{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.2502930374306478,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025005860748612955,
      "grad_norm": 0.9269847273826599,
      "learning_rate": 4e-05,
      "loss": 2.5172,
      "step": 1
    },
    {
      "epoch": 0.005001172149722591,
      "grad_norm": 0.8822197318077087,
      "learning_rate": 8e-05,
      "loss": 2.5129,
      "step": 2
    },
    {
      "epoch": 0.007501758224583887,
      "grad_norm": 0.9105328917503357,
      "learning_rate": 0.00012,
      "loss": 2.4871,
      "step": 3
    },
    {
      "epoch": 0.010002344299445182,
      "grad_norm": 1.040933609008789,
      "learning_rate": 0.00016,
      "loss": 2.4756,
      "step": 4
    },
    {
      "epoch": 0.012502930374306479,
      "grad_norm": 0.9631335735321045,
      "learning_rate": 0.0002,
      "loss": 2.2208,
      "step": 5
    },
    {
      "epoch": 0.015003516449167774,
      "grad_norm": 0.9249287247657776,
      "learning_rate": 0.0001998322147651007,
      "loss": 1.9561,
      "step": 6
    },
    {
      "epoch": 0.01750410252402907,
      "grad_norm": 1.0489821434020996,
      "learning_rate": 0.00019966442953020134,
      "loss": 1.7816,
      "step": 7
    },
    {
      "epoch": 0.020004688598890364,
      "grad_norm": 0.7718613147735596,
      "learning_rate": 0.00019949664429530202,
      "loss": 1.5392,
      "step": 8
    },
    {
      "epoch": 0.02250527467375166,
      "grad_norm": 0.6948288679122925,
      "learning_rate": 0.00019932885906040267,
      "loss": 1.3313,
      "step": 9
    },
    {
      "epoch": 0.025005860748612958,
      "grad_norm": 0.4082912504673004,
      "learning_rate": 0.00019916107382550338,
      "loss": 1.284,
      "step": 10
    },
    {
      "epoch": 0.02750644682347425,
      "grad_norm": 0.39728468656539917,
      "learning_rate": 0.00019899328859060403,
      "loss": 1.263,
      "step": 11
    },
    {
      "epoch": 0.030007032898335548,
      "grad_norm": 0.44735899567604065,
      "learning_rate": 0.00019882550335570471,
      "loss": 1.2095,
      "step": 12
    },
    {
      "epoch": 0.032507618973196845,
      "grad_norm": 0.5090083479881287,
      "learning_rate": 0.0001986577181208054,
      "loss": 1.2178,
      "step": 13
    },
    {
      "epoch": 0.03500820504805814,
      "grad_norm": 0.5362133979797363,
      "learning_rate": 0.00019848993288590605,
      "loss": 1.2615,
      "step": 14
    },
    {
      "epoch": 0.03750879112291943,
      "grad_norm": 0.6663621664047241,
      "learning_rate": 0.00019832214765100673,
      "loss": 1.1609,
      "step": 15
    },
    {
      "epoch": 0.04000937719778073,
      "grad_norm": 0.8338614106178284,
      "learning_rate": 0.00019815436241610738,
      "loss": 1.0952,
      "step": 16
    },
    {
      "epoch": 0.042509963272642025,
      "grad_norm": 0.8141220211982727,
      "learning_rate": 0.00019798657718120806,
      "loss": 1.1661,
      "step": 17
    },
    {
      "epoch": 0.04501054934750332,
      "grad_norm": 0.8922987580299377,
      "learning_rate": 0.0001978187919463087,
      "loss": 1.1088,
      "step": 18
    },
    {
      "epoch": 0.04751113542236462,
      "grad_norm": 0.4849202334880829,
      "learning_rate": 0.00019765100671140942,
      "loss": 1.0611,
      "step": 19
    },
    {
      "epoch": 0.050011721497225915,
      "grad_norm": 0.20992806553840637,
      "learning_rate": 0.00019748322147651007,
      "loss": 1.1372,
      "step": 20
    },
    {
      "epoch": 0.052512307572087205,
      "grad_norm": 0.20208662748336792,
      "learning_rate": 0.00019731543624161075,
      "loss": 1.1255,
      "step": 21
    },
    {
      "epoch": 0.0550128936469485,
      "grad_norm": 0.19485554099082947,
      "learning_rate": 0.00019714765100671143,
      "loss": 1.1028,
      "step": 22
    },
    {
      "epoch": 0.0575134797218098,
      "grad_norm": 0.2088543176651001,
      "learning_rate": 0.00019697986577181208,
      "loss": 1.0978,
      "step": 23
    },
    {
      "epoch": 0.060014065796671096,
      "grad_norm": 0.21725241839885712,
      "learning_rate": 0.00019681208053691276,
      "loss": 1.0679,
      "step": 24
    },
    {
      "epoch": 0.06251465187153239,
      "grad_norm": 0.21685351431369781,
      "learning_rate": 0.00019664429530201342,
      "loss": 1.08,
      "step": 25
    },
    {
      "epoch": 0.06501523794639369,
      "grad_norm": 0.22109799087047577,
      "learning_rate": 0.0001964765100671141,
      "loss": 1.0804,
      "step": 26
    },
    {
      "epoch": 0.06751582402125499,
      "grad_norm": 0.1903853863477707,
      "learning_rate": 0.00019630872483221478,
      "loss": 1.0673,
      "step": 27
    },
    {
      "epoch": 0.07001641009611628,
      "grad_norm": 0.2121160328388214,
      "learning_rate": 0.00019614093959731546,
      "loss": 1.029,
      "step": 28
    },
    {
      "epoch": 0.07251699617097758,
      "grad_norm": 0.17948715388774872,
      "learning_rate": 0.00019597315436241613,
      "loss": 1.0788,
      "step": 29
    },
    {
      "epoch": 0.07501758224583886,
      "grad_norm": 0.18863339722156525,
      "learning_rate": 0.0001958053691275168,
      "loss": 1.1238,
      "step": 30
    },
    {
      "epoch": 0.07751816832070016,
      "grad_norm": 0.18628939986228943,
      "learning_rate": 0.00019563758389261747,
      "loss": 1.0934,
      "step": 31
    },
    {
      "epoch": 0.08001875439556146,
      "grad_norm": 0.16961562633514404,
      "learning_rate": 0.00019546979865771812,
      "loss": 0.983,
      "step": 32
    },
    {
      "epoch": 0.08251934047042275,
      "grad_norm": 0.19999153912067413,
      "learning_rate": 0.0001953020134228188,
      "loss": 1.0447,
      "step": 33
    },
    {
      "epoch": 0.08501992654528405,
      "grad_norm": 0.18386781215667725,
      "learning_rate": 0.00019513422818791945,
      "loss": 1.1093,
      "step": 34
    },
    {
      "epoch": 0.08752051262014535,
      "grad_norm": 0.19115187227725983,
      "learning_rate": 0.00019496644295302013,
      "loss": 1.0573,
      "step": 35
    },
    {
      "epoch": 0.09002109869500664,
      "grad_norm": 0.17980585992336273,
      "learning_rate": 0.0001947986577181208,
      "loss": 1.0733,
      "step": 36
    },
    {
      "epoch": 0.09252168476986794,
      "grad_norm": 0.17686498165130615,
      "learning_rate": 0.0001946308724832215,
      "loss": 1.1531,
      "step": 37
    },
    {
      "epoch": 0.09502227084472924,
      "grad_norm": 0.19470718502998352,
      "learning_rate": 0.00019446308724832217,
      "loss": 1.134,
      "step": 38
    },
    {
      "epoch": 0.09752285691959053,
      "grad_norm": 0.2018202841281891,
      "learning_rate": 0.00019429530201342282,
      "loss": 1.0134,
      "step": 39
    },
    {
      "epoch": 0.10002344299445183,
      "grad_norm": 0.19689340889453888,
      "learning_rate": 0.0001941275167785235,
      "loss": 1.0327,
      "step": 40
    },
    {
      "epoch": 0.10252402906931311,
      "grad_norm": 0.19733501970767975,
      "learning_rate": 0.00019395973154362416,
      "loss": 1.0542,
      "step": 41
    },
    {
      "epoch": 0.10502461514417441,
      "grad_norm": 0.20530100166797638,
      "learning_rate": 0.00019379194630872484,
      "loss": 1.0185,
      "step": 42
    },
    {
      "epoch": 0.10752520121903571,
      "grad_norm": 0.20656965672969818,
      "learning_rate": 0.00019362416107382552,
      "loss": 0.9785,
      "step": 43
    },
    {
      "epoch": 0.110025787293897,
      "grad_norm": 0.1925908923149109,
      "learning_rate": 0.00019345637583892617,
      "loss": 1.0632,
      "step": 44
    },
    {
      "epoch": 0.1125263733687583,
      "grad_norm": 0.1836056113243103,
      "learning_rate": 0.00019328859060402688,
      "loss": 1.0046,
      "step": 45
    },
    {
      "epoch": 0.1150269594436196,
      "grad_norm": 0.1750098317861557,
      "learning_rate": 0.00019312080536912753,
      "loss": 1.0088,
      "step": 46
    },
    {
      "epoch": 0.1175275455184809,
      "grad_norm": 0.17450976371765137,
      "learning_rate": 0.0001929530201342282,
      "loss": 1.0329,
      "step": 47
    },
    {
      "epoch": 0.12002813159334219,
      "grad_norm": 0.17772209644317627,
      "learning_rate": 0.00019278523489932886,
      "loss": 1.0071,
      "step": 48
    },
    {
      "epoch": 0.12252871766820349,
      "grad_norm": 0.19410440325737,
      "learning_rate": 0.00019261744966442954,
      "loss": 1.0533,
      "step": 49
    },
    {
      "epoch": 0.12502930374306478,
      "grad_norm": 0.18247346580028534,
      "learning_rate": 0.00019244966442953022,
      "loss": 0.9578,
      "step": 50
    },
    {
      "epoch": 0.12752988981792607,
      "grad_norm": 0.19110924005508423,
      "learning_rate": 0.00019228187919463087,
      "loss": 1.0692,
      "step": 51
    },
    {
      "epoch": 0.13003047589278738,
      "grad_norm": 0.19710960984230042,
      "learning_rate": 0.00019211409395973155,
      "loss": 1.0528,
      "step": 52
    },
    {
      "epoch": 0.13253106196764866,
      "grad_norm": 0.19629694521427155,
