      "grad_norm": 0.1526716649532318,
      "learning_rate": 3.6913333045933934e-05,
      "loss": 0.16148923635482787,
      "step": 1990
    },
    {
      "epoch": 0.36299126637554585,
      "grad_norm": 0.15328513085842133,
      "learning_rate": 3.684856848968209e-05,
      "loss": 0.1553613781929016,
      "step": 1995
    },
    {
      "epoch": 0.363901018922853,
      "grad_norm": 0.16129714250564575,
      "learning_rate": 3.6783701217813995e-05,
      "loss": 0.16724612712860107,
      "step": 2000
    },
    {
      "epoch": 0.3648107714701601,
      "grad_norm": 0.15715539455413818,
      "learning_rate": 3.6718731792666086e-05,
      "loss": 0.15867922306060792,
      "step": 2005
    },
    {
      "epoch": 0.36572052401746724,
      "grad_norm": 0.15569166839122772,
      "learning_rate": 3.6653660777460366e-05,
      "loss": 0.1552058696746826,
      "step": 2010
    },
    {
      "epoch": 0.36663027656477437,
      "grad_norm": 0.16223010420799255,
      "learning_rate": 3.6588488736299535e-05,
      "loss": 0.1583200454711914,
      "step": 2015
    },
    {
      "epoch": 0.3675400291120815,
      "grad_norm": 0.18441995978355408,
      "learning_rate": 3.652321623416209e-05,
      "loss": 0.15050662755966188,
      "step": 2020
    },
    {
      "epoch": 0.36844978165938863,
      "grad_norm": 0.13792674243450165,
      "learning_rate": 3.645784383689742e-05,
      "loss": 0.15458759069442748,
      "step": 2025
    },
    {
      "epoch": 0.36935953420669576,
      "grad_norm": 0.14993111789226532,
      "learning_rate": 3.639237211122091e-05,
      "loss": 0.15926222801208495,
      "step": 2030
    },
    {
      "epoch": 0.3702692867540029,
      "grad_norm": 0.16815930604934692,
      "learning_rate": 3.632680162470904e-05,
      "loss": 0.15524441003799438,
      "step": 2035
    },
    {
      "epoch": 0.37117903930131,
      "grad_norm": 0.13312821090221405,
      "learning_rate": 3.626113294579441e-05,
      "loss": 0.15883516073226928,
      "step": 2040
    },
    {
      "epoch": 0.37208879184861715,
      "grad_norm": 0.16838273406028748,
      "learning_rate": 3.619536664376091e-05,
      "loss": 0.15829603672027587,
      "step": 2045
    },
    {
      "epoch": 0.37299854439592434,
      "grad_norm": 0.14706873893737793,
      "learning_rate": 3.612950328873869e-05,
      "loss": 0.15644397735595703,
      "step": 2050
    },
    {
      "epoch": 0.37390829694323147,
      "grad_norm": 0.1644199639558792,
      "learning_rate": 3.606354345169926e-05,
      "loss": 0.15858219861984252,
      "step": 2055
    },
    {
      "epoch": 0.3748180494905386,
      "grad_norm": 0.18077051639556885,
      "learning_rate": 3.599748770445055e-05,
      "loss": 0.1641286849975586,
      "step": 2060
    },
    {
      "epoch": 0.3757278020378457,
      "grad_norm": 0.16329127550125122,
      "learning_rate": 3.5931336619631914e-05,
      "loss": 0.15027186870574952,
      "step": 2065
    },
    {
      "epoch": 0.37663755458515286,
      "grad_norm": 0.16346783936023712,
      "learning_rate": 3.586509077070922e-05,
      "loss": 0.1558641314506531,
      "step": 2070
    },
    {
      "epoch": 0.37754730713246,
      "grad_norm": 0.1727602630853653,
      "learning_rate": 3.5798750731969834e-05,
      "loss": 0.15390506982803345,
      "step": 2075
    },
    {
      "epoch": 0.3784570596797671,
      "grad_norm": 0.7598192691802979,
      "learning_rate": 3.5732317078517654e-05,
      "loss": 0.1533232808113098,
      "step": 2080
    },
    {
      "epoch": 0.37936681222707425,
      "grad_norm": 0.1433355212211609,
      "learning_rate": 3.5665790386268124e-05,
      "loss": 0.15560413599014283,
      "step": 2085
    },
    {
      "epoch": 0.3802765647743814,
      "grad_norm": 0.18439625203609467,
      "learning_rate": 3.559917123194325e-05,
      "loss": 0.16695556640625,
      "step": 2090
    },
    {
      "epoch": 0.3811863173216885,
      "grad_norm": 0.1693502813577652,
      "learning_rate": 3.55324601930666e-05,
      "loss": 0.15957870483398437,
      "step": 2095
    },
    {
      "epoch": 0.38209606986899564,
      "grad_norm": 0.17776088416576385,
      "learning_rate": 3.54656578479583e-05,
      "loss": 0.1527492880821228,
      "step": 2100
    },
    {
      "epoch": 0.38300582241630277,
      "grad_norm": 0.15993724763393402,
      "learning_rate": 3.539876477572998e-05,
      "loss": 0.1567505717277527,
      "step": 2105
    },
    {
      "epoch": 0.3839155749636099,
      "grad_norm": 0.17067375779151917,
      "learning_rate": 3.533178155627981e-05,
      "loss": 0.14660797119140626,
      "step": 2110
    },
    {
      "epoch": 0.384825327510917,
      "grad_norm": 0.20239882171154022,
      "learning_rate": 3.526470877028745e-05,
      "loss": 0.1596767544746399,
      "step": 2115
    },
    {
      "epoch": 0.38573508005822416,
      "grad_norm": 0.1863643079996109,
      "learning_rate": 3.5197546999209005e-05,
      "loss": 0.15738571882247926,
      "step": 2120
    },
    {
      "epoch": 0.3866448326055313,
      "grad_norm": 0.16994133591651917,
      "learning_rate": 3.5130296825272014e-05,
      "loss": 0.16255316734313965,
      "step": 2125
    },
    {
      "epoch": 0.3875545851528384,
      "grad_norm": 0.18703415989875793,
      "learning_rate": 3.5062958831470355e-05,
      "loss": 0.15206334590911866,
      "step": 2130
    },
    {
      "epoch": 0.38846433770014555,
      "grad_norm": 0.15433982014656067,
      "learning_rate": 3.4995533601559226e-05,
      "loss": 0.1590178370475769,
      "step": 2135
    },
    {
      "epoch": 0.3893740902474527,
      "grad_norm": 0.16498146951198578,
      "learning_rate": 3.4928021720050104e-05,
      "loss": 0.14759145975112914,
      "step": 2140
    },
    {
      "epoch": 0.3902838427947598,
      "grad_norm": 0.17880478501319885,
      "learning_rate": 3.486042377220562e-05,
      "loss": 0.1642458915710449,
      "step": 2145
    },
    {
      "epoch": 0.39119359534206694,
      "grad_norm": 0.14700061082839966,
      "learning_rate": 3.479274034403455e-05,
      "loss": 0.16105138063430785,
      "step": 2150
    },
    {
      "epoch": 0.39210334788937407,
      "grad_norm": 0.1620762050151825,
      "learning_rate": 3.472497202228664e-05,
      "loss": 0.15104985237121582,
      "step": 2155
    },
    {
      "epoch": 0.3930131004366812,
      "grad_norm": 0.1625058799982071,
      "learning_rate": 3.4657119394447654e-05,
      "loss": 0.16145485639572144,
      "step": 2160
    },
    {
      "epoch": 0.3939228529839884,
      "grad_norm": 0.1631549596786499,
      "learning_rate": 3.458918304873417e-05,
      "loss": 0.16712255477905275,
      "step": 2165
    },
    {
      "epoch": 0.3948326055312955,
      "grad_norm": 0.16041551530361176,
      "learning_rate": 3.452116357408853e-05,
      "loss": 0.15118330717086792,
      "step": 2170
    },
    {
      "epoch": 0.39574235807860264,
      "grad_norm": 0.16692611575126648,
      "learning_rate": 3.44530615601737e-05,
      "loss": 0.16982550621032716,
      "step": 2175
    },
    {
      "epoch": 0.39665211062590977,
      "grad_norm": 0.16082268953323364,
      "learning_rate": 3.438487759736821e-05,
      "loss": 0.1513260006904602,
      "step": 2180
    },
    {
      "epoch": 0.3975618631732169,
      "grad_norm": 0.1474589854478836,
      "learning_rate": 3.4316612276761004e-05,
      "loss": 0.14968743324279785,
      "step": 2185
    },
    {
      "epoch": 0.39847161572052403,
      "grad_norm": 0.14531342685222626,
      "learning_rate": 3.42482661901463e-05,
      "loss": 0.1563260555267334,
      "step": 2190
    },
    {
      "epoch": 0.39938136826783116,
      "grad_norm": 0.16775506734848022,
      "learning_rate": 3.41798399300185e-05,
      "loss": 0.14861010313034057,
      "step": 2195
    },
    {
      "epoch": 0.4002911208151383,
      "grad_norm": 0.15065217018127441,
      "learning_rate": 3.411133408956703e-05,
      "loss": 0.15559519529342652,
      "step": 2200
    },
    {
      "epoch": 0.4012008733624454,
      "grad_norm": 0.16655296087265015,
      "learning_rate": 3.4042749262671184e-05,
      "loss": 0.16025567054748535,
      "step": 2205
    },
    {
      "epoch": 0.40211062590975255,
      "grad_norm": 0.14773905277252197,
      "learning_rate": 3.397408604389501e-05,
      "loss": 0.15074082612991332,
      "step": 2210
    },
    {
      "epoch": 0.4030203784570597,
      "grad_norm": 0.16233304142951965,
      "learning_rate": 3.3905345028482125e-05,