      "learning_rate": 0.0001919463087248322,
      "loss": 0.976,
      "step": 53
    },
    {
      "epoch": 0.13503164804250997,
      "grad_norm": 0.19290994107723236,
      "learning_rate": 0.0001917785234899329,
      "loss": 1.0599,
      "step": 54
    },
    {
      "epoch": 0.13753223411737125,
      "grad_norm": 0.18594202399253845,
      "learning_rate": 0.00019161073825503357,
      "loss": 1.0428,
      "step": 55
    },
    {
      "epoch": 0.14003282019223257,
      "grad_norm": 0.19421391189098358,
      "learning_rate": 0.00019144295302013425,
      "loss": 1.0367,
      "step": 56
    },
    {
      "epoch": 0.14253340626709385,
      "grad_norm": 0.19107426702976227,
      "learning_rate": 0.0001912751677852349,
      "loss": 1.0337,
      "step": 57
    },
    {
      "epoch": 0.14503399234195516,
      "grad_norm": 0.19118137657642365,
      "learning_rate": 0.00019110738255033558,
      "loss": 1.0528,
      "step": 58
    },
    {
      "epoch": 0.14753457841681644,
      "grad_norm": 0.19613830745220184,
      "learning_rate": 0.00019093959731543626,
      "loss": 1.0288,
      "step": 59
    },
    {
      "epoch": 0.15003516449167772,
      "grad_norm": 0.19156797230243683,
      "learning_rate": 0.0001907718120805369,
      "loss": 1.0409,
      "step": 60
    },
    {
      "epoch": 0.15253575056653904,
      "grad_norm": 0.1780826449394226,
      "learning_rate": 0.0001906040268456376,
      "loss": 0.9963,
      "step": 61
    },
    {
      "epoch": 0.15503633664140032,
      "grad_norm": 0.20309200882911682,
      "learning_rate": 0.00019043624161073827,
      "loss": 0.9674,
      "step": 62
    },
    {
      "epoch": 0.15753692271626163,
      "grad_norm": 0.20832936465740204,
      "learning_rate": 0.00019026845637583895,
      "loss": 1.0019,
      "step": 63
    },
    {
      "epoch": 0.1600375087911229,
      "grad_norm": 0.18242955207824707,
      "learning_rate": 0.0001901006711409396,
      "loss": 0.9708,
      "step": 64
    },
    {
      "epoch": 0.16253809486598422,
      "grad_norm": 0.1992724984884262,
      "learning_rate": 0.00018993288590604028,
      "loss": 1.0076,
      "step": 65
    },
    {
      "epoch": 0.1650386809408455,
      "grad_norm": 0.20120841264724731,
      "learning_rate": 0.00018976510067114096,
      "loss": 0.9708,
      "step": 66
    },
    {
      "epoch": 0.16753926701570682,
      "grad_norm": 0.21059167385101318,
      "learning_rate": 0.00018959731543624161,
      "loss": 1.0076,
      "step": 67
    },
    {
      "epoch": 0.1700398530905681,
      "grad_norm": 0.1988890916109085,
      "learning_rate": 0.0001894295302013423,
      "loss": 1.0054,
      "step": 68
    },
    {
      "epoch": 0.1725404391654294,
      "grad_norm": 0.1952708512544632,
      "learning_rate": 0.00018926174496644295,
      "loss": 1.0351,
      "step": 69
    },
    {
      "epoch": 0.1750410252402907,
      "grad_norm": 0.23466959595680237,
      "learning_rate": 0.00018909395973154363,
      "loss": 0.9814,
      "step": 70
    },
    {
      "epoch": 0.17754161131515198,
      "grad_norm": 0.20591197907924652,
      "learning_rate": 0.0001889261744966443,
      "loss": 0.9691,
      "step": 71
    },
    {
      "epoch": 0.1800421973900133,
      "grad_norm": 0.2023579180240631,
      "learning_rate": 0.000188758389261745,
      "loss": 1.0003,
      "step": 72
    },
    {
      "epoch": 0.18254278346487457,
      "grad_norm": 0.20543326437473297,
      "learning_rate": 0.00018859060402684564,
      "loss": 0.9683,
      "step": 73
    },
    {
      "epoch": 0.18504336953973588,
      "grad_norm": 0.20226700603961945,
      "learning_rate": 0.00018842281879194632,
      "loss": 1.0036,
      "step": 74
    },
    {
      "epoch": 0.18754395561459716,
      "grad_norm": 0.19225859642028809,
      "learning_rate": 0.000188255033557047,
      "loss": 0.9743,
      "step": 75
    },
    {
      "epoch": 0.19004454168945847,
      "grad_norm": 0.21251380443572998,
      "learning_rate": 0.00018808724832214765,
      "loss": 1.0073,
      "step": 76
    },
    {
      "epoch": 0.19254512776431976,
      "grad_norm": 0.2131969928741455,
      "learning_rate": 0.00018791946308724833,
      "loss": 0.9934,
      "step": 77
    },
    {
      "epoch": 0.19504571383918107,
      "grad_norm": 0.19129155576229095,
      "learning_rate": 0.00018775167785234898,
      "loss": 1.0119,
      "step": 78
    },
    {
      "epoch": 0.19754629991404235,
      "grad_norm": 0.20633932948112488,
      "learning_rate": 0.00018758389261744966,
      "loss": 1.0344,
      "step": 79
    },
    {
      "epoch": 0.20004688598890366,
      "grad_norm": 0.21870285272598267,
      "learning_rate": 0.00018741610738255034,
      "loss": 1.0207,
      "step": 80
    },
    {
      "epoch": 0.20254747206376494,
      "grad_norm": 0.2022286206483841,
      "learning_rate": 0.00018724832214765102,
      "loss": 1.026,
      "step": 81
    },
    {
      "epoch": 0.20504805813862623,
      "grad_norm": 0.21065476536750793,
      "learning_rate": 0.0001870805369127517,
      "loss": 1.0396,
      "step": 82
    },
    {
      "epoch": 0.20754864421348754,
      "grad_norm": 0.19675321877002716,
      "learning_rate": 0.00018691275167785236,
      "loss": 0.9884,
      "step": 83
    },
    {
      "epoch": 0.21004923028834882,
      "grad_norm": 0.22069697082042694,
      "learning_rate": 0.00018674496644295304,
      "loss": 1.0053,
      "step": 84
    },
    {
      "epoch": 0.21254981636321013,
      "grad_norm": 0.19039078056812286,
      "learning_rate": 0.0001865771812080537,
      "loss": 0.9954,
      "step": 85
    },
    {
      "epoch": 0.21505040243807141,
      "grad_norm": 0.2229384034872055,
      "learning_rate": 0.00018640939597315437,
      "loss": 0.9337,
      "step": 86
    },
    {
      "epoch": 0.21755098851293272,
      "grad_norm": 0.19707229733467102,
      "learning_rate": 0.00018624161073825502,
      "loss": 1.01,
      "step": 87
    },
    {
      "epoch": 0.220051574587794,
      "grad_norm": 0.19986790418624878,
      "learning_rate": 0.0001860738255033557,
      "loss": 0.9801,
      "step": 88
    },
    {
      "epoch": 0.22255216066265532,
      "grad_norm": 0.2047620266675949,
      "learning_rate": 0.00018590604026845638,
      "loss": 0.9507,
      "step": 89
    },
    {
      "epoch": 0.2250527467375166,
      "grad_norm": 0.20746001601219177,
      "learning_rate": 0.00018573825503355706,
      "loss": 1.0103,
      "step": 90
    },
    {
      "epoch": 0.2275533328123779,
      "grad_norm": 0.2248009592294693,
      "learning_rate": 0.00018557046979865774,
      "loss": 0.9869,
      "step": 91
    },
    {
      "epoch": 0.2300539188872392,
      "grad_norm": 0.20264257490634918,
      "learning_rate": 0.0001854026845637584,
      "loss": 0.9913,
      "step": 92
    },
    {
      "epoch": 0.2325545049621005,
      "grad_norm": 0.20468488335609436,
      "learning_rate": 0.00018523489932885907,
      "loss": 0.9607,
      "step": 93
    },
    {
      "epoch": 0.2350550910369618,
      "grad_norm": 0.23831503093242645,
      "learning_rate": 0.00018506711409395973,
      "loss": 1.0247,
      "step": 94
    },
    {
      "epoch": 0.23755567711182307,
      "grad_norm": 0.18826642632484436,
      "learning_rate": 0.0001848993288590604,
      "loss": 0.9482,
      "step": 95
    },
    {
      "epoch": 0.24005626318668438,
      "grad_norm": 0.19682301580905914,
      "learning_rate": 0.00018473154362416109,
      "loss": 1.001,
      "step": 96
    },
    {
      "epoch": 0.24255684926154567,
      "grad_norm": 0.2301325500011444,
      "learning_rate": 0.00018456375838926174,
      "loss": 1.0467,
      "step": 97
    },
    {
      "epoch": 0.24505743533640698,
      "grad_norm": 0.20185357332229614,
      "learning_rate": 0.00018439597315436244,
      "loss": 0.9464,
      "step": 98
    },
    {
      "epoch": 0.24755802141126826,
      "grad_norm": 0.2085759937763214,
      "learning_rate": 0.0001842281879194631,
      "loss": 1.0131,
      "step": 99
    },
    {
      "epoch": 0.25005860748612957,
      "grad_norm": 0.20679374039173126,
      "learning_rate": 0.00018406040268456378,
      "loss": 1.0529,
      "step": 100
    },
    {
      "epoch": 0.2525591935609909,
      "grad_norm": 0.21764545142650604,
      "learning_rate": 0.00018389261744966443,
      "loss": 1.017,
      "step": 101
    },
    {
      "epoch": 0.25505977963585214,
      "grad_norm": 0.2044128179550171,
      "learning_rate": 0.0001837248322147651,
      "loss": 0.9725,
      "step": 102
    },
    {
      "epoch": 0.25756036571071345,
      "grad_norm": 0.19335702061653137,
      "learning_rate": 0.0001835570469798658,
      "loss": 0.9906,
      "step": 103
    },
    {
      "epoch": 0.26006095178557476,
      "grad_norm": 0.195275217294693,
      "learning_rate": 0.00018338926174496644,
      "loss": 0.967,
      "step": 104
    },
    {
      "epoch": 0.26256153786043607,
      "grad_norm": 0.2024708092212677,
      "learning_rate": 0.00018322147651006712,
      "loss": 0.9881,
      "step": 105