      "loss": 0.15490520000457764,
      "step": 2215
    },
    {
      "epoch": 0.4039301310043668,
      "grad_norm": 0.17520153522491455,
      "learning_rate": 3.383652681235058e-05,
      "loss": 0.1517520785331726,
      "step": 2220
    },
    {
      "epoch": 0.40483988355167394,
      "grad_norm": 0.14749875664710999,
      "learning_rate": 3.376763199208766e-05,
      "loss": 0.15410997867584228,
      "step": 2225
    },
    {
      "epoch": 0.40574963609898107,
      "grad_norm": 0.16855919361114502,
      "learning_rate": 3.369866116494477e-05,
      "loss": 0.1510261058807373,
      "step": 2230
    },
    {
      "epoch": 0.4066593886462882,
      "grad_norm": 0.1594122350215912,
      "learning_rate": 3.362961492883218e-05,
      "loss": 0.1493813395500183,
      "step": 2235
    },
    {
      "epoch": 0.40756914119359533,
      "grad_norm": 0.13645926117897034,
      "learning_rate": 3.3560493882313915e-05,
      "loss": 0.14876762628555298,
      "step": 2240
    },
    {
      "epoch": 0.40847889374090246,
      "grad_norm": 0.14304400980472565,
      "learning_rate": 3.349129862460251e-05,
      "loss": 0.15567013025283813,
      "step": 2245
    },
    {
      "epoch": 0.4093886462882096,
      "grad_norm": 0.17040041089057922,
      "learning_rate": 3.342202975555386e-05,
      "loss": 0.1563249945640564,
      "step": 2250
    },
    {
      "epoch": 0.4102983988355167,
      "grad_norm": 0.15594671666622162,
      "learning_rate": 3.3352687875661984e-05,
      "loss": 0.1546410083770752,
      "step": 2255
    },
    {
      "epoch": 0.41120815138282385,
      "grad_norm": 0.1677195280790329,
      "learning_rate": 3.328327358605384e-05,
      "loss": 0.15710171461105346,
      "step": 2260
    },
    {
      "epoch": 0.412117903930131,
      "grad_norm": 0.1731705516576767,
      "learning_rate": 3.321378748848412e-05,
      "loss": 0.16444036960601807,
      "step": 2265
    },
    {
      "epoch": 0.4130276564774381,
      "grad_norm": 0.18779033422470093,
      "learning_rate": 3.3144230185329984e-05,
      "loss": 0.15659687519073487,
      "step": 2270
    },
    {
      "epoch": 0.4139374090247453,
      "grad_norm": 0.1543768346309662,
      "learning_rate": 3.3074602279585913e-05,
      "loss": 0.15100739002227784,
      "step": 2275
    },
    {
      "epoch": 0.4148471615720524,
      "grad_norm": 0.16672168672084808,
      "learning_rate": 3.300490437485843e-05,
      "loss": 0.15535364151000977,
      "step": 2280
    },
    {
      "epoch": 0.41575691411935956,
      "grad_norm": 0.16741308569908142,
      "learning_rate": 3.293513707536089e-05,
      "loss": 0.15523911714553834,
      "step": 2285
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 0.1488303542137146,
      "learning_rate": 3.286530098590822e-05,
      "loss": 0.1542000651359558,
      "step": 2290
    },
    {
      "epoch": 0.4175764192139738,
      "grad_norm": 0.1637732982635498,
      "learning_rate": 3.2795396711911694e-05,
      "loss": 0.15354831218719484,
      "step": 2295
    },
    {
      "epoch": 0.41848617176128095,
      "grad_norm": 0.1472022533416748,
      "learning_rate": 3.272542485937369e-05,
      "loss": 0.16235145330429077,
      "step": 2300
    },
    {
      "epoch": 0.4193959243085881,
      "grad_norm": 0.15908290445804596,
      "learning_rate": 3.265538603488241e-05,
      "loss": 0.15642645359039306,
      "step": 2305
    },
    {
      "epoch": 0.4203056768558952,
      "grad_norm": 0.1584865301847458,
      "learning_rate": 3.2585280845606645e-05,
      "loss": 0.15490249395370484,
      "step": 2310
    },
    {
      "epoch": 0.42121542940320233,
      "grad_norm": 0.15893949568271637,
      "learning_rate": 3.251510989929052e-05,
      "loss": 0.1598116159439087,
      "step": 2315
    },
    {
      "epoch": 0.42212518195050946,
      "grad_norm": 0.18930596113204956,
      "learning_rate": 3.244487380424817e-05,
      "loss": 0.1482008934020996,
      "step": 2320
    },
    {
      "epoch": 0.4230349344978166,
      "grad_norm": 0.132876455783844,
      "learning_rate": 3.237457316935856e-05,
      "loss": 0.15304710865020751,
      "step": 2325
    },
    {
      "epoch": 0.4239446870451237,
      "grad_norm": 0.16447032988071442,
      "learning_rate": 3.2304208604060106e-05,
      "loss": 0.15298750400543212,
      "step": 2330
    },
    {
      "epoch": 0.42485443959243085,
      "grad_norm": 0.17748120427131653,
      "learning_rate": 3.223378071834546e-05,
      "loss": 0.1556084156036377,
      "step": 2335
    },
    {
      "epoch": 0.425764192139738,
      "grad_norm": 0.16366586089134216,
      "learning_rate": 3.2163290122756206e-05,
      "loss": 0.14387927055358887,
      "step": 2340
    },
    {
      "epoch": 0.4266739446870451,
      "grad_norm": 0.15398970246315002,
      "learning_rate": 3.209273742837755e-05,
      "loss": 0.16091293096542358,
      "step": 2345
    },
    {
      "epoch": 0.42758369723435224,
      "grad_norm": 0.164212167263031,
      "learning_rate": 3.202212324683305e-05,
      "loss": 0.15523531436920165,
      "step": 2350
    },
    {
      "epoch": 0.4284934497816594,
      "grad_norm": 0.16749800741672516,
      "learning_rate": 3.1951448190279255e-05,
      "loss": 0.15354975461959838,
      "step": 2355
    },
    {
      "epoch": 0.4294032023289665,
      "grad_norm": 0.14137034118175507,
      "learning_rate": 3.18807128714005e-05,
      "loss": 0.14981694221496583,
      "step": 2360
    },
    {
      "epoch": 0.43031295487627363,
      "grad_norm": 0.14848439395427704,
      "learning_rate": 3.1809917903403507e-05,
      "loss": 0.15448769330978393,
      "step": 2365
    },
    {
      "epoch": 0.43122270742358076,
      "grad_norm": 0.1747605800628662,
      "learning_rate": 3.1739063900012095e-05,
      "loss": 0.15882387161254882,
      "step": 2370
    },
    {
      "epoch": 0.4321324599708879,
      "grad_norm": 0.16054467856884003,
      "learning_rate": 3.166815147546186e-05,
      "loss": 0.15170297622680665,
      "step": 2375
    },
    {
      "epoch": 0.433042212518195,
      "grad_norm": 0.15428027510643005,
      "learning_rate": 3.1597181244494886e-05,
      "loss": 0.16202548742294312,
      "step": 2380
    },
    {
      "epoch": 0.4339519650655022,
      "grad_norm": 0.16747219860553741,
      "learning_rate": 3.1526153822354325e-05,
      "loss": 0.15461477041244506,
      "step": 2385
    },
    {
      "epoch": 0.43486171761280934,
      "grad_norm": 0.17415772378444672,
      "learning_rate": 3.145506982477918e-05,
      "loss": 0.16173542737960817,
      "step": 2390
    },
    {
      "epoch": 0.43577147016011647,
      "grad_norm": 0.1293518990278244,
      "learning_rate": 3.1383929867998865e-05,
      "loss": 0.15572521686553956,
      "step": 2395
    },
    {
      "epoch": 0.4366812227074236,
      "grad_norm": 0.16909323632717133,
      "learning_rate": 3.1312734568727935e-05,
      "loss": 0.15898628234863282,
      "step": 2400
    },
    {
      "epoch": 0.43759097525473073,
      "grad_norm": 0.16770294308662415,
      "learning_rate": 3.124148454416069e-05,
      "loss": 0.1536281704902649,
      "step": 2405
    },
    {
      "epoch": 0.43850072780203786,
      "grad_norm": 0.14078612625598907,
      "learning_rate": 3.117018041196585e-05,
      "loss": 0.15274266004562378,
      "step": 2410
    },
    {
      "epoch": 0.439410480349345,
      "grad_norm": 0.15457536280155182,
      "learning_rate": 3.1098822790281226e-05,
      "loss": 0.15391263961791993,
      "step": 2415
    },
    {
      "epoch": 0.4403202328966521,
      "grad_norm": 0.1640717089176178,
      "learning_rate": 3.102741229770827e-05,
      "loss": 0.15515168905258178,
      "step": 2420
    },
    {
      "epoch": 0.44122998544395925,
      "grad_norm": 0.2601533830165863,
      "learning_rate": 3.095594955330683e-05,
      "loss": 0.1587247371673584,
      "step": 2425
    },
    {
      "epoch": 0.4421397379912664,
      "grad_norm": 0.1352529525756836,
      "learning_rate": 3.08844351765897e-05,
      "loss": 0.1483217477798462,
      "step": 2430
    },
    {
      "epoch": 0.4430494905385735,
      "grad_norm": 0.18479721248149872,
      "learning_rate": 3.081286978751728e-05,
      "loss": 0.15121787786483765,
      "step": 2435
    },
    {
      "epoch": 0.44395924308588064,
      "grad_norm": 0.16954511404037476,
      "learning_rate": 3.074125400649221e-05,
      "loss": 0.16073100566864013,
      "step": 2440
    },
    {
      "epoch": 0.44486899563318777,
      "grad_norm": 0.15154729783535004,
      "learning_rate": 3.0669588454353944e-05,
      "loss": 0.15738017559051515,
      "step": 2445
    },
    {
      "epoch": 0.4457787481804949,
      "grad_norm": 0.1540488302707672,
      "learning_rate": 3.059787375237344e-05,
      "loss": 0.1515384554862976,
      "step": 2450
    },
    {
      "epoch": 0.44668850072780203,
      "grad_norm": 0.1814432442188263,
      "learning_rate": 3.052611052224774e-05,
      "loss": 0.15731438398361205,
      "step": 2455
    },
    {
      "epoch": 0.44759825327510916,
      "grad_norm": 0.16657036542892456,
      "learning_rate": 3.0454299386094542e-05,
      "loss": 0.15741543769836425,
      "step": 2460
    },
    {
      "epoch": 0.4485080058224163,
      "grad_norm": 0.2177237570285797,
      "learning_rate": 3.0382440966446875e-05,
      "loss": 0.14972515106201173,
      "step": 2465
    },
    {
      "epoch": 0.4494177583697234,
      "grad_norm": 0.1669909954071045,
      "learning_rate": 3.031053588624766e-05,
      "loss": 0.1506432294845581,
      "step": 2470
    },
    {
      "epoch": 0.45032751091703055,
      "grad_norm": 0.1752234250307083,
      "learning_rate": 3.0238584768844313e-05,
      "loss": 0.14969609975814818,
      "step": 2475
    },
    {
      "epoch": 0.4512372634643377,
      "grad_norm": 0.18267901241779327,
      "learning_rate": 3.0166588237983363e-05,
      "loss": 0.15112748146057128,
      "step": 2480
    },
    {
      "epoch": 0.4521470160116448,
      "grad_norm": 0.16250105202198029,
      "learning_rate": 3.0094546917805007e-05,
      "loss": 0.15864100456237792,
      "step": 2485
    },
    {
      "epoch": 0.45305676855895194,
      "grad_norm": 0.14825721085071564,
      "learning_rate": 3.0022461432837752e-05,
      "loss": 0.1513954520225525,
      "step": 2490
    },
    {
      "epoch": 0.4539665211062591,
      "grad_norm": 0.1626640111207962,
      "learning_rate": 2.9950332407992943e-05,
      "loss": 0.1505578875541687,
      "step": 2495
    },
    {
      "epoch": 0.45487627365356625,
      "grad_norm": 0.1535351574420929,
      "learning_rate": 2.987816046855939e-05,
      "loss": 0.15255829095840454,
      "step": 2500
    },
    {
      "epoch": 0.4557860262008734,
      "grad_norm": 0.17552775144577026,
      "learning_rate": 2.9805946240197928e-05,
      "loss": 0.1516443133354187,
      "step": 2505
    },
    {
      "epoch": 0.4566957787481805,
      "grad_norm": 0.16020981967449188,
      "learning_rate": 2.9733690348935994e-05,
      "loss": 0.14519743919372557,
      "step": 2510
    },
    {
      "epoch": 0.45760553129548764,
      "grad_norm": 0.17800211906433105,
      "learning_rate": 2.9661393421162204e-05,
      "loss": 0.15679080486297609,
      "step": 2515
    },
    {
      "epoch": 0.4585152838427948,
      "grad_norm": 0.16016991436481476,
      "learning_rate": 2.9589056083620902e-05,
      "loss": 0.14768127202987671,
      "step": 2520
    },
    {
      "epoch": 0.4594250363901019,
      "grad_norm": 0.16272081434726715,
      "learning_rate": 2.951667896340679e-05,
      "loss": 0.1513301968574524,
      "step": 2525
    },
    {
      "epoch": 0.46033478893740903,
      "grad_norm": 0.1726413071155548,
      "learning_rate": 2.9444262687959402e-05,
      "loss": 0.14819332361221313,
      "step": 2530
    },
    {
      "epoch": 0.46124454148471616,
      "grad_norm": 0.1670403778553009,
      "learning_rate": 2.9371807885057735e-05,
      "loss": 0.15245940685272216,
      "step": 2535
    },
    {
      "epoch": 0.4621542940320233,
      "grad_norm": 0.1650049239397049,
      "learning_rate": 2.9299315182814772e-05,
      "loss": 0.15187418460845947,
      "step": 2540
    },
    {
      "epoch": 0.4630640465793304,
      "grad_norm": 0.16327734291553497,
      "learning_rate": 2.9226785209672047e-05,
      "loss": 0.15579828023910522,
      "step": 2545
    },
    {
      "epoch": 0.46397379912663755,
      "grad_norm": 0.3367880582809448,
      "learning_rate": 2.91542185943942e-05,
      "loss": 0.15617697238922118,
      "step": 2550
    },
    {
      "epoch": 0.4648835516739447,
      "grad_norm": 0.1731594055891037,
      "learning_rate": 2.908161596606353e-05,
      "loss": 0.1559603691101074,
      "step": 2555
    },
    {
      "epoch": 0.4657933042212518,
      "grad_norm": 0.1477293074131012,
      "learning_rate": 2.9008977954074517e-05,
      "loss": 0.15567959547042848,
      "step": 2560
    },
    {
      "epoch": 0.46670305676855894,
      "grad_norm": 0.16227173805236816,
      "learning_rate": 2.8936305188128392e-05,
      "loss": 0.1522113561630249,
      "step": 2565
    },
    {
      "epoch": 0.4676128093158661,
      "grad_norm": 0.2031075656414032,
      "learning_rate": 2.8863598298227674e-05,
      "loss": 0.15054640769958497,
      "step": 2570
    },
    {
      "epoch": 0.4685225618631732,
      "grad_norm": 0.18351472914218903,
      "learning_rate": 2.8790857914670698e-05,
      "loss": 0.15837019681930542,
      "step": 2575
    },
    {
      "epoch": 0.46943231441048033,
      "grad_norm": 0.15914765000343323,
      "learning_rate": 2.871808466804616e-05,
      "loss": 0.1550259470939636,
      "step": 2580
    },
    {
      "epoch": 0.47034206695778746,
      "grad_norm": 0.17366717755794525,
      "learning_rate": 2.8645279189227636e-05,
      "loss": 0.15702390670776367,
      "step": 2585
    },
    {
      "epoch": 0.4712518195050946,
      "grad_norm": 0.13677838444709778,
      "learning_rate": 2.8572442109368134e-05,
      "loss": 0.15485031604766847,
      "step": 2590
    },
    {
      "epoch": 0.4721615720524017,
      "grad_norm": 0.1477748304605484,
      "learning_rate": 2.8499574059894617e-05,
      "loss": 0.14577245712280273,
      "step": 2595
    },
    {
      "epoch": 0.47307132459970885,
      "grad_norm": 0.1582217663526535,
      "learning_rate": 2.842667567250252e-05,
      "loss": 0.15586793422698975,
      "step": 2600
    },
    {
      "epoch": 0.47398107714701604,
      "grad_norm": 0.19658738374710083,
      "learning_rate": 2.8353747579150268e-05,
      "loss": 0.15060495138168334,
      "step": 2605
    },
    {
      "epoch": 0.47489082969432317,
      "grad_norm": 0.176767036318779,
      "learning_rate": 2.828079041205382e-05,
      "loss": 0.15116705894470214,
      "step": 2610
    },
    {
      "epoch": 0.4758005822416303,
      "grad_norm": 0.16972507536411285,
      "learning_rate": 2.820780480368117e-05,
      "loss": 0.1541937470436096,
      "step": 2615
    },
    {
      "epoch": 0.47671033478893743,
      "grad_norm": 0.1548585742712021,
      "learning_rate": 2.8134791386746884e-05,
      "loss": 0.14334756135940552,
      "step": 2620
    },
    {
      "epoch": 0.47762008733624456,
      "grad_norm": 0.15411986410617828,
      "learning_rate": 2.806175079420658e-05,
      "loss": 0.14642289876937867,
      "step": 2625
    },
    {
      "epoch": 0.4785298398835517,
      "grad_norm": 0.16609491407871246,
      "learning_rate": 2.7988683659251474e-05,
      "loss": 0.15083469152450563,
      "step": 2630
    },
    {
      "epoch": 0.4794395924308588,
      "grad_norm": 0.16592684388160706,
      "learning_rate": 2.791559061530289e-05,
      "loss": 0.14218480587005616,
      "step": 2635
    },
    {
      "epoch": 0.48034934497816595,
      "grad_norm": 0.1764935404062271,
      "learning_rate": 2.7842472296006722e-05,
      "loss": 0.15004343986511232,
      "step": 2640
    },
    {
      "epoch": 0.4812590975254731,
      "grad_norm": 0.20094354450702667,
      "learning_rate": 2.7769329335228022e-05,
      "loss": 0.14975016117095946,
      "step": 2645
    },
    {
      "epoch": 0.4821688500727802,
      "grad_norm": 0.1869269460439682,
      "learning_rate": 2.769616236704542e-05,
      "loss": 0.155981707572937,
      "step": 2650
    },
    {
      "epoch": 0.48307860262008734,
      "grad_norm": 0.16671574115753174,
      "learning_rate": 2.762297202574571e-05,
      "loss": 0.14633859395980836,
      "step": 2655
    },
    {
      "epoch": 0.48398835516739447,
      "grad_norm": 0.14999663829803467,
      "learning_rate": 2.754975894581826e-05,
      "loss": 0.15692603588104248,
      "step": 2660
    },
    {
      "epoch": 0.4848981077147016,
      "grad_norm": 0.16893649101257324,
      "learning_rate": 2.7476523761949592e-05,
      "loss": 0.14530394077301026,
      "step": 2665
    },
    {
      "epoch": 0.48580786026200873,
      "grad_norm": 0.16039884090423584,