    },
    {
      "epoch": 0.2650621239352973,
      "grad_norm": 0.1868991106748581,
      "learning_rate": 0.0001830536912751678,
      "loss": 0.9886,
      "step": 106
    },
    {
      "epoch": 0.26756271001015863,
      "grad_norm": 0.20454883575439453,
      "learning_rate": 0.00018288590604026848,
      "loss": 1.0121,
      "step": 107
    },
    {
      "epoch": 0.27006329608501994,
      "grad_norm": 0.20686966180801392,
      "learning_rate": 0.00018271812080536913,
      "loss": 0.9569,
      "step": 108
    },
    {
      "epoch": 0.2725638821598812,
      "grad_norm": 0.20435401797294617,
      "learning_rate": 0.00018255033557046981,
      "loss": 0.9742,
      "step": 109
    },
    {
      "epoch": 0.2750644682347425,
      "grad_norm": 0.18989619612693787,
      "learning_rate": 0.00018238255033557047,
      "loss": 0.9616,
      "step": 110
    },
    {
      "epoch": 0.2775650543096038,
      "grad_norm": 0.2045942097902298,
      "learning_rate": 0.00018221476510067115,
      "loss": 0.9302,
      "step": 111
    },
    {
      "epoch": 0.28006564038446513,
      "grad_norm": 0.20995117723941803,
      "learning_rate": 0.00018204697986577183,
      "loss": 1.0072,
      "step": 112
    },
    {
      "epoch": 0.2825662264593264,
      "grad_norm": 0.19431668519973755,
      "learning_rate": 0.00018187919463087248,
      "loss": 0.9932,
      "step": 113
    },
    {
      "epoch": 0.2850668125341877,
      "grad_norm": 0.20368535816669464,
      "learning_rate": 0.00018171140939597316,
      "loss": 0.9882,
      "step": 114
    },
    {
      "epoch": 0.287567398609049,
      "grad_norm": 0.1923864632844925,
      "learning_rate": 0.00018154362416107384,
      "loss": 0.9779,
      "step": 115
    },
    {
      "epoch": 0.2900679846839103,
      "grad_norm": 0.19875271618366241,
      "learning_rate": 0.00018137583892617452,
      "loss": 0.9934,
      "step": 116
    },
    {
      "epoch": 0.2925685707587716,
      "grad_norm": 0.21339964866638184,
      "learning_rate": 0.00018120805369127517,
      "loss": 0.9366,
      "step": 117
    },
    {
      "epoch": 0.2950691568336329,
      "grad_norm": 0.20380328595638275,
      "learning_rate": 0.00018104026845637585,
      "loss": 0.9729,
      "step": 118
    },
    {
      "epoch": 0.2975697429084942,
      "grad_norm": 0.20112350583076477,
      "learning_rate": 0.00018087248322147653,
      "loss": 0.9686,
      "step": 119
    },
    {
      "epoch": 0.30007032898335545,
      "grad_norm": 0.2018086016178131,
      "learning_rate": 0.00018070469798657718,
      "loss": 1.0412,
      "step": 120
    },
    {
      "epoch": 0.30257091505821676,
      "grad_norm": 0.20576363801956177,
      "learning_rate": 0.00018053691275167786,
      "loss": 0.9666,
      "step": 121
    },
    {
      "epoch": 0.30507150113307807,
      "grad_norm": 0.22615446150302887,
      "learning_rate": 0.00018036912751677852,
      "loss": 0.9518,
      "step": 122
    },
    {
      "epoch": 0.3075720872079394,
      "grad_norm": 0.19727525115013123,
      "learning_rate": 0.0001802013422818792,
      "loss": 1.0006,
      "step": 123
    },
    {
      "epoch": 0.31007267328280064,
      "grad_norm": 0.20703637599945068,
      "learning_rate": 0.00018003355704697988,
      "loss": 0.994,
      "step": 124
    },
    {
      "epoch": 0.31257325935766195,
      "grad_norm": 0.2170065939426422,
      "learning_rate": 0.00017986577181208056,
      "loss": 0.9449,
      "step": 125
    },
    {
      "epoch": 0.31507384543252326,
      "grad_norm": 0.21106544137001038,
      "learning_rate": 0.0001796979865771812,
      "loss": 0.999,
      "step": 126
    },
    {
      "epoch": 0.31757443150738457,
      "grad_norm": 0.20383739471435547,
      "learning_rate": 0.0001795302013422819,
      "loss": 0.9679,
      "step": 127
    },
    {
      "epoch": 0.3200750175822458,
      "grad_norm": 0.20005188882350922,
      "learning_rate": 0.00017936241610738257,
      "loss": 0.9361,
      "step": 128
    },
    {
      "epoch": 0.32257560365710714,
      "grad_norm": 0.21745333075523376,
      "learning_rate": 0.00017919463087248322,
      "loss": 0.9293,
      "step": 129
    },
    {
      "epoch": 0.32507618973196845,
      "grad_norm": 0.2078651785850525,
      "learning_rate": 0.0001790268456375839,
      "loss": 0.9523,
      "step": 130
    },
    {
      "epoch": 0.3275767758068297,
      "grad_norm": 0.18979056179523468,
      "learning_rate": 0.00017885906040268455,
      "loss": 0.9534,
      "step": 131
    },
    {
      "epoch": 0.330077361881691,
      "grad_norm": 0.20072820782661438,
      "learning_rate": 0.00017869127516778523,
      "loss": 0.9605,
      "step": 132
    },
    {
      "epoch": 0.3325779479565523,
      "grad_norm": 0.19807642698287964,
      "learning_rate": 0.0001785234899328859,
      "loss": 0.9626,
      "step": 133
    },
    {
      "epoch": 0.33507853403141363,
      "grad_norm": 0.20472458004951477,
      "learning_rate": 0.0001783557046979866,
      "loss": 0.9659,
      "step": 134
    },
    {
      "epoch": 0.3375791201062749,
      "grad_norm": 0.19827553629875183,
      "learning_rate": 0.00017818791946308727,
      "loss": 0.9452,
      "step": 135
    },
    {
      "epoch": 0.3400797061811362,
      "grad_norm": 0.21104063093662262,
      "learning_rate": 0.00017802013422818792,
      "loss": 0.9595,
      "step": 136
    },
    {
      "epoch": 0.3425802922559975,
      "grad_norm": 0.18921682238578796,
      "learning_rate": 0.0001778523489932886,
      "loss": 0.9619,
      "step": 137
    },
    {
      "epoch": 0.3450808783308588,
      "grad_norm": 0.2175590544939041,
      "learning_rate": 0.00017768456375838926,
      "loss": 0.9695,
      "step": 138
    },
    {
      "epoch": 0.3475814644057201,
      "grad_norm": 0.1978655904531479,
      "learning_rate": 0.00017751677852348994,
      "loss": 0.9493,
      "step": 139
    },
    {
      "epoch": 0.3500820504805814,
      "grad_norm": 0.19963012635707855,
      "learning_rate": 0.00017734899328859062,
      "loss": 0.9141,
      "step": 140
    },
    {
      "epoch": 0.3525826365554427,
      "grad_norm": 0.20079948008060455,
      "learning_rate": 0.0001771812080536913,
      "loss": 0.9649,
      "step": 141
    },
    {
      "epoch": 0.35508322263030395,
      "grad_norm": 0.19476771354675293,
      "learning_rate": 0.00017701342281879198,
      "loss": 0.9056,
      "step": 142
    },
    {
      "epoch": 0.35758380870516526,
      "grad_norm": 0.18434399366378784,
      "learning_rate": 0.00017684563758389263,
      "loss": 0.9166,
      "step": 143
    },
    {
      "epoch": 0.3600843947800266,
      "grad_norm": 0.20533886551856995,
      "learning_rate": 0.0001766778523489933,
      "loss": 0.974,
      "step": 144
    },
    {
      "epoch": 0.3625849808548879,
      "grad_norm": 0.2047143578529358,
      "learning_rate": 0.00017651006711409396,
      "loss": 0.9513,
      "step": 145
    },
    {
      "epoch": 0.36508556692974914,
      "grad_norm": 0.19077660143375397,
      "learning_rate": 0.00017634228187919464,
      "loss": 0.9358,
      "step": 146
    },
    {
      "epoch": 0.36758615300461045,
      "grad_norm": 0.21231941878795624,
      "learning_rate": 0.0001761744966442953,
      "loss": 0.9875,
      "step": 147
    },
    {
      "epoch": 0.37008673907947176,
      "grad_norm": 0.20398589968681335,
      "learning_rate": 0.00017600671140939597,
      "loss": 0.9638,
      "step": 148
    },
    {
      "epoch": 0.37258732515433307,
      "grad_norm": 0.1901940405368805,
      "learning_rate": 0.00017583892617449665,
      "loss": 0.954,
      "step": 149
    },
    {
      "epoch": 0.3750879112291943,
      "grad_norm": 0.19586050510406494,
      "learning_rate": 0.00017567114093959733,
      "loss": 0.943,
      "step": 150
    },
    {
      "epoch": 0.37758849730405564,
      "grad_norm": 0.20500780642032623,
      "learning_rate": 0.000175503355704698,
      "loss": 0.9939,
      "step": 151
    },
    {
      "epoch": 0.38008908337891695,
      "grad_norm": 0.2010958045721054,
      "learning_rate": 0.00017533557046979867,
      "loss": 0.9963,
      "step": 152
    },
    {
      "epoch": 0.3825896694537782,
      "grad_norm": 0.20818760991096497,
      "learning_rate": 0.00017516778523489935,
      "loss": 0.9368,
      "step": 153
    },
    {
      "epoch": 0.3850902555286395,
      "grad_norm": 0.20369277894496918,
      "learning_rate": 0.000175,
      "loss": 0.9901,
      "step": 154
    },
    {
      "epoch": 0.3875908416035008,
      "grad_norm": 0.20049050450325012,
      "learning_rate": 0.00017483221476510068,
      "loss": 0.9104,
      "step": 155
    },
    {
      "epoch": 0.39009142767836213,
      "grad_norm": 0.20531973242759705,
      "learning_rate": 0.00017466442953020136,
      "loss": 0.9193,
      "step": 156
    },
    {
      "epoch": 0.3925920137532234,
      "grad_norm": 0.19537755846977234,
      "learning_rate": 0.000174496644295302,
      "loss": 0.9368,
      "step": 157
    },
    {
      "epoch": 0.3950925998280847,