      "learning_rate": 2.740326710901784e-05,
      "loss": 0.15013915300369263,
      "step": 2670
    },
    {
      "epoch": 0.48671761280931586,
      "grad_norm": 0.16672006249427795,
      "learning_rate": 2.732998962208725e-05,
      "loss": 0.15667349100112915,
      "step": 2675
    },
    {
      "epoch": 0.487627365356623,
      "grad_norm": 0.2160867303609848,
      "learning_rate": 2.7256691936402684e-05,
      "loss": 0.14335414171218872,
      "step": 2680
    },
    {
      "epoch": 0.4885371179039301,
      "grad_norm": 0.349030077457428,
      "learning_rate": 2.71833746873841e-05,
      "loss": 0.1437530279159546,
      "step": 2685
    },
    {
      "epoch": 0.48944687045123725,
      "grad_norm": 0.18380966782569885,
      "learning_rate": 2.7110038510621073e-05,
      "loss": 0.1476014256477356,
      "step": 2690
    },
    {
      "epoch": 0.4903566229985444,
      "grad_norm": 0.1523742377758026,
      "learning_rate": 2.703668404186722e-05,
      "loss": 0.14578526020050048,
      "step": 2695
    },
    {
      "epoch": 0.4912663755458515,
      "grad_norm": 0.16092729568481445,
      "learning_rate": 2.696331191703479e-05,
      "loss": 0.15335593223571778,
      "step": 2700
    },
    {
      "epoch": 0.49217612809315864,
      "grad_norm": 0.17185333371162415,
      "learning_rate": 2.688992277218904e-05,
      "loss": 0.1540898084640503,
      "step": 2705
    },
    {
      "epoch": 0.49308588064046577,
      "grad_norm": 0.1521969735622406,
      "learning_rate": 2.6816517243542792e-05,
      "loss": 0.15171396732330322,
      "step": 2710
    },
    {
      "epoch": 0.49399563318777295,
      "grad_norm": 0.16064171493053436,
      "learning_rate": 2.674309596745092e-05,
      "loss": 0.1505839228630066,
      "step": 2715
    },
    {
      "epoch": 0.4949053857350801,
      "grad_norm": 0.16430898010730743,
      "learning_rate": 2.6669659580404795e-05,
      "loss": 0.1551363468170166,
      "step": 2720
    },
    {
      "epoch": 0.4958151382823872,
      "grad_norm": 0.16125477850437164,
      "learning_rate": 2.659620871902677e-05,
      "loss": 0.15069286823272704,
      "step": 2725
    },
    {
      "epoch": 0.49672489082969434,
      "grad_norm": 0.1428450047969818,
      "learning_rate": 2.652274402006471e-05,
      "loss": 0.15511081218719483,
      "step": 2730
    },
    {
      "epoch": 0.4976346433770015,
      "grad_norm": 0.15452754497528076,
      "learning_rate": 2.6449266120386406e-05,
      "loss": 0.14941939115524291,
      "step": 2735
    },
    {
      "epoch": 0.4985443959243086,
      "grad_norm": 0.17243537306785583,
      "learning_rate": 2.6375775656974123e-05,
      "loss": 0.151741623878479,
      "step": 2740
    },
    {
      "epoch": 0.49945414847161573,
      "grad_norm": 0.13736453652381897,
      "learning_rate": 2.6302273266919008e-05,
      "loss": 0.147042977809906,
      "step": 2745
    },
    {
      "epoch": 0.5003639010189228,
      "grad_norm": 0.16241495311260223,
      "learning_rate": 2.6228759587415614e-05,
      "loss": 0.14664684534072875,
      "step": 2750
    },
    {
      "epoch": 0.50127365356623,
      "grad_norm": 0.193496435880661,
      "learning_rate": 2.6155235255756356e-05,
      "loss": 0.15486966371536254,
      "step": 2755
    },
    {
      "epoch": 0.5021834061135371,
      "grad_norm": 0.1542847901582718,
      "learning_rate": 2.6081700909326e-05,
      "loss": 0.15148009061813356,
      "step": 2760
    },
    {
      "epoch": 0.5030931586608443,
      "grad_norm": 0.1696511209011078,
      "learning_rate": 2.6008157185596142e-05,
      "loss": 0.14190055131912233,
      "step": 2765
    },
    {
      "epoch": 0.5040029112081513,
      "grad_norm": 0.14690077304840088,
      "learning_rate": 2.5934604722119655e-05,
      "loss": 0.1570739269256592,
      "step": 2770
    },
    {
      "epoch": 0.5049126637554585,
      "grad_norm": 0.17149671912193298,
      "learning_rate": 2.5861044156525162e-05,
      "loss": 0.14940304756164552,
      "step": 2775
    },
    {
      "epoch": 0.5058224163027657,
      "grad_norm": 0.16639231145381927,
      "learning_rate": 2.578747612651155e-05,
      "loss": 0.15691237449645995,
      "step": 2780
    },
    {
      "epoch": 0.5067321688500728,
      "grad_norm": 0.2062763124704361,
      "learning_rate": 2.5713901269842404e-05,
      "loss": 0.1564734935760498,
      "step": 2785
    },
    {
      "epoch": 0.50764192139738,
      "grad_norm": 0.12636308372020721,
      "learning_rate": 2.5640320224340502e-05,
      "loss": 0.14539417028427123,
      "step": 2790
    },
    {
      "epoch": 0.508551673944687,
      "grad_norm": 0.16893689334392548,
      "learning_rate": 2.556673362788225e-05,
      "loss": 0.15440930128097535,
      "step": 2795
    },
    {
      "epoch": 0.5094614264919942,
      "grad_norm": 0.16250015795230865,
      "learning_rate": 2.54931421183922e-05,
      "loss": 0.14485647678375244,
      "step": 2800
    },
    {
      "epoch": 0.5103711790393013,
      "grad_norm": 0.1700994372367859,
      "learning_rate": 2.5419546333837462e-05,
      "loss": 0.15411126613616943,
      "step": 2805
    },
    {
      "epoch": 0.5112809315866085,
      "grad_norm": 0.1547706127166748,
      "learning_rate": 2.5345946912222256e-05,
      "loss": 0.15516072511672974,
      "step": 2810
    },
    {
      "epoch": 0.5121906841339156,
      "grad_norm": 0.17955681681632996,
      "learning_rate": 2.527234449158228e-05,
      "loss": 0.15546923875808716,
      "step": 2815
    },
    {
      "epoch": 0.5131004366812227,
      "grad_norm": 0.163709819316864,
      "learning_rate": 2.519873970997927e-05,
      "loss": 0.15665037631988527,
      "step": 2820
    },
    {
      "epoch": 0.5140101892285298,
      "grad_norm": 0.17859576642513275,
      "learning_rate": 2.5125133205495405e-05,
      "loss": 0.1539722204208374,
      "step": 2825
    },
    {
      "epoch": 0.514919941775837,
      "grad_norm": 0.17443150281906128,
      "learning_rate": 2.5051525616227806e-05,
      "loss": 0.148411762714386,
      "step": 2830
    },
    {
      "epoch": 0.5158296943231441,
      "grad_norm": 0.17397581040859222,
      "learning_rate": 2.4977917580283007e-05,
      "loss": 0.14880497455596925,
      "step": 2835
    },
    {
      "epoch": 0.5167394468704513,
      "grad_norm": 0.14565663039684296,
      "learning_rate": 2.4904309735771405e-05,
      "loss": 0.14934680461883545,
      "step": 2840
    },
    {
      "epoch": 0.5176491994177583,
      "grad_norm": 0.17895659804344177,
      "learning_rate": 2.4830702720801746e-05,
      "loss": 0.15287939310073853,
      "step": 2845
    },
    {
      "epoch": 0.5185589519650655,
      "grad_norm": 0.15812788903713226,
      "learning_rate": 2.4757097173475572e-05,
      "loss": 0.14576947689056396,
      "step": 2850
    },
    {
      "epoch": 0.5194687045123726,
      "grad_norm": 0.17123781144618988,
      "learning_rate": 2.46834937318817e-05,
      "loss": 0.15224847793579102,
      "step": 2855
    },
    {
      "epoch": 0.5203784570596798,
      "grad_norm": 0.14845474064350128,
      "learning_rate": 2.460989303409072e-05,
      "loss": 0.14901585578918458,
      "step": 2860
    },
    {
      "epoch": 0.5212882096069869,
      "grad_norm": 0.23493704199790955,
      "learning_rate": 2.4536295718149407e-05,
      "loss": 0.1517487049102783,
      "step": 2865
    },
    {
      "epoch": 0.522197962154294,
      "grad_norm": 0.16209843754768372,
      "learning_rate": 2.4462702422075217e-05,
      "loss": 0.14327445030212402,
      "step": 2870
    },
    {
      "epoch": 0.5231077147016011,
      "grad_norm": 0.17249803245067596,
      "learning_rate": 2.4389113783850793e-05,
      "loss": 0.1517549753189087,
      "step": 2875
    },
    {
      "epoch": 0.5240174672489083,
      "grad_norm": 0.14561402797698975,
      "learning_rate": 2.431553044141836e-05,
      "loss": 0.14764087200164794,
      "step": 2880
    },
    {
      "epoch": 0.5249272197962155,
      "grad_norm": 0.17033302783966064,
      "learning_rate": 2.4241953032674256e-05,
      "loss": 0.15181604623794556,
      "step": 2885
    },
    {
      "epoch": 0.5258369723435226,
      "grad_norm": 0.1184430941939354,
      "learning_rate": 2.4168382195463367e-05,
      "loss": 0.14264242649078368,
      "step": 2890
    },
    {
      "epoch": 0.5267467248908297,
      "grad_norm": 0.17521196603775024,
      "learning_rate": 2.4094818567573618e-05,
      "loss": 0.1509538173675537,
      "step": 2895