      "grad_norm": 0.21875996887683868,
      "learning_rate": 0.0001743288590604027,
      "loss": 0.9799,
      "step": 158
    },
    {
      "epoch": 0.397593185902946,
      "grad_norm": 0.21377162635326385,
      "learning_rate": 0.00017416107382550337,
      "loss": 1.0224,
      "step": 159
    },
    {
      "epoch": 0.4000937719778073,
      "grad_norm": 0.20617148280143738,
      "learning_rate": 0.00017399328859060405,
      "loss": 0.9825,
      "step": 160
    },
    {
      "epoch": 0.4025943580526686,
      "grad_norm": 0.19385607540607452,
      "learning_rate": 0.0001738255033557047,
      "loss": 0.9567,
      "step": 161
    },
    {
      "epoch": 0.4050949441275299,
      "grad_norm": 0.20452259480953217,
      "learning_rate": 0.00017365771812080538,
      "loss": 0.8854,
      "step": 162
    },
    {
      "epoch": 0.4075955302023912,
      "grad_norm": 0.20258085429668427,
      "learning_rate": 0.00017348993288590604,
      "loss": 1.0458,
      "step": 163
    },
    {
      "epoch": 0.41009611627725245,
      "grad_norm": 0.21564531326293945,
      "learning_rate": 0.00017332214765100671,
      "loss": 0.9514,
      "step": 164
    },
    {
      "epoch": 0.41259670235211376,
      "grad_norm": 0.21387049555778503,
      "learning_rate": 0.0001731543624161074,
      "loss": 1.0035,
      "step": 165
    },
    {
      "epoch": 0.4150972884269751,
      "grad_norm": 0.20146381855010986,
      "learning_rate": 0.00017298657718120805,
      "loss": 0.9247,
      "step": 166
    },
    {
      "epoch": 0.4175978745018364,
      "grad_norm": 0.20543105900287628,
      "learning_rate": 0.00017281879194630873,
      "loss": 0.9505,
      "step": 167
    },
    {
      "epoch": 0.42009846057669764,
      "grad_norm": 0.21827350556850433,
      "learning_rate": 0.0001726510067114094,
      "loss": 0.9993,
      "step": 168
    },
    {
      "epoch": 0.42259904665155895,
      "grad_norm": 0.22608278691768646,
      "learning_rate": 0.0001724832214765101,
      "loss": 0.9393,
      "step": 169
    },
    {
      "epoch": 0.42509963272642026,
      "grad_norm": 0.21495342254638672,
      "learning_rate": 0.00017231543624161074,
      "loss": 1.0455,
      "step": 170
    },
    {
      "epoch": 0.4276002188012816,
      "grad_norm": 0.21326063573360443,
      "learning_rate": 0.00017214765100671142,
      "loss": 1.017,
      "step": 171
    },
    {
      "epoch": 0.43010080487614283,
      "grad_norm": 0.2060144692659378,
      "learning_rate": 0.0001719798657718121,
      "loss": 0.9671,
      "step": 172
    },
    {
      "epoch": 0.43260139095100414,
      "grad_norm": 0.21247944235801697,
      "learning_rate": 0.00017181208053691275,
      "loss": 0.912,
      "step": 173
    },
    {
      "epoch": 0.43510197702586545,
      "grad_norm": 0.20313112437725067,
      "learning_rate": 0.00017164429530201343,
      "loss": 1.021,
      "step": 174
    },
    {
      "epoch": 0.43760256310072676,
      "grad_norm": 0.20316354930400848,
      "learning_rate": 0.00017147651006711408,
      "loss": 0.9542,
      "step": 175
    },
    {
      "epoch": 0.440103149175588,
      "grad_norm": 0.19503550231456757,
      "learning_rate": 0.0001713087248322148,
      "loss": 0.9495,
      "step": 176
    },
    {
      "epoch": 0.4426037352504493,
      "grad_norm": 0.19268807768821716,
      "learning_rate": 0.00017114093959731544,
      "loss": 0.9913,
      "step": 177
    },
    {
      "epoch": 0.44510432132531064,
      "grad_norm": 0.19619421660900116,
      "learning_rate": 0.00017097315436241612,
      "loss": 0.9136,
      "step": 178
    },
    {
      "epoch": 0.4476049074001719,
      "grad_norm": 0.21306179463863373,
      "learning_rate": 0.0001708053691275168,
      "loss": 0.9468,
      "step": 179
    },
    {
      "epoch": 0.4501054934750332,
      "grad_norm": 0.1926979422569275,
      "learning_rate": 0.00017063758389261746,
      "loss": 0.9138,
      "step": 180
    },
    {
      "epoch": 0.4526060795498945,
      "grad_norm": 0.20351314544677734,
      "learning_rate": 0.00017046979865771814,
      "loss": 0.9424,
      "step": 181
    },
    {
      "epoch": 0.4551066656247558,
      "grad_norm": 0.20273157954216003,
      "learning_rate": 0.0001703020134228188,
      "loss": 0.9901,
      "step": 182
    },
    {
      "epoch": 0.4576072516996171,
      "grad_norm": 0.19532570242881775,
      "learning_rate": 0.00017013422818791947,
      "loss": 0.9278,
      "step": 183
    },
    {
      "epoch": 0.4601078377744784,
      "grad_norm": 0.2106495201587677,
      "learning_rate": 0.00016996644295302012,
      "loss": 0.9103,
      "step": 184
    },
    {
      "epoch": 0.4626084238493397,
      "grad_norm": 0.19396382570266724,
      "learning_rate": 0.00016979865771812083,
      "loss": 0.9493,
      "step": 185
    },
    {
      "epoch": 0.465109009924201,
      "grad_norm": 0.19334650039672852,
      "learning_rate": 0.00016963087248322148,
      "loss": 0.9813,
      "step": 186
    },
    {
      "epoch": 0.46760959599906227,
      "grad_norm": 0.20727260410785675,
      "learning_rate": 0.00016946308724832216,
      "loss": 0.9721,
      "step": 187
    },
    {
      "epoch": 0.4701101820739236,
      "grad_norm": 0.1958143711090088,
      "learning_rate": 0.00016929530201342284,
      "loss": 0.975,
      "step": 188
    },
    {
      "epoch": 0.4726107681487849,
      "grad_norm": 0.2058304399251938,
      "learning_rate": 0.0001691275167785235,
      "loss": 0.9718,
      "step": 189
    },
    {
      "epoch": 0.47511135422364614,
      "grad_norm": 0.19323155283927917,
      "learning_rate": 0.00016895973154362417,
      "loss": 0.933,
      "step": 190
    },
    {
      "epoch": 0.47761194029850745,
      "grad_norm": 0.2087579071521759,
      "learning_rate": 0.00016879194630872483,
      "loss": 0.9643,
      "step": 191
    },
    {
      "epoch": 0.48011252637336876,
      "grad_norm": 0.19288691878318787,
      "learning_rate": 0.0001686241610738255,
      "loss": 0.9452,
      "step": 192
    },
    {
      "epoch": 0.4826131124482301,
      "grad_norm": 0.20016451179981232,
      "learning_rate": 0.00016845637583892619,
      "loss": 1.0201,
      "step": 193
    },
    {
      "epoch": 0.48511369852309133,
      "grad_norm": 0.20064382255077362,
      "learning_rate": 0.00016828859060402686,
      "loss": 0.9329,
      "step": 194
    },
    {
      "epoch": 0.48761428459795264,
      "grad_norm": 0.20682549476623535,
      "learning_rate": 0.00016812080536912754,
      "loss": 0.9067,
      "step": 195
    },
    {
      "epoch": 0.49011487067281395,
      "grad_norm": 0.2095707803964615,
      "learning_rate": 0.0001679530201342282,
      "loss": 0.964,
      "step": 196
    },
    {
      "epoch": 0.49261545674767526,
      "grad_norm": 0.19708895683288574,
      "learning_rate": 0.00016778523489932888,
      "loss": 0.9555,
      "step": 197
    },
    {
      "epoch": 0.4951160428225365,
      "grad_norm": 0.21263785660266876,
      "learning_rate": 0.00016761744966442953,
      "loss": 0.9607,
      "step": 198
    },
    {
      "epoch": 0.49761662889739783,
      "grad_norm": 0.2375573068857193,
      "learning_rate": 0.0001674496644295302,
      "loss": 0.93,
      "step": 199
    },
    {
      "epoch": 0.5001172149722591,
      "grad_norm": 0.19389759004116058,
      "learning_rate": 0.00016728187919463086,
      "loss": 0.9339,
      "step": 200
    },
    {
      "epoch": 0.5026178010471204,
      "grad_norm": 0.21175242960453033,
      "learning_rate": 0.00016711409395973154,
      "loss": 0.9171,
      "step": 201
    },
    {
      "epoch": 0.5051183871219818,
      "grad_norm": 0.21076923608779907,
      "learning_rate": 0.00016694630872483222,
      "loss": 0.872,
      "step": 202
    },
    {
      "epoch": 0.507618973196843,
      "grad_norm": 0.20474554598331451,
      "learning_rate": 0.0001667785234899329,
      "loss": 0.9452,
      "step": 203
    },
    {
      "epoch": 0.5101195592717043,
      "grad_norm": 0.21046273410320282,
      "learning_rate": 0.00016661073825503358,
      "loss": 0.9573,
      "step": 204
    },
    {
      "epoch": 0.5126201453465656,
      "grad_norm": 0.2026781141757965,
      "learning_rate": 0.00016644295302013423,
      "loss": 0.9899,
      "step": 205
    },
    {
      "epoch": 0.5151207314214269,
      "grad_norm": 0.22526352107524872,
      "learning_rate": 0.00016627516778523491,
      "loss": 0.9826,
      "step": 206
    },
    {
      "epoch": 0.5176213174962881,
      "grad_norm": 0.20340263843536377,
      "learning_rate": 0.00016610738255033557,
      "loss": 0.9356,
      "step": 207
    },
    {
      "epoch": 0.5201219035711495,
      "grad_norm": 0.1983516812324524,
      "learning_rate": 0.00016593959731543625,
      "loss": 0.9663,
      "step": 208
    },
    {
      "epoch": 0.5226224896460108,
      "grad_norm": 0.19852115213871002,
      "learning_rate": 0.00016577181208053693,
      "loss": 0.97,
      "step": 209
    },
    {
      "epoch": 0.5251230757208721,
      "grad_norm": 0.20500719547271729,
      "learning_rate": 0.00016560402684563758,
      "loss": 0.9304,
      "step": 210
    },
    {
      "epoch": 0.5276236617957334,
      "grad_norm": 0.2010101079940796,
      "learning_rate": 0.00016543624161073829,
      "loss": 0.9102,
      "step": 211
    },
    {
      "epoch": 0.5301242478705946,
      "grad_norm": 0.21323886513710022,
      "learning_rate": 0.00016526845637583894,
      "loss": 0.9794,
      "step": 212
    },
    {
      "epoch": 0.532624833945456,
      "grad_norm": 0.20126739144325256,
      "learning_rate": 0.00016510067114093962,
      "loss": 0.9326,
      "step": 213
    },
    {
      "epoch": 0.5351254200203173,
      "grad_norm": 0.2181158810853958,
      "learning_rate": 0.00016493288590604027,
      "loss": 0.9925,
      "step": 214
    },
    {
      "epoch": 0.5376260060951785,
      "grad_norm": 0.2002563178539276,
      "learning_rate": 0.00016476510067114095,
      "loss": 0.9283,
      "step": 215
    },
    {
      "epoch": 0.5401265921700399,
      "grad_norm": 0.1901605725288391,
      "learning_rate": 0.0001645973154362416,
      "loss": 0.9481,
      "step": 216
    },
    {
      "epoch": 0.5426271782449011,
      "grad_norm": 0.20211246609687805,
      "learning_rate": 0.00016442953020134228,
      "loss": 0.9343,
      "step": 217
    },
    {
      "epoch": 0.5451277643197624,
      "grad_norm": 0.19748587906360626,
      "learning_rate": 0.00016426174496644296,
      "loss": 0.9967,
      "step": 218
    },
    {
      "epoch": 0.5476283503946238,
      "grad_norm": 0.2044479250907898,
      "learning_rate": 0.00016409395973154362,
      "loss": 0.9436,
      "step": 219
    },
    {
      "epoch": 0.550128936469485,
      "grad_norm": 0.1923314779996872,
      "learning_rate": 0.00016392617449664432,
      "loss": 0.9535,
      "step": 220
    },
    {
      "epoch": 0.5526295225443464,
      "grad_norm": 0.1981159895658493,
      "learning_rate": 0.00016375838926174498,
      "loss": 0.9031,
      "step": 221
    },
    {
      "epoch": 0.5551301086192076,
      "grad_norm": 0.19014570116996765,
      "learning_rate": 0.00016359060402684566,
      "loss": 0.9497,
      "step": 222
    },
    {
      "epoch": 0.5576306946940689,
      "grad_norm": 0.19516299664974213,
      "learning_rate": 0.0001634228187919463,
      "loss": 0.9481,
      "step": 223
    },
    {
      "epoch": 0.5601312807689303,
      "grad_norm": 0.2148059755563736,
      "learning_rate": 0.000163255033557047,
      "loss": 0.9571,
      "step": 224
    },
    {
      "epoch": 0.5626318668437915,
      "grad_norm": 0.20576442778110504,
      "learning_rate": 0.00016308724832214767,
      "loss": 1.0018,
      "step": 225
    },
    {
      "epoch": 0.5651324529186528,
      "grad_norm": 0.20371298491954803,
      "learning_rate": 0.00016291946308724832,
      "loss": 0.8954,
      "step": 226
    },
    {
      "epoch": 0.5676330389935141,
      "grad_norm": 0.1865856647491455,
      "learning_rate": 0.000162751677852349,
      "loss": 0.9592,
      "step": 227
    },
    {
      "epoch": 0.5701336250683754,
      "grad_norm": 0.20932011306285858,
      "learning_rate": 0.00016258389261744965,
      "loss": 0.9412,
      "step": 228
    },
    {
      "epoch": 0.5726342111432366,
      "grad_norm": 0.2131514698266983,
      "learning_rate": 0.00016241610738255036,
      "loss": 0.9413,
      "step": 229
    },
    {
      "epoch": 0.575134797218098,
      "grad_norm": 0.19242137670516968,
      "learning_rate": 0.000162248322147651,
      "loss": 0.9244,
      "step": 230
    },
    {
      "epoch": 0.5776353832929593,
      "grad_norm": 0.20453810691833496,
      "learning_rate": 0.0001620805369127517,
      "loss": 0.9972,
      "step": 231
    },
    {
      "epoch": 0.5801359693678206,
      "grad_norm": 0.19789357483386993,
      "learning_rate": 0.00016191275167785237,
      "loss": 0.9411,
      "step": 232
    },
    {
      "epoch": 0.5826365554426819,
      "grad_norm": 0.1875084787607193,
      "learning_rate": 0.00016174496644295302,
      "loss": 0.8877,
      "step": 233
    },
    {
      "epoch": 0.5851371415175431,
      "grad_norm": 0.21921932697296143,
      "learning_rate": 0.0001615771812080537,
      "loss": 0.8957,
      "step": 234
    },
    {
      "epoch": 0.5876377275924045,
      "grad_norm": 0.19880889356136322,
      "learning_rate": 0.00016140939597315436,
      "loss": 1.0228,
      "step": 235
    },
    {
      "epoch": 0.5901383136672658,
      "grad_norm": 0.19592322409152985,
      "learning_rate": 0.00016124161073825504,
      "loss": 0.9665,
      "step": 236
    },
    {
      "epoch": 0.592638899742127,
      "grad_norm": 0.19552145898342133,
      "learning_rate": 0.0001610738255033557,
      "loss": 0.8964,
      "step": 237
    },
    {
      "epoch": 0.5951394858169884,
      "grad_norm": 0.20831383764743805,
      "learning_rate": 0.0001609060402684564,
      "loss": 0.9962,
      "step": 238
    },
    {
      "epoch": 0.5976400718918496,
      "grad_norm": 0.20157143473625183,
      "learning_rate": 0.00016073825503355705,
      "loss": 0.9736,
      "step": 239
    },
    {
      "epoch": 0.6001406579667109,
      "grad_norm": 0.19122959673404694,
      "learning_rate": 0.00016057046979865773,
      "loss": 0.9004,
      "step": 240
    },
    {
      "epoch": 0.6026412440415723,
      "grad_norm": 0.19804859161376953,
      "learning_rate": 0.0001604026845637584,
      "loss": 0.9438,
      "step": 241
    },
    {
      "epoch": 0.6051418301164335,
      "grad_norm": 0.20546962320804596,
      "learning_rate": 0.00016023489932885906,
      "loss": 0.9389,
      "step": 242
    },
    {
      "epoch": 0.6076424161912949,
      "grad_norm": 0.20515991747379303,
      "learning_rate": 0.00016006711409395974,
      "loss": 0.9325,
      "step": 243
    },
    {
      "epoch": 0.6101430022661561,
      "grad_norm": 0.20005853474140167,
      "learning_rate": 0.0001598993288590604,
      "loss": 0.9827,
      "step": 244
    },
    {
      "epoch": 0.6126435883410174,
      "grad_norm": 0.22935104370117188,
      "learning_rate": 0.00015973154362416107,
      "loss": 0.9733,
      "step": 245
    },
    {
      "epoch": 0.6151441744158788,
      "grad_norm": 0.19898930191993713,
      "learning_rate": 0.00015956375838926175,
      "loss": 0.976,
      "step": 246
    },
    {
      "epoch": 0.61764476049074,
      "grad_norm": 0.19529736042022705,
      "learning_rate": 0.00015939597315436243,
      "loss": 0.9177,
      "step": 247
    },
    {
      "epoch": 0.6201453465656013,
      "grad_norm": 0.2278802990913391,
      "learning_rate": 0.0001592281879194631,
      "loss": 0.9902,
      "step": 248
    },
    {
      "epoch": 0.6226459326404626,
      "grad_norm": 0.21218013763427734,
      "learning_rate": 0.00015906040268456377,
      "loss": 0.9617,
      "step": 249
    },
    {
      "epoch": 0.6251465187153239,
      "grad_norm": 0.20722109079360962,
      "learning_rate": 0.00015889261744966445,
      "loss": 0.9364,
      "step": 250
    },
    {
      "epoch": 0.6276471047901852,
      "grad_norm": 0.21361340582370758,
      "learning_rate": 0.0001587248322147651,
      "loss": 0.9022,
      "step": 251
    },
    {
      "epoch": 0.6301476908650465,
      "grad_norm": 0.2029501050710678,
      "learning_rate": 0.00015855704697986578,
      "loss": 0.9071,
      "step": 252
    },
    {
      "epoch": 0.6326482769399078,
      "grad_norm": 0.21769894659519196,
      "learning_rate": 0.00015838926174496643,
      "loss": 0.9579,
      "step": 253
    },
    {
      "epoch": 0.6351488630147691,
      "grad_norm": 0.2267335206270218,
      "learning_rate": 0.0001582214765100671,
      "loss": 0.9522,
      "step": 254
    },
    {
      "epoch": 0.6376494490896304,
      "grad_norm": 0.20004138350486755,
      "learning_rate": 0.0001580536912751678,
      "loss": 0.9873,
      "step": 255
    },
    {
      "epoch": 0.6401500351644916,
      "grad_norm": 0.1902337670326233,
      "learning_rate": 0.00015788590604026847,
      "loss": 0.9001,
      "step": 256
    },
    {
      "epoch": 0.642650621239353,
      "grad_norm": 0.2013217657804489,
      "learning_rate": 0.00015771812080536915,
      "loss": 0.9644,
      "step": 257
    },
    {
      "epoch": 0.6451512073142143,
      "grad_norm": 0.1940159648656845,
      "learning_rate": 0.0001575503355704698,
      "loss": 0.9844,
      "step": 258
    },
    {
      "epoch": 0.6476517933890755,
      "grad_norm": 0.20359578728675842,
      "learning_rate": 0.00015738255033557048,
      "loss": 0.9652,
      "step": 259
    },
    {
      "epoch": 0.6501523794639369,
      "grad_norm": 0.18913763761520386,
      "learning_rate": 0.00015721476510067114,
      "loss": 0.9698,
      "step": 260
    },
    {
      "epoch": 0.6526529655387981,
      "grad_norm": 0.19329224526882172,
      "learning_rate": 0.00015704697986577181,
      "loss": 0.9558,
      "step": 261
    },
    {
      "epoch": 0.6551535516136594,
      "grad_norm": 0.20145884156227112,
      "learning_rate": 0.0001568791946308725,
      "loss": 1.0232,
      "step": 262
    },
    {
      "epoch": 0.6576541376885208,