    },
    {
      "epoch": 0.5276564774381368,
      "grad_norm": 0.1681576371192932,
      "learning_rate": 2.4021262786730428e-05,
      "loss": 0.15344605445861817,
      "step": 2900
    },
    {
      "epoch": 0.528566229985444,
      "grad_norm": 0.17134182155132294,
      "learning_rate": 2.3947715490591206e-05,
      "loss": 0.15161689519882202,
      "step": 2905
    },
    {
      "epoch": 0.5294759825327511,
      "grad_norm": 0.1796472817659378,
      "learning_rate": 2.3874177316739778e-05,
      "loss": 0.15086464881896972,
      "step": 2910
    },
    {
      "epoch": 0.5303857350800583,
      "grad_norm": 0.23268625140190125,
      "learning_rate": 2.380064890268093e-05,
      "loss": 0.15354180335998535,
      "step": 2915
    },
    {
      "epoch": 0.5312954876273653,
      "grad_norm": 0.16318941116333008,
      "learning_rate": 2.372713088583481e-05,
      "loss": 0.15131797790527343,
      "step": 2920
    },
    {
      "epoch": 0.5322052401746725,
      "grad_norm": 0.18171803653240204,
      "learning_rate": 2.365362390353143e-05,
      "loss": 0.15784090757369995,
      "step": 2925
    },
    {
      "epoch": 0.5331149927219796,
      "grad_norm": 0.17672640085220337,
      "learning_rate": 2.3580128593005156e-05,
      "loss": 0.15509436130523682,
      "step": 2930
    },
    {
      "epoch": 0.5340247452692868,
      "grad_norm": 0.15985223650932312,
      "learning_rate": 2.3506645591389174e-05,
      "loss": 0.14851027727127075,
      "step": 2935
    },
    {
      "epoch": 0.5349344978165939,
      "grad_norm": 0.16597607731819153,
      "learning_rate": 2.343317553570995e-05,
      "loss": 0.1504931092262268,
      "step": 2940
    },
    {
      "epoch": 0.535844250363901,
      "grad_norm": 0.20180748403072357,
      "learning_rate": 2.3359719062881725e-05,
      "loss": 0.15023820400238036,
      "step": 2945
    },
    {
      "epoch": 0.5367540029112081,
      "grad_norm": 0.1735963076353073,
      "learning_rate": 2.3286276809701e-05,
      "loss": 0.15374408960342406,
      "step": 2950
    },
    {
      "epoch": 0.5376637554585153,
      "grad_norm": 0.17629501223564148,
      "learning_rate": 2.3212849412840995e-05,
      "loss": 0.15007833242416382,
      "step": 2955
    },
    {
      "epoch": 0.5385735080058224,
      "grad_norm": 0.1493796557188034,
      "learning_rate": 2.3139437508846155e-05,
      "loss": 0.15206656455993653,
      "step": 2960
    },
    {
      "epoch": 0.5394832605531296,
      "grad_norm": 0.17426837980747223,
      "learning_rate": 2.306604173412659e-05,
      "loss": 0.1441131591796875,
      "step": 2965
    },
    {
      "epoch": 0.5403930131004366,
      "grad_norm": 0.16984431445598602,
      "learning_rate": 2.2992662724952613e-05,
      "loss": 0.14438753128051757,
      "step": 2970
    },
    {
      "epoch": 0.5413027656477438,
      "grad_norm": 0.1814386397600174,
      "learning_rate": 2.2919301117449167e-05,
      "loss": 0.14887022972106934,
      "step": 2975
    },
    {
      "epoch": 0.5422125181950509,
      "grad_norm": 0.158392995595932,
      "learning_rate": 2.2845957547590368e-05,
      "loss": 0.14404361248016356,
      "step": 2980
    },
    {
      "epoch": 0.5431222707423581,
      "grad_norm": 0.17496263980865479,
      "learning_rate": 2.2772632651193953e-05,
      "loss": 0.1454906702041626,
      "step": 2985
    },
    {
      "epoch": 0.5440320232896652,
      "grad_norm": 0.157533198595047,
      "learning_rate": 2.2699327063915766e-05,
      "loss": 0.1458217740058899,
      "step": 2990
    },
    {
      "epoch": 0.5449417758369723,
      "grad_norm": 0.1767890453338623,
      "learning_rate": 2.262604142124427e-05,
      "loss": 0.14384825229644777,
      "step": 2995
    },
    {
      "epoch": 0.5458515283842795,
      "grad_norm": 0.1851050704717636,
      "learning_rate": 2.2552776358495033e-05,
      "loss": 0.14832457304000854,
      "step": 3000
    },
    {
      "epoch": 0.5467612809315866,
      "grad_norm": 0.164175882935524,
      "learning_rate": 2.247953251080521e-05,
      "loss": 0.14999878406524658,
      "step": 3005
    },
    {
      "epoch": 0.5476710334788938,
      "grad_norm": 0.3403675854206085,
      "learning_rate": 2.240631051312804e-05,
      "loss": 0.1443937063217163,
      "step": 3010
    },
    {
      "epoch": 0.5485807860262009,
      "grad_norm": 0.16751109063625336,
      "learning_rate": 2.2333111000227342e-05,
      "loss": 0.1462402105331421,
      "step": 3015
    },
    {
      "epoch": 0.549490538573508,
      "grad_norm": 0.14741151034832,
      "learning_rate": 2.225993460667201e-05,
      "loss": 0.149855899810791,
      "step": 3020
    },
    {
      "epoch": 0.5504002911208151,
      "grad_norm": 0.20605266094207764,
      "learning_rate": 2.218678196683054e-05,
      "loss": 0.15413178205490113,
      "step": 3025
    },
    {
      "epoch": 0.5513100436681223,
      "grad_norm": 0.14884796738624573,
      "learning_rate": 2.2113653714865473e-05,
      "loss": 0.14592334032058715,
      "step": 3030
    },
    {
      "epoch": 0.5522197962154294,
      "grad_norm": 0.17114350199699402,
      "learning_rate": 2.2040550484727943e-05,
      "loss": 0.1498338460922241,
      "step": 3035
    },
    {
      "epoch": 0.5531295487627366,
      "grad_norm": 0.16496853530406952,
      "learning_rate": 2.196747291015219e-05,
      "loss": 0.14650315046310425,
      "step": 3040
    },
    {
      "epoch": 0.5540393013100436,
      "grad_norm": 0.15172401070594788,
      "learning_rate": 2.189442162465001e-05,
      "loss": 0.14984124898910522,
      "step": 3045
    },
    {
      "epoch": 0.5549490538573508,
      "grad_norm": 0.19258467853069305,
      "learning_rate": 2.182139726150532e-05,
      "loss": 0.1486764669418335,
      "step": 3050
    },
    {
      "epoch": 0.5558588064046579,
      "grad_norm": 0.1749001443386078,
      "learning_rate": 2.1748400453768652e-05,
      "loss": 0.14983701705932617,
      "step": 3055
    },
    {
      "epoch": 0.5567685589519651,
      "grad_norm": 0.37510567903518677,
      "learning_rate": 2.1675431834251637e-05,
      "loss": 0.14483561515808105,
      "step": 3060
    },
    {
      "epoch": 0.5576783114992722,
      "grad_norm": 0.16932405531406403,
      "learning_rate": 2.1602492035521553e-05,
      "loss": 0.14487643241882325,
      "step": 3065
    },
    {
      "epoch": 0.5585880640465793,
      "grad_norm": 0.174176424741745,
      "learning_rate": 2.152958168989584e-05,
      "loss": 0.14737497568130492,
      "step": 3070
    },
    {
      "epoch": 0.5594978165938864,
      "grad_norm": 0.1601252257823944,
      "learning_rate": 2.1456701429436577e-05,
      "loss": 0.15183379650115966,
      "step": 3075
    },
    {
      "epoch": 0.5604075691411936,
      "grad_norm": 0.14960910379886627,
      "learning_rate": 2.1383851885945085e-05,
      "loss": 0.143074893951416,
      "step": 3080
    },
    {
      "epoch": 0.5613173216885007,
      "grad_norm": 0.1678633838891983,
      "learning_rate": 2.1311033690956346e-05,
      "loss": 0.14961432218551635,
      "step": 3085
    },
    {
      "epoch": 0.5622270742358079,
      "grad_norm": 0.15814319252967834,
      "learning_rate": 2.1238247475733613e-05,
      "loss": 0.14308581352233887,
      "step": 3090
    },
    {
      "epoch": 0.5631368267831149,
      "grad_norm": 0.21240772306919098,
      "learning_rate": 2.1165493871262887e-05,
      "loss": 0.14737485647201537,
      "step": 3095
    },
    {
      "epoch": 0.5640465793304221,
      "grad_norm": 0.15161271393299103,
      "learning_rate": 2.109277350824749e-05,
      "loss": 0.14534420967102052,
      "step": 3100
    },
    {
      "epoch": 0.5649563318777293,
      "grad_norm": 0.16572362184524536,
      "learning_rate": 2.1020087017102537e-05,
      "loss": 0.14299670457839966,
      "step": 3105
    },
    {
      "epoch": 0.5658660844250364,
      "grad_norm": 0.1548164039850235,
      "learning_rate": 2.094743502794954e-05,
      "loss": 0.14371142387390137,
      "step": 3110
    },
    {
      "epoch": 0.5667758369723436,
      "grad_norm": 0.2574169933795929,
      "learning_rate": 2.0874818170610885e-05,
      "loss": 0.14350423812866211,
      "step": 3115
    },
    {
      "epoch": 0.5676855895196506,
      "grad_norm": 0.16359548270702362,
      "learning_rate": 2.080223707460443e-05,
      "loss": 0.1520243763923645,
      "step": 3120
    },
    {
      "epoch": 0.5685953420669578,
      "grad_norm": 0.1798320859670639,
      "learning_rate": 2.072969236913799e-05,
      "loss": 0.14832595586776734,
      "step": 3125
    },
    {
      "epoch": 0.5695050946142649,
      "grad_norm": 0.17045916616916656,
      "learning_rate": 2.0657184683103926e-05,
      "loss": 0.15308042764663696,
      "step": 3130
    },
    {
      "epoch": 0.5704148471615721,
      "grad_norm": 0.16345897316932678,
      "learning_rate": 2.058471464507366e-05,
      "loss": 0.14564799070358275,
      "step": 3135
    },
    {
      "epoch": 0.5713245997088792,
      "grad_norm": 0.15170110762119293,
      "learning_rate": 2.0512282883292257e-05,
      "loss": 0.14161767959594726,
      "step": 3140
    },
    {
      "epoch": 0.5722343522561864,
      "grad_norm": 0.8107472658157349,
      "learning_rate": 2.0439890025672955e-05,
      "loss": 0.14481087923049926,
      "step": 3145
    },
    {
      "epoch": 0.5731441048034934,
      "grad_norm": 0.15346679091453552,
      "learning_rate": 2.036753669979174e-05,
      "loss": 0.14860262870788574,
      "step": 3150
    },
    {
      "epoch": 0.5740538573508006,
      "grad_norm": 0.1632593423128128,
      "learning_rate": 2.0295223532881886e-05,
      "loss": 0.1481687307357788,
      "step": 3155
    },
    {
      "epoch": 0.5749636098981077,
      "grad_norm": 0.23399172723293304,
      "learning_rate": 2.022295115182852e-05,
      "loss": 0.149153733253479,
      "step": 3160
    },
    {
      "epoch": 0.5758733624454149,
      "grad_norm": 0.14977394044399261,
      "learning_rate": 2.015072018316323e-05,
      "loss": 0.14921388626098633,
      "step": 3165
    },
    {
      "epoch": 0.576783114992722,
      "grad_norm": 0.1550658792257309,
      "learning_rate": 2.007853125305856e-05,
      "loss": 0.1482759475708008,
      "step": 3170
    },
    {
      "epoch": 0.5776928675400291,
      "grad_norm": 0.16661737859249115,
      "learning_rate": 2.0006384987322645e-05,
      "loss": 0.14903552532196046,
      "step": 3175
    },
    {
      "epoch": 0.5786026200873362,
      "grad_norm": 0.1746823936700821,
      "learning_rate": 1.9934282011393753e-05,
      "loss": 0.1412947654724121,
      "step": 3180
    },
    {
      "epoch": 0.5795123726346434,
      "grad_norm": 0.17025792598724365,
      "learning_rate": 1.9862222950334857e-05,
      "loss": 0.15289769172668458,
      "step": 3185
    },
    {
      "epoch": 0.5804221251819505,
      "grad_norm": 0.16857658326625824,
      "learning_rate": 1.9790208428828252e-05,
      "loss": 0.14419941902160643,
      "step": 3190
    },
    {
      "epoch": 0.5813318777292577,
      "grad_norm": 0.16099876165390015,
      "learning_rate": 1.9718239071170118e-05,
      "loss": 0.14476487636566163,
      "step": 3195
    },
    {
      "epoch": 0.5822416302765647,
      "grad_norm": 0.16140873730182648,
      "learning_rate": 1.964631550126508e-05,
      "loss": 0.14588416814804078,
      "step": 3200
    },
    {
      "epoch": 0.5831513828238719,
      "grad_norm": 0.15719448029994965,
      "learning_rate": 1.957443834262087e-05,
      "loss": 0.15144693851470947,
      "step": 3205
    },
    {
      "epoch": 0.584061135371179,
      "grad_norm": 0.16512645781040192,
      "learning_rate": 1.950260821834285e-05,
      "loss": 0.14787566661834717,
      "step": 3210
    },
    {
      "epoch": 0.5849708879184862,
      "grad_norm": 0.18584516644477844,
      "learning_rate": 1.9430825751128643e-05,
      "loss": 0.14514710903167724,
      "step": 3215
    },
    {
      "epoch": 0.5858806404657934,
      "grad_norm": 0.17640981078147888,
      "learning_rate": 1.9359091563262742e-05,
      "loss": 0.1511004686355591,
      "step": 3220
    },
    {
      "epoch": 0.5867903930131004,
      "grad_norm": 0.1697624921798706,
      "learning_rate": 1.9287406276611095e-05,
      "loss": 0.15392563343048096,
      "step": 3225
    },
    {
      "epoch": 0.5877001455604076,
      "grad_norm": 0.1677260845899582,
      "learning_rate": 1.9215770512615725e-05,
      "loss": 0.15311745405197144,
      "step": 3230
    },
    {
      "epoch": 0.5886098981077147,
      "grad_norm": 0.15357480943202972,
      "learning_rate": 1.9144184892289337e-05,
      "loss": 0.14370160102844237,
      "step": 3235
    },
    {
      "epoch": 0.5895196506550219,
      "grad_norm": 0.18601207435131073,
      "learning_rate": 1.9072650036209955e-05,
      "loss": 0.14095077514648438,
      "step": 3240
    },
    {
      "epoch": 0.590429403202329,
      "grad_norm": 0.17313526570796967,
      "learning_rate": 1.9001166564515513e-05,
      "loss": 0.148259174823761,
      "step": 3245
    },
    {
      "epoch": 0.5913391557496361,
      "grad_norm": 0.1634378433227539,
      "learning_rate": 1.8929735096898504e-05,
      "loss": 0.15082294940948487,
      "step": 3250
    },
    {
      "epoch": 0.5922489082969432,
      "grad_norm": 0.18542174994945526,
      "learning_rate": 1.885835625260058e-05,
      "loss": 0.14461435079574586,
      "step": 3255
    },
    {
      "epoch": 0.5931586608442504,
      "grad_norm": 0.1740756630897522,
      "learning_rate": 1.87870306504072e-05,
      "loss": 0.14083608388900756,
      "step": 3260
    },
    {
      "epoch": 0.5940684133915575,
      "grad_norm": 0.25606217980384827,
      "learning_rate": 1.8715758908642288e-05,
      "loss": 0.15125386714935302,
      "step": 3265
    },
    {
      "epoch": 0.5949781659388647,
      "grad_norm": 0.20194627344608307,
      "learning_rate": 1.8644541645162834e-05,
      "loss": 0.14433003664016725,
      "step": 3270
    },
    {
      "epoch": 0.5958879184861717,
      "grad_norm": 0.1902168095111847,
      "learning_rate": 1.8573379477353542e-05,
      "loss": 0.14718132019042968,
      "step": 3275
    },
    {
      "epoch": 0.5967976710334789,
      "grad_norm": 0.15122972428798676,
      "learning_rate": 1.850227302212151e-05,
      "loss": 0.153376567363739,
      "step": 3280
    },
    {
      "epoch": 0.597707423580786,
      "grad_norm": 0.14331959187984467,
      "learning_rate": 1.843122289589085e-05,
      "loss": 0.146630597114563,
      "step": 3285
    },
    {
      "epoch": 0.5986171761280932,
      "grad_norm": 0.15083099901676178,
      "learning_rate": 1.836022971459737e-05,
      "loss": 0.1445971965789795,
      "step": 3290
    },
    {
      "epoch": 0.5995269286754003,
      "grad_norm": 0.16585418581962585,
      "learning_rate": 1.828929409368321e-05,
      "loss": 0.15120241641998292,
      "step": 3295
    },
    {
      "epoch": 0.6004366812227074,
      "grad_norm": 0.1653224229812622,
      "learning_rate": 1.8218416648091524e-05,
      "loss": 0.14349838495254516,
      "step": 3300
    },
    {
      "epoch": 0.6013464337700145,
      "grad_norm": 0.1891375184059143,
      "learning_rate": 1.8147597992261124e-05,
      "loss": 0.15171384811401367,
      "step": 3305
    },
    {
      "epoch": 0.6022561863173217,
      "grad_norm": 0.13392704725265503,
      "learning_rate": 1.8076838740121187e-05,
      "loss": 0.14607118368148803,
      "step": 3310
    },
    {
      "epoch": 0.6031659388646288,
      "grad_norm": 0.15421944856643677,
      "learning_rate": 1.8006139505085926e-05,
      "loss": 0.1380957007408142,
      "step": 3315
    },
    {
      "epoch": 0.604075691411936,
      "grad_norm": 0.16637761890888214,
      "learning_rate": 1.7935500900049246e-05,
      "loss": 0.14604611396789552,
      "step": 3320
    },
    {
      "epoch": 0.6049854439592431,
      "grad_norm": 0.16638441383838654,
      "learning_rate": 1.7864923537379445e-05,
      "loss": 0.1513611912727356,
      "step": 3325
    },
    {
      "epoch": 0.6058951965065502,
      "grad_norm": 0.1745707094669342,
      "learning_rate": 1.779440802891394e-05,
      "loss": 0.15391240119934083,
      "step": 3330
    },
    {
      "epoch": 0.6068049490538574,
      "grad_norm": 0.1620505005121231,
      "learning_rate": 1.77239549859539e-05,
      "loss": 0.14986472129821776,
      "step": 3335
    },
    {
      "epoch": 0.6077147016011645,
      "grad_norm": 0.1579132080078125,
      "learning_rate": 1.7653565019259e-05,
      "loss": 0.1466603994369507,
      "step": 3340
    },
    {
      "epoch": 0.6086244541484717,
      "grad_norm": 0.19154994189739227,
      "learning_rate": 1.7583238739042086e-05,
      "loss": 0.15228934288024903,
      "step": 3345
    },
    {
      "epoch": 0.6095342066957787,
      "grad_norm": 0.15771779417991638,
      "learning_rate": 1.7512976754963913e-05,
      "loss": 0.14965078830718995,
      "step": 3350