      "grad_norm": 0.18802523612976074,
      "learning_rate": 0.00015671140939597315,
      "loss": 0.9492,
      "step": 263
    },
    {
      "epoch": 0.660154723763382,
      "grad_norm": 0.19531258940696716,
      "learning_rate": 0.00015654362416107385,
      "loss": 0.9791,
      "step": 264
    },
    {
      "epoch": 0.6626553098382434,
      "grad_norm": 0.1917187124490738,
      "learning_rate": 0.0001563758389261745,
      "loss": 0.9741,
      "step": 265
    },
    {
      "epoch": 0.6651558959131046,
      "grad_norm": 0.19565711915493011,
      "learning_rate": 0.0001562080536912752,
      "loss": 0.9876,
      "step": 266
    },
    {
      "epoch": 0.6676564819879659,
      "grad_norm": 0.19605979323387146,
      "learning_rate": 0.00015604026845637584,
      "loss": 0.8845,
      "step": 267
    },
    {
      "epoch": 0.6701570680628273,
      "grad_norm": 0.20349417626857758,
      "learning_rate": 0.00015587248322147652,
      "loss": 0.9595,
      "step": 268
    },
    {
      "epoch": 0.6726576541376885,
      "grad_norm": 0.19674451649188995,
      "learning_rate": 0.0001557046979865772,
      "loss": 0.9113,
      "step": 269
    },
    {
      "epoch": 0.6751582402125498,
      "grad_norm": 0.19608086347579956,
      "learning_rate": 0.00015553691275167785,
      "loss": 0.8849,
      "step": 270
    },
    {
      "epoch": 0.6776588262874111,
      "grad_norm": 0.1995520442724228,
      "learning_rate": 0.00015536912751677853,
      "loss": 0.9341,
      "step": 271
    },
    {
      "epoch": 0.6801594123622724,
      "grad_norm": 0.20707178115844727,
      "learning_rate": 0.00015520134228187918,
      "loss": 0.9262,
      "step": 272
    },
    {
      "epoch": 0.6826599984371337,
      "grad_norm": 0.20216511189937592,
      "learning_rate": 0.0001550335570469799,
      "loss": 0.9162,
      "step": 273
    },
    {
      "epoch": 0.685160584511995,
      "grad_norm": 0.19384877383708954,
      "learning_rate": 0.00015486577181208054,
      "loss": 0.9264,
      "step": 274
    },
    {
      "epoch": 0.6876611705868563,
      "grad_norm": 0.21822841465473175,
      "learning_rate": 0.00015469798657718122,
      "loss": 0.9299,
      "step": 275
    },
    {
      "epoch": 0.6901617566617176,
      "grad_norm": 0.195476695895195,
      "learning_rate": 0.00015453020134228188,
      "loss": 0.9246,
      "step": 276
    },
    {
      "epoch": 0.6926623427365789,
      "grad_norm": 0.2062695026397705,
      "learning_rate": 0.00015436241610738256,
      "loss": 0.9143,
      "step": 277
    },
    {
      "epoch": 0.6951629288114402,
      "grad_norm": 0.20120318233966827,
      "learning_rate": 0.00015419463087248324,
      "loss": 0.9244,
      "step": 278
    },
    {
      "epoch": 0.6976635148863015,
      "grad_norm": 0.19195373356342316,
      "learning_rate": 0.0001540268456375839,
      "loss": 0.9629,
      "step": 279
    },
    {
      "epoch": 0.7001641009611628,
      "grad_norm": 0.20471717417240143,
      "learning_rate": 0.00015385906040268457,
      "loss": 0.9761,
      "step": 280
    },
    {
      "epoch": 0.702664687036024,
      "grad_norm": 0.192673459649086,
      "learning_rate": 0.00015369127516778522,
      "loss": 0.9769,
      "step": 281
    },
    {
      "epoch": 0.7051652731108854,
      "grad_norm": 0.18674695491790771,
      "learning_rate": 0.00015352348993288593,
      "loss": 0.908,
      "step": 282
    },
    {
      "epoch": 0.7076658591857466,
      "grad_norm": 0.2033309042453766,
      "learning_rate": 0.00015335570469798658,
      "loss": 0.9619,
      "step": 283
    },
    {
      "epoch": 0.7101664452606079,
      "grad_norm": 0.20086367428302765,
      "learning_rate": 0.00015318791946308726,
      "loss": 0.9986,
      "step": 284
    },
    {
      "epoch": 0.7126670313354693,
      "grad_norm": 0.197890967130661,
      "learning_rate": 0.00015302013422818794,
      "loss": 0.9179,
      "step": 285
    },
    {
      "epoch": 0.7151676174103305,
      "grad_norm": 0.19057410955429077,
      "learning_rate": 0.0001528523489932886,
      "loss": 0.956,
      "step": 286
    },
    {
      "epoch": 0.7176682034851919,
      "grad_norm": 0.1913488209247589,
      "learning_rate": 0.00015268456375838927,
      "loss": 0.8821,
      "step": 287
    },
    {
      "epoch": 0.7201687895600531,
      "grad_norm": 0.19540366530418396,
      "learning_rate": 0.00015251677852348993,
      "loss": 0.8933,
      "step": 288
    },
    {
      "epoch": 0.7226693756349144,
      "grad_norm": 0.20779870450496674,
      "learning_rate": 0.0001523489932885906,
      "loss": 0.9556,
      "step": 289
    },
    {
      "epoch": 0.7251699617097758,
      "grad_norm": 0.19707651436328888,
      "learning_rate": 0.00015218120805369129,
      "loss": 0.9283,
      "step": 290
    },
    {
      "epoch": 0.727670547784637,
      "grad_norm": 0.19629661738872528,
      "learning_rate": 0.00015201342281879196,
      "loss": 0.9423,
      "step": 291
    },
    {
      "epoch": 0.7301711338594983,
      "grad_norm": 0.19412437081336975,
      "learning_rate": 0.00015184563758389262,
      "loss": 0.9046,
      "step": 292
    },
    {
      "epoch": 0.7326717199343596,
      "grad_norm": 0.19544045627117157,
      "learning_rate": 0.0001516778523489933,
      "loss": 0.8976,
      "step": 293
    },
    {
      "epoch": 0.7351723060092209,
      "grad_norm": 0.19209088385105133,
      "learning_rate": 0.00015151006711409398,
      "loss": 0.9031,
      "step": 294
    },
    {
      "epoch": 0.7376728920840822,
      "grad_norm": 0.20053426921367645,
      "learning_rate": 0.00015134228187919463,
      "loss": 0.9324,
      "step": 295
    },
    {
      "epoch": 0.7401734781589435,
      "grad_norm": 0.2002066671848297,
      "learning_rate": 0.0001511744966442953,
      "loss": 0.995,
      "step": 296
    },
    {
      "epoch": 0.7426740642338048,
      "grad_norm": 0.1972004473209381,
      "learning_rate": 0.00015100671140939596,
      "loss": 0.9182,
      "step": 297
    },
    {
      "epoch": 0.7451746503086661,
      "grad_norm": 0.19501295685768127,
      "learning_rate": 0.00015083892617449664,
      "loss": 0.9431,
      "step": 298
    },
    {
      "epoch": 0.7476752363835274,
      "grad_norm": 0.20371028780937195,
      "learning_rate": 0.00015067114093959732,
      "loss": 0.9059,
      "step": 299
    },
    {
      "epoch": 0.7501758224583887,
      "grad_norm": 0.23006804287433624,
      "learning_rate": 0.000150503355704698,
      "loss": 0.9876,
      "step": 300
    },
    {
      "epoch": 0.75267640853325,
      "grad_norm": 0.18891564011573792,
      "learning_rate": 0.00015033557046979868,
      "loss": 0.9465,
      "step": 301
    },
    {
      "epoch": 0.7551769946081113,
      "grad_norm": 0.1992032378911972,
      "learning_rate": 0.00015016778523489933,
      "loss": 0.939,
      "step": 302
    },
    {
      "epoch": 0.7576775806829725,
      "grad_norm": 0.20672324299812317,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.8997,
      "step": 303
    },
    {
      "epoch": 0.7601781667578339,
      "grad_norm": 0.20514875650405884,
      "learning_rate": 0.00014983221476510067,
      "loss": 0.9027,
      "step": 304
    },
    {
      "epoch": 0.7626787528326952,
      "grad_norm": 0.19662059843540192,
      "learning_rate": 0.00014966442953020135,
      "loss": 0.9504,
      "step": 305
    },
    {
      "epoch": 0.7651793389075564,
      "grad_norm": 0.19113412499427795,
      "learning_rate": 0.00014949664429530203,
      "loss": 0.8445,
      "step": 306
    },
    {
      "epoch": 0.7676799249824178,
      "grad_norm": 0.20623773336410522,
      "learning_rate": 0.00014932885906040268,
      "loss": 0.9669,
      "step": 307
    },
    {
      "epoch": 0.770180511057279,
      "grad_norm": 0.20261040329933167,
      "learning_rate": 0.00014916107382550339,
      "loss": 0.9047,
      "step": 308
    },
    {
      "epoch": 0.7726810971321404,
      "grad_norm": 0.19355683028697968,
      "learning_rate": 0.00014899328859060404,
      "loss": 0.9422,
      "step": 309
    },
    {
      "epoch": 0.7751816832070016,
      "grad_norm": 0.21379676461219788,
      "learning_rate": 0.00014882550335570472,
      "loss": 0.9782,
      "step": 310
    },
    {
      "epoch": 0.7776822692818629,
      "grad_norm": 0.20317813754081726,
      "learning_rate": 0.00014865771812080537,
      "loss": 0.931,
      "step": 311
    },
    {
      "epoch": 0.7801828553567243,
      "grad_norm": 0.20362474024295807,
      "learning_rate": 0.00014848993288590605,
      "loss": 0.8662,
      "step": 312
    },
    {
      "epoch": 0.7826834414315855,
      "grad_norm": 0.20510531961917877,
      "learning_rate": 0.0001483221476510067,
      "loss": 1.0119,
      "step": 313
    },
    {
      "epoch": 0.7851840275064468,
      "grad_norm": 0.19395427405834198,
      "learning_rate": 0.00014815436241610738,
      "loss": 0.9228,
      "step": 314
    },
    {
      "epoch": 0.7876846135813081,
      "grad_norm": 0.1922769993543625,
      "learning_rate": 0.00014798657718120806,