    },
    {
      "epoch": 0.6104439592430859,
      "grad_norm": 0.18406136333942413,
      "learning_rate": 1.744277967612785e-05,
      "loss": 0.1473196864128113,
      "step": 3355
    },
    {
      "epoch": 0.611353711790393,
      "grad_norm": 0.17603816092014313,
      "learning_rate": 1.7372648111074607e-05,
      "loss": 0.1430676221847534,
      "step": 3360
    },
    {
      "epoch": 0.6122634643377002,
      "grad_norm": 0.156408429145813,
      "learning_rate": 1.7302582667776933e-05,
      "loss": 0.14018454551696777,
      "step": 3365
    },
    {
      "epoch": 0.6131732168850073,
      "grad_norm": 0.14504843950271606,
      "learning_rate": 1.7232583953634407e-05,
      "loss": 0.14505640268325806,
      "step": 3370
    },
    {
      "epoch": 0.6140829694323144,
      "grad_norm": 0.1864968240261078,
      "learning_rate": 1.716265257546808e-05,
      "loss": 0.14810394048690795,
      "step": 3375
    },
    {
      "epoch": 0.6149927219796215,
      "grad_norm": 0.1621711403131485,
      "learning_rate": 1.7092789139515295e-05,
      "loss": 0.14203091859817504,
      "step": 3380
    },
    {
      "epoch": 0.6159024745269287,
      "grad_norm": 0.17994914948940277,
      "learning_rate": 1.70229942514244e-05,
      "loss": 0.14565644264221192,
      "step": 3385
    },
    {
      "epoch": 0.6168122270742358,
      "grad_norm": 0.1707388162612915,
      "learning_rate": 1.6953268516249486e-05,
      "loss": 0.14449434280395507,
      "step": 3390
    },
    {
      "epoch": 0.617721979621543,
      "grad_norm": 0.16425329446792603,
      "learning_rate": 1.6883612538445175e-05,
      "loss": 0.15185940265655518,
      "step": 3395
    },
    {
      "epoch": 0.61863173216885,
      "grad_norm": 0.15987788140773773,
      "learning_rate": 1.6814026921861335e-05,
      "loss": 0.14994431734085084,
      "step": 3400
    },
    {
      "epoch": 0.6195414847161572,
      "grad_norm": 0.2987690269947052,
      "learning_rate": 1.6744512269737894e-05,
      "loss": 0.14652738571166993,
      "step": 3405
    },
    {
      "epoch": 0.6204512372634643,
      "grad_norm": 0.1681315004825592,
      "learning_rate": 1.6675069184699574e-05,
      "loss": 0.14566165208816528,
      "step": 3410
    },
    {
      "epoch": 0.6213609898107715,
      "grad_norm": 0.15847846865653992,
      "learning_rate": 1.660569826875069e-05,
      "loss": 0.1374401330947876,
      "step": 3415
    },
    {
      "epoch": 0.6222707423580786,
      "grad_norm": 0.16370312869548798,
      "learning_rate": 1.6536400123269907e-05,
      "loss": 0.14905524253845215,
      "step": 3420
    },
    {
      "epoch": 0.6231804949053857,
      "grad_norm": 0.16054444015026093,
      "learning_rate": 1.6467175349005054e-05,
      "loss": 0.1496324896812439,
      "step": 3425
    },
    {
      "epoch": 0.6240902474526928,
      "grad_norm": 0.1663951277732849,
      "learning_rate": 1.639802454606788e-05,
      "loss": 0.1504170298576355,
      "step": 3430
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.1591310054063797,
      "learning_rate": 1.6328948313928906e-05,
      "loss": 0.1410186171531677,
      "step": 3435
    },
    {
      "epoch": 0.6259097525473072,
      "grad_norm": 0.1637524962425232,
      "learning_rate": 1.6259947251412178e-05,
      "loss": 0.13963305950164795,
      "step": 3440
    },
    {
      "epoch": 0.6268195050946143,
      "grad_norm": 0.1688017100095749,
      "learning_rate": 1.6191021956690096e-05,
      "loss": 0.14727941751480103,
      "step": 3445
    },
    {
      "epoch": 0.6277292576419214,
      "grad_norm": 0.1691795438528061,
      "learning_rate": 1.612217302727821e-05,
      "loss": 0.14856183528900146,
      "step": 3450
    },
    {
      "epoch": 0.6286390101892285,
      "grad_norm": 0.18501746654510498,
      "learning_rate": 1.60534010600301e-05,
      "loss": 0.1481746554374695,
      "step": 3455
    },
    {
      "epoch": 0.6295487627365357,
      "grad_norm": 0.16234716773033142,
      "learning_rate": 1.5984706651132125e-05,
      "loss": 0.1427530527114868,
      "step": 3460
    },
    {
      "epoch": 0.6304585152838428,
      "grad_norm": 0.16013780236244202,
      "learning_rate": 1.5916090396098293e-05,
      "loss": 0.14264426231384278,
      "step": 3465
    },
    {
      "epoch": 0.63136826783115,
      "grad_norm": 0.17116396129131317,
      "learning_rate": 1.5847552889765095e-05,
      "loss": 0.14109257459640503,
      "step": 3470
    },
    {
      "epoch": 0.632278020378457,
      "grad_norm": 0.16949769854545593,
      "learning_rate": 1.5779094726286344e-05,
      "loss": 0.1387040376663208,
      "step": 3475
    },
    {
      "epoch": 0.6331877729257642,
      "grad_norm": 0.14983431994915009,
      "learning_rate": 1.5710716499128044e-05,
      "loss": 0.13645120859146118,
      "step": 3480
    },
    {
      "epoch": 0.6340975254730713,
      "grad_norm": 0.1632554531097412,
      "learning_rate": 1.564241880106321e-05,
      "loss": 0.14883992671966553,
      "step": 3485
    },
    {
      "epoch": 0.6350072780203785,
      "grad_norm": 0.15686506032943726,
      "learning_rate": 1.5574202224166744e-05,
      "loss": 0.14244272708892822,
      "step": 3490
    },
    {
      "epoch": 0.6359170305676856,
      "grad_norm": 0.18843458592891693,
      "learning_rate": 1.5506067359810333e-05,
      "loss": 0.15149861574172974,
      "step": 3495
    },
    {
      "epoch": 0.6368267831149927,
      "grad_norm": 0.15874551236629486,
      "learning_rate": 1.5438014798657275e-05,
      "loss": 0.15188233852386473,
      "step": 3500
    },
    {
      "epoch": 0.6377365356622998,
      "grad_norm": 0.17014239728450775,
      "learning_rate": 1.5370045130657366e-05,
      "loss": 0.14694437980651856,
      "step": 3505
    },
    {
      "epoch": 0.638646288209607,
      "grad_norm": 0.14744038879871368,
      "learning_rate": 1.5302158945041838e-05,
      "loss": 0.14434736967086792,
      "step": 3510
    },
    {
      "epoch": 0.6395560407569141,
      "grad_norm": 0.2069770246744156,
      "learning_rate": 1.523435683031818e-05,
      "loss": 0.13982917070388795,
      "step": 3515
    },
    {
      "epoch": 0.6404657933042213,
      "grad_norm": 0.17811502516269684,
      "learning_rate": 1.5166639374265063e-05,
      "loss": 0.1408839702606201,
      "step": 3520
    },
    {
      "epoch": 0.6413755458515283,
      "grad_norm": 0.165786474943161,
      "learning_rate": 1.509900716392728e-05,
      "loss": 0.15312877893447877,
      "step": 3525
    },
    {
      "epoch": 0.6422852983988355,
      "grad_norm": 0.1633884161710739,
      "learning_rate": 1.5031460785610596e-05,
      "loss": 0.1488795518875122,
      "step": 3530
    },
    {
      "epoch": 0.6431950509461426,
      "grad_norm": 0.16498984396457672,
      "learning_rate": 1.4964000824876723e-05,
      "loss": 0.15031465291976928,
      "step": 3535
    },
    {
      "epoch": 0.6441048034934498,
      "grad_norm": 0.18043678998947144,
      "learning_rate": 1.4896627866538191e-05,
      "loss": 0.147829806804657,
      "step": 3540
    },
    {
      "epoch": 0.6450145560407569,
      "grad_norm": 0.16813597083091736,
      "learning_rate": 1.4829342494653315e-05,
      "loss": 0.1418998956680298,
      "step": 3545
    },
    {
      "epoch": 0.645924308588064,
      "grad_norm": 0.1817242056131363,
      "learning_rate": 1.4762145292521118e-05,
      "loss": 0.14508869647979736,
      "step": 3550
    },
    {
      "epoch": 0.6468340611353712,
      "grad_norm": 0.14666494727134705,
      "learning_rate": 1.469503684267628e-05,
      "loss": 0.14159854650497436,
      "step": 3555
    },
    {
      "epoch": 0.6477438136826783,
      "grad_norm": 0.16485381126403809,
      "learning_rate": 1.4628017726884086e-05,
      "loss": 0.14419105052947997,
      "step": 3560
    },
    {
      "epoch": 0.6486535662299855,
      "grad_norm": 0.16100342571735382,
      "learning_rate": 1.4561088526135375e-05,
      "loss": 0.14501721858978273,
      "step": 3565
    },
    {
      "epoch": 0.6495633187772926,
      "grad_norm": 0.16996590793132782,
      "learning_rate": 1.4494249820641493e-05,
      "loss": 0.1377166509628296,
      "step": 3570
    },
    {
      "epoch": 0.6504730713245997,
      "grad_norm": 0.16168837249279022,
      "learning_rate": 1.4427502189829339e-05,
      "loss": 0.1414325475692749,
      "step": 3575
    },
    {
      "epoch": 0.6513828238719068,
      "grad_norm": 0.16318906843662262,
      "learning_rate": 1.436084621233621e-05,
      "loss": 0.14685193300247193,
      "step": 3580
    },
    {
      "epoch": 0.652292576419214,
      "grad_norm": 0.1636219322681427,
      "learning_rate": 1.4294282466004899e-05,
      "loss": 0.1405899167060852,
      "step": 3585
    },
    {
      "epoch": 0.6532023289665211,
      "grad_norm": 0.1838461309671402,
      "learning_rate": 1.422781152787865e-05,
      "loss": 0.14386332035064697,
      "step": 3590
    },
    {
      "epoch": 0.6541120815138283,
      "grad_norm": 0.1796344667673111,
      "learning_rate": 1.4161433974196115e-05,
      "loss": 0.1513024687767029,
      "step": 3595
    },
    {
      "epoch": 0.6550218340611353,
      "grad_norm": 0.16424529254436493,
      "learning_rate": 1.4095150380386427e-05,
      "loss": 0.14238927364349366,
      "step": 3600
    },
    {
      "epoch": 0.6559315866084425,
      "grad_norm": 0.19264160096645355,
      "learning_rate": 1.402896132106415e-05,
      "loss": 0.14297477006912232,
      "step": 3605
    },
    {
      "epoch": 0.6568413391557496,
      "grad_norm": 0.18319948017597198,
      "learning_rate": 1.3962867370024347e-05,
      "loss": 0.1448880434036255,
      "step": 3610
    },
    {
      "epoch": 0.6577510917030568,
      "grad_norm": 0.16507290303707123,
      "learning_rate": 1.389686910023758e-05,
      "loss": 0.14724698066711425,
      "step": 3615
    },
    {
      "epoch": 0.6586608442503639,
      "grad_norm": 0.17871244251728058,
      "learning_rate": 1.3830967083844942e-05,
      "loss": 0.14479386806488037,
      "step": 3620
    },
    {
      "epoch": 0.659570596797671,
      "grad_norm": 0.1846228390932083,
      "learning_rate": 1.3765161892153112e-05,
      "loss": 0.1453616738319397,
      "step": 3625
    },
    {
      "epoch": 0.6604803493449781,
      "grad_norm": 0.17185978591442108,
      "learning_rate": 1.3699454095629372e-05,
      "loss": 0.14906206130981445,
      "step": 3630
    },
    {
      "epoch": 0.6613901018922853,
      "grad_norm": 0.14751191437244415,
      "learning_rate": 1.3633844263896698e-05,
      "loss": 0.13991892337799072,
      "step": 3635
    },
    {
      "epoch": 0.6622998544395924,
      "grad_norm": 0.22059763967990875,
      "learning_rate": 1.3568332965728817e-05,
      "loss": 0.14680869579315187,
      "step": 3640
    },
    {
      "epoch": 0.6632096069868996,
      "grad_norm": 0.15295909345149994,
      "learning_rate": 1.3502920769045232e-05,
      "loss": 0.1404443383216858,
      "step": 3645
    },
    {
      "epoch": 0.6641193595342066,
      "grad_norm": 0.14600558578968048,
      "learning_rate": 1.3437608240906364e-05,
      "loss": 0.14663270711898804,
      "step": 3650
    },
    {
      "epoch": 0.6650291120815138,
      "grad_norm": 0.15548352897167206,
      "learning_rate": 1.3372395947508587e-05,
      "loss": 0.1431443452835083,
      "step": 3655
    },
    {
      "epoch": 0.665938864628821,
      "grad_norm": 0.1813388466835022,
      "learning_rate": 1.3307284454179342e-05,
      "loss": 0.1458706736564636,
      "step": 3660
    },
    {
      "epoch": 0.6668486171761281,
      "grad_norm": 0.16326870024204254,
      "learning_rate": 1.3242274325372247e-05,
      "loss": 0.14700595140457154,
      "step": 3665
    },
    {
      "epoch": 0.6677583697234353,
      "grad_norm": 0.18779197335243225,
      "learning_rate": 1.3177366124662149e-05,
      "loss": 0.1497237801551819,
      "step": 3670
    },
    {
      "epoch": 0.6686681222707423,
      "grad_norm": 0.16291002929210663,
      "learning_rate": 1.3112560414740315e-05,
      "loss": 0.1387086868286133,
      "step": 3675
    },
    {
      "epoch": 0.6695778748180495,
      "grad_norm": 0.1532297134399414,
      "learning_rate": 1.3047857757409487e-05,
      "loss": 0.14497545957565308,
      "step": 3680
    },
    {
      "epoch": 0.6704876273653566,
      "grad_norm": 0.14697515964508057,
      "learning_rate": 1.2983258713579066e-05,
      "loss": 0.1494283437728882,
      "step": 3685
    },
    {
      "epoch": 0.6713973799126638,
      "grad_norm": 0.15213452279567719,
      "learning_rate": 1.2918763843260218e-05,
      "loss": 0.1468907594680786,
      "step": 3690
    },
    {
      "epoch": 0.6723071324599709,
      "grad_norm": 0.1745215803384781,
      "learning_rate": 1.285437370556099e-05,
      "loss": 0.14997754096984864,
      "step": 3695
    },
    {
      "epoch": 0.673216885007278,
      "grad_norm": 0.19207637012004852,
      "learning_rate": 1.2790088858681577e-05,
      "loss": 0.14202862977981567,
      "step": 3700
    },
    {
      "epoch": 0.6741266375545851,
      "grad_norm": 0.1521359086036682,
      "learning_rate": 1.2725909859909313e-05,
      "loss": 0.14547673463821412,
      "step": 3705
    },
    {
      "epoch": 0.6750363901018923,
      "grad_norm": 0.16975535452365875,
      "learning_rate": 1.2661837265613999e-05,
      "loss": 0.14006874561309815,
      "step": 3710
    },
    {
      "epoch": 0.6759461426491994,
      "grad_norm": 0.22234582901000977,
      "learning_rate": 1.2597871631242992e-05,
      "loss": 0.13691173791885375,
      "step": 3715
    },
    {
      "epoch": 0.6768558951965066,
      "grad_norm": 0.16082969307899475,
      "learning_rate": 1.2534013511316383e-05,
      "loss": 0.14932308197021485,
      "step": 3720
    },
    {
      "epoch": 0.6777656477438136,
      "grad_norm": 0.1751091182231903,
      "learning_rate": 1.247026345942226e-05,
      "loss": 0.14531974792480468,
      "step": 3725
    },
    {
      "epoch": 0.6786754002911208,
      "grad_norm": 0.15838147699832916,
      "learning_rate": 1.2406622028211844e-05,
      "loss": 0.14759832620620728,
      "step": 3730
    },
    {
      "epoch": 0.6795851528384279,
      "grad_norm": 0.1771744042634964,
      "learning_rate": 1.2343089769394714e-05,
      "loss": 0.1382831573486328,
      "step": 3735
    },
    {
      "epoch": 0.6804949053857351,
      "grad_norm": 0.16301538050174713,
      "learning_rate": 1.2279667233734037e-05,
      "loss": 0.14444775581359864,
      "step": 3740
    },
    {
      "epoch": 0.6814046579330422,
      "grad_norm": 0.1584121286869049,
      "learning_rate": 1.2216354971041796e-05,
      "loss": 0.14200170040130616,
      "step": 3745
    },
    {
      "epoch": 0.6823144104803494,
      "grad_norm": 0.139187291264534,
      "learning_rate": 1.2153153530174007e-05,
      "loss": 0.14318310022354125,
      "step": 3750
    },
    {
      "epoch": 0.6832241630276564,
      "grad_norm": 0.13665248453617096,
      "learning_rate": 1.2090063459025955e-05,
      "loss": 0.1411946654319763,
      "step": 3755
    },
    {
      "epoch": 0.6841339155749636,
      "grad_norm": 0.16273781657218933,
      "learning_rate": 1.2027085304527475e-05,
      "loss": 0.14873508214950562,
      "step": 3760
    },
    {
      "epoch": 0.6850436681222707,
      "grad_norm": 0.16317526996135712,
      "learning_rate": 1.1964219612638194e-05,
      "loss": 0.14644203186035157,
      "step": 3765
    },
    {
      "epoch": 0.6859534206695779,
      "grad_norm": 0.17253617942333221,
      "learning_rate": 1.1901466928342777e-05,
      "loss": 0.14027841091156007,
      "step": 3770
    },
    {
      "epoch": 0.6868631732168851,
      "grad_norm": 0.19692830741405487,
      "learning_rate": 1.183882779564624e-05,
      "loss": 0.14411110877990724,
      "step": 3775
    },
    {
      "epoch": 0.6877729257641921,
      "grad_norm": 0.15444578230381012,
      "learning_rate": 1.1776302757569214e-05,
      "loss": 0.14355008602142333,
      "step": 3780
    },
    {
      "epoch": 0.6886826783114993,
      "grad_norm": 0.1622200757265091,
      "learning_rate": 1.1713892356143239e-05,
      "loss": 0.14794334173202514,
      "step": 3785
    },
    {
      "epoch": 0.6895924308588064,
      "grad_norm": 0.1898501068353653,
      "learning_rate": 1.1651597132406073e-05,
      "loss": 0.1418622612953186,
      "step": 3790
    },
    {
      "epoch": 0.6905021834061136,
      "grad_norm": 0.17803208529949188,
      "learning_rate": 1.1589417626396973e-05,
      "loss": 0.14576040506362914,
      "step": 3795
    },
    {
      "epoch": 0.6914119359534207,
      "grad_norm": 0.17138013243675232,
      "learning_rate": 1.1527354377152053e-05,
      "loss": 0.14494270086288452,
      "step": 3800
    }
  ],
  "logging_steps": 5,
  "max_steps": 5500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.0912782443288745e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}