      "loss": 0.9197,
      "step": 315
    },
    {
      "epoch": 0.7901851996561694,
      "grad_norm": 0.2138831913471222,
      "learning_rate": 0.00014781879194630872,
      "loss": 0.9551,
      "step": 316
    },
    {
      "epoch": 0.7926857857310307,
      "grad_norm": 0.1988006830215454,
      "learning_rate": 0.00014765100671140942,
      "loss": 0.9624,
      "step": 317
    },
    {
      "epoch": 0.795186371805892,
      "grad_norm": 0.19090843200683594,
      "learning_rate": 0.00014748322147651008,
      "loss": 0.9382,
      "step": 318
    },
    {
      "epoch": 0.7976869578807533,
      "grad_norm": 0.19148418307304382,
      "learning_rate": 0.00014731543624161076,
      "loss": 0.9222,
      "step": 319
    },
    {
      "epoch": 0.8001875439556146,
      "grad_norm": 0.19201642274856567,
      "learning_rate": 0.0001471476510067114,
      "loss": 0.9356,
      "step": 320
    },
    {
      "epoch": 0.8026881300304759,
      "grad_norm": 0.18535450100898743,
      "learning_rate": 0.0001469798657718121,
      "loss": 0.9196,
      "step": 321
    },
    {
      "epoch": 0.8051887161053372,
      "grad_norm": 0.19076795876026154,
      "learning_rate": 0.00014681208053691277,
      "loss": 0.9523,
      "step": 322
    },
    {
      "epoch": 0.8076893021801985,
      "grad_norm": 0.2030184417963028,
      "learning_rate": 0.00014664429530201342,
      "loss": 0.9695,
      "step": 323
    },
    {
      "epoch": 0.8101898882550598,
      "grad_norm": 0.18903104960918427,
      "learning_rate": 0.0001464765100671141,
      "loss": 0.9315,
      "step": 324
    },
    {
      "epoch": 0.812690474329921,
      "grad_norm": 0.18826857209205627,
      "learning_rate": 0.00014630872483221478,
      "loss": 0.9309,
      "step": 325
    },
    {
      "epoch": 0.8151910604047824,
      "grad_norm": 0.1963105946779251,
      "learning_rate": 0.00014614093959731546,
      "loss": 0.8993,
      "step": 326
    },
    {
      "epoch": 0.8176916464796437,
      "grad_norm": 0.20250087976455688,
      "learning_rate": 0.0001459731543624161,
      "loss": 0.9275,
      "step": 327
    },
    {
      "epoch": 0.8201922325545049,
      "grad_norm": 0.20003145933151245,
      "learning_rate": 0.0001458053691275168,
      "loss": 0.9373,
      "step": 328
    },
    {
      "epoch": 0.8226928186293663,
      "grad_norm": 0.18792639672756195,
      "learning_rate": 0.00014563758389261744,
      "loss": 0.861,
      "step": 329
    },
    {
      "epoch": 0.8251934047042275,
      "grad_norm": 0.19464413821697235,
      "learning_rate": 0.00014546979865771812,
      "loss": 0.9148,
      "step": 330
    },
    {
      "epoch": 0.8276939907790889,
      "grad_norm": 0.19977621734142303,
      "learning_rate": 0.0001453020134228188,
      "loss": 0.9171,
      "step": 331
    },
    {
      "epoch": 0.8301945768539502,
      "grad_norm": 0.20777297019958496,
      "learning_rate": 0.00014513422818791946,
      "loss": 0.9772,
      "step": 332
    },
    {
      "epoch": 0.8326951629288114,
      "grad_norm": 0.2004861682653427,
      "learning_rate": 0.00014496644295302014,
      "loss": 0.9501,
      "step": 333
    },
    {
      "epoch": 0.8351957490036728,
      "grad_norm": 0.19017265737056732,
      "learning_rate": 0.00014479865771812082,
      "loss": 0.8614,
      "step": 334
    },
    {
      "epoch": 0.837696335078534,
      "grad_norm": 0.20576266944408417,
      "learning_rate": 0.0001446308724832215,
      "loss": 0.9464,
      "step": 335
    },
    {
      "epoch": 0.8401969211533953,
      "grad_norm": 0.2054765373468399,
      "learning_rate": 0.00014446308724832215,
      "loss": 0.9268,
      "step": 336
    },
    {
      "epoch": 0.8426975072282566,
      "grad_norm": 0.19856566190719604,
      "learning_rate": 0.00014429530201342283,
      "loss": 0.9044,
      "step": 337
    },
    {
      "epoch": 0.8451980933031179,
      "grad_norm": 0.20033764839172363,
      "learning_rate": 0.0001441275167785235,
      "loss": 0.9379,
      "step": 338
    },
    {
      "epoch": 0.8476986793779792,
      "grad_norm": 0.19791364669799805,
      "learning_rate": 0.00014395973154362416,
      "loss": 0.8634,
      "step": 339
    },
    {
      "epoch": 0.8501992654528405,
      "grad_norm": 0.19763191044330597,
      "learning_rate": 0.00014379194630872484,
      "loss": 0.9071,
      "step": 340
    },
    {
      "epoch": 0.8526998515277018,
      "grad_norm": 0.2084035873413086,
      "learning_rate": 0.0001436241610738255,
      "loss": 0.9449,
      "step": 341
    },
    {
      "epoch": 0.8552004376025631,
      "grad_norm": 0.20290718972682953,
      "learning_rate": 0.00014345637583892617,
      "loss": 0.9239,
      "step": 342
    },
    {
      "epoch": 0.8577010236774244,
      "grad_norm": 0.20317819714546204,
      "learning_rate": 0.00014328859060402685,
      "loss": 0.9065,
      "step": 343
    },
    {
      "epoch": 0.8602016097522857,
      "grad_norm": 0.19348326325416565,
      "learning_rate": 0.00014312080536912753,
      "loss": 0.8981,
      "step": 344
    },
    {
      "epoch": 0.862702195827147,
      "grad_norm": 0.20921850204467773,
      "learning_rate": 0.00014295302013422819,
      "loss": 0.8473,
      "step": 345
    },
    {
      "epoch": 0.8652027819020083,
      "grad_norm": 0.1959138959646225,
      "learning_rate": 0.00014278523489932887,
      "loss": 0.9086,
      "step": 346
    },
    {
      "epoch": 0.8677033679768695,
      "grad_norm": 0.18429264426231384,
      "learning_rate": 0.00014261744966442955,
      "loss": 0.9492,
      "step": 347
    },
    {
      "epoch": 0.8702039540517309,
      "grad_norm": 0.19408418238162994,
      "learning_rate": 0.0001424496644295302,
      "loss": 0.9161,
      "step": 348
    },
    {
      "epoch": 0.8727045401265922,
      "grad_norm": 0.19348210096359253,
      "learning_rate": 0.00014228187919463088,
      "loss": 0.8937,
      "step": 349
    },
    {
      "epoch": 0.8752051262014535,
      "grad_norm": 0.20142613351345062,
      "learning_rate": 0.00014211409395973153,
      "loss": 0.928,
      "step": 350
    },
    {
      "epoch": 0.8777057122763148,
      "grad_norm": 0.19699464738368988,
      "learning_rate": 0.0001419463087248322,
      "loss": 0.9856,
      "step": 351
    },
    {
      "epoch": 0.880206298351176,
      "grad_norm": 0.19020123779773712,
      "learning_rate": 0.0001417785234899329,
      "loss": 0.9221,
      "step": 352
    },
    {
      "epoch": 0.8827068844260374,
      "grad_norm": 0.18610498309135437,
      "learning_rate": 0.00014161073825503357,
      "loss": 0.8846,
      "step": 353
    },
    {
      "epoch": 0.8852074705008987,
      "grad_norm": 0.20566537976264954,
      "learning_rate": 0.00014144295302013425,
      "loss": 0.9766,
      "step": 354
    },
    {
      "epoch": 0.8877080565757599,
      "grad_norm": 0.18680301308631897,
      "learning_rate": 0.0001412751677852349,
      "loss": 0.8741,
      "step": 355
    },
    {
      "epoch": 0.8902086426506213,
      "grad_norm": 0.19031471014022827,
      "learning_rate": 0.00014110738255033558,
      "loss": 0.9063,
      "step": 356
    },
    {
      "epoch": 0.8927092287254825,
      "grad_norm": 0.18606281280517578,
      "learning_rate": 0.00014093959731543624,
      "loss": 0.9157,
      "step": 357
    },
    {
      "epoch": 0.8952098148003438,
      "grad_norm": 0.19429543614387512,
      "learning_rate": 0.00014077181208053691,
      "loss": 0.9557,
      "step": 358
    },
    {
      "epoch": 0.8977104008752052,
      "grad_norm": 0.205494686961174,
      "learning_rate": 0.0001406040268456376,
      "loss": 0.9504,
      "step": 359
    },
    {
      "epoch": 0.9002109869500664,
      "grad_norm": 0.21151868999004364,
      "learning_rate": 0.00014043624161073827,
      "loss": 0.9404,
      "step": 360
    },
    {
      "epoch": 0.9027115730249278,
      "grad_norm": 0.19715413451194763,
      "learning_rate": 0.00014026845637583895,
      "loss": 0.9368,
      "step": 361
    },
    {
      "epoch": 0.905212159099789,
      "grad_norm": 0.20190200209617615,
      "learning_rate": 0.0001401006711409396,
      "loss": 0.8945,
      "step": 362
    },
    {
      "epoch": 0.9077127451746503,
      "grad_norm": 0.19868037104606628,
      "learning_rate": 0.0001399328859060403,
      "loss": 0.914,
      "step": 363
    },
    {
      "epoch": 0.9102133312495116,
      "grad_norm": 0.1939004808664322,
      "learning_rate": 0.00013976510067114094,
      "loss": 0.9319,
      "step": 364
    },
    {
      "epoch": 0.9127139173243729,
      "grad_norm": 0.21012766659259796,
      "learning_rate": 0.00013959731543624162,
      "loss": 0.9357,
      "step": 365
    },
    {
      "epoch": 0.9152145033992342,
      "grad_norm": 0.19320148229599,
      "learning_rate": 0.00013942953020134227,
      "loss": 0.9171,
      "step": 366
    },
    {
      "epoch": 0.9177150894740955,
      "grad_norm": 0.19462816417217255,
      "learning_rate": 0.00013926174496644295,
      "loss": 0.8754,
      "step": 367
    },
    {
      "epoch": 0.9202156755489568,
      "grad_norm": 0.19171462953090668,
      "learning_rate": 0.00013909395973154363,
      "loss": 0.8649,
      "step": 368
    },
    {
      "epoch": 0.922716261623818,
      "grad_norm": 0.19302335381507874,
      "learning_rate": 0.0001389261744966443,
      "loss": 0.8818,
      "step": 369
    },
    {
      "epoch": 0.9252168476986794,
      "grad_norm": 0.19845272600650787,
      "learning_rate": 0.000138758389261745,
      "loss": 0.9664,
      "step": 370
    },
    {
      "epoch": 0.9277174337735407,
      "grad_norm": 0.19285465776920319,
      "learning_rate": 0.00013859060402684564,
      "loss": 0.938,
      "step": 371
    },
    {
      "epoch": 0.930218019848402,
      "grad_norm": 0.19765235483646393,
      "learning_rate": 0.00013842281879194632,
      "loss": 0.9196,
      "step": 372
    },
    {
      "epoch": 0.9327186059232633,
      "grad_norm": 0.19708356261253357,
      "learning_rate": 0.00013825503355704698,
      "loss": 0.9941,
      "step": 373
    },
    {
      "epoch": 0.9352191919981245,
      "grad_norm": 0.20135480165481567,
      "learning_rate": 0.00013808724832214766,
      "loss": 0.9202,
      "step": 374
    },
    {
      "epoch": 0.9377197780729859,
      "grad_norm": 0.20005004107952118,
      "learning_rate": 0.00013791946308724834,
      "loss": 0.9331,
      "step": 375
    },
    {
      "epoch": 0.9402203641478472,
      "grad_norm": 0.19034837186336517,
      "learning_rate": 0.000137751677852349,
      "loss": 0.8916,
      "step": 376
    },
    {
      "epoch": 0.9427209502227084,
      "grad_norm": 0.19903801381587982,
      "learning_rate": 0.00013758389261744967,
      "loss": 0.8614,
      "step": 377
    },
    {
      "epoch": 0.9452215362975698,
      "grad_norm": 0.19618506729602814,
      "learning_rate": 0.00013741610738255035,
      "loss": 0.9527,
      "step": 378
    },
    {
      "epoch": 0.947722122372431,
      "grad_norm": 0.1987503319978714,
      "learning_rate": 0.00013724832214765103,
      "loss": 0.8987,
      "step": 379
    },
    {
      "epoch": 0.9502227084472923,
      "grad_norm": 0.1936248540878296,
      "learning_rate": 0.00013708053691275168,
      "loss": 0.8943,
      "step": 380
    },
    {
      "epoch": 0.9527232945221537,
      "grad_norm": 0.19770075380802155,
      "learning_rate": 0.00013691275167785236,
      "loss": 0.918,
      "step": 381
    },
    {
      "epoch": 0.9552238805970149,
      "grad_norm": 0.19526584446430206,
      "learning_rate": 0.000136744966442953,
      "loss": 0.9709,
      "step": 382
    },
    {
      "epoch": 0.9577244666718763,
      "grad_norm": 0.20261335372924805,
      "learning_rate": 0.0001365771812080537,
      "loss": 0.9189,
      "step": 383
    },
    {
      "epoch": 0.9602250527467375,
      "grad_norm": 0.2129514068365097,
      "learning_rate": 0.00013640939597315437,
      "loss": 0.9054,
      "step": 384
    },
    {
      "epoch": 0.9627256388215988,
      "grad_norm": 0.20009979605674744,
      "learning_rate": 0.00013624161073825503,
      "loss": 0.8555,
      "step": 385
    },
    {
      "epoch": 0.9652262248964601,
      "grad_norm": 0.22270314395427704,
      "learning_rate": 0.0001360738255033557,
      "loss": 0.9823,
      "step": 386
    },
    {
      "epoch": 0.9677268109713214,
      "grad_norm": 0.20095857977867126,
      "learning_rate": 0.00013590604026845639,
      "loss": 0.8974,
      "step": 387
    },
    {
      "epoch": 0.9702273970461827,
      "grad_norm": 0.21703922748565674,
      "learning_rate": 0.00013573825503355706,
      "loss": 0.9612,
      "step": 388
    },
    {
      "epoch": 0.972727983121044,
      "grad_norm": 0.20171691477298737,
      "learning_rate": 0.00013557046979865772,
      "loss": 0.9066,
      "step": 389
    },
    {
      "epoch": 0.9752285691959053,
      "grad_norm": 0.21097329258918762,
      "learning_rate": 0.0001354026845637584,
      "loss": 0.9024,
      "step": 390
    },
    {
      "epoch": 0.9777291552707665,
      "grad_norm": 0.1949266642332077,
      "learning_rate": 0.00013523489932885908,
      "loss": 0.8925,
      "step": 391
    },
    {
      "epoch": 0.9802297413456279,
      "grad_norm": 0.20178557932376862,
      "learning_rate": 0.00013506711409395973,
      "loss": 0.9671,
      "step": 392
    },
    {
      "epoch": 0.9827303274204892,
      "grad_norm": 0.1976921707391739,
      "learning_rate": 0.0001348993288590604,
      "loss": 0.8416,
      "step": 393
    },
    {
      "epoch": 0.9852309134953505,
      "grad_norm": 0.20067280530929565,
      "learning_rate": 0.00013473154362416106,
      "loss": 0.9176,
      "step": 394
    },
    {
      "epoch": 0.9877314995702118,
      "grad_norm": 0.20026645064353943,
      "learning_rate": 0.00013456375838926174,
      "loss": 0.9605,
      "step": 395
    },
    {
      "epoch": 0.990232085645073,
      "grad_norm": 0.2071172446012497,
      "learning_rate": 0.00013439597315436242,
      "loss": 0.8994,
      "step": 396
    },
    {
      "epoch": 0.9927326717199344,
      "grad_norm": 0.20478585362434387,
      "learning_rate": 0.0001342281879194631,
      "loss": 0.8575,
      "step": 397
    },
    {
      "epoch": 0.9952332577947957,
      "grad_norm": 0.21187831461429596,
      "learning_rate": 0.00013406040268456378,
      "loss": 0.9329,
      "step": 398
    },
    {
      "epoch": 0.9977338438696569,
      "grad_norm": 0.20360170304775238,
      "learning_rate": 0.00013389261744966443,
      "loss": 0.912,
      "step": 399
    },
    {
      "epoch": 1.0002344299445183,
      "grad_norm": 0.20638534426689148,
      "learning_rate": 0.00013372483221476511,
      "loss": 0.9548,
      "step": 400
    },
    {
      "epoch": 1.0027350160193795,
      "grad_norm": 0.20016121864318848,
      "learning_rate": 0.00013355704697986577,
      "loss": 0.8672,
      "step": 401
    },
    {
      "epoch": 1.0052356020942408,
      "grad_norm": 0.19950714707374573,
      "learning_rate": 0.00013338926174496645,
      "loss": 0.9067,
      "step": 402
    },
    {
      "epoch": 1.007736188169102,
      "grad_norm": 0.19529801607131958,
      "learning_rate": 0.0001332214765100671,
      "loss": 0.9288,
      "step": 403
    },
    {
      "epoch": 1.0102367742439635,
      "grad_norm": 0.19638019800186157,
      "learning_rate": 0.0001330536912751678,
      "loss": 0.8655,
      "step": 404
    },
    {
      "epoch": 1.0127373603188248,
      "grad_norm": 0.2076416313648224,
      "learning_rate": 0.00013288590604026846,
      "loss": 0.8996,
      "step": 405
    },
    {
      "epoch": 1.015237946393686,
      "grad_norm": 0.19819454848766327,
      "learning_rate": 0.00013271812080536914,
      "loss": 0.8955,
      "step": 406
    },
    {
      "epoch": 1.0177385324685473,
      "grad_norm": 0.2053442746400833,
      "learning_rate": 0.00013255033557046982,
      "loss": 0.8902,
      "step": 407
    },
    {
      "epoch": 1.0202391185434085,
      "grad_norm": 0.211964949965477,
      "learning_rate": 0.00013238255033557047,
      "loss": 0.8836,
      "step": 408
    },
    {
      "epoch": 1.02273970461827,
      "grad_norm": 0.21029819548130035,
      "learning_rate": 0.00013221476510067115,
      "loss": 0.8894,
      "step": 409
    },
    {
      "epoch": 1.0252402906931313,
      "grad_norm": 0.20015518367290497,
      "learning_rate": 0.0001320469798657718,
      "loss": 0.9041,
      "step": 410
    },
    {
      "epoch": 1.0277408767679925,
      "grad_norm": 0.2067364752292633,
      "learning_rate": 0.00013187919463087248,
      "loss": 0.8769,
      "step": 411
    },
    {
      "epoch": 1.0302414628428538,
      "grad_norm": 0.21249079704284668,
      "learning_rate": 0.00013171140939597316,
      "loss": 0.8352,
      "step": 412
    },
    {
      "epoch": 1.032742048917715,
      "grad_norm": 0.20129866898059845,
      "learning_rate": 0.00013154362416107384,
      "loss": 0.8499,
      "step": 413
    },
    {
      "epoch": 1.0352426349925763,
      "grad_norm": 0.19970041513442993,
      "learning_rate": 0.00013137583892617452,
      "loss": 0.8604,
      "step": 414
    },
    {
      "epoch": 1.0377432210674378,
      "grad_norm": 0.20939721167087555,
      "learning_rate": 0.00013120805369127518,
      "loss": 0.875,
      "step": 415
    },
    {
      "epoch": 1.040243807142299,
      "grad_norm": 0.19969108700752258,
      "learning_rate": 0.00013104026845637586,
      "loss": 0.8776,
      "step": 416
    },
    {
      "epoch": 1.0427443932171603,
      "grad_norm": 0.21169830858707428,
      "learning_rate": 0.0001308724832214765,
      "loss": 0.8733,
      "step": 417
    },
    {
      "epoch": 1.0452449792920215,
      "grad_norm": 0.20807021856307983,
      "learning_rate": 0.0001307046979865772,
      "loss": 0.9011,
      "step": 418
    },
    {
      "epoch": 1.0477455653668828,
      "grad_norm": 0.20478905737400055,
      "learning_rate": 0.00013053691275167784,
      "loss": 0.8469,
      "step": 419
    },
    {
      "epoch": 1.050246151441744,
      "grad_norm": 0.20112550258636475,
      "learning_rate": 0.00013036912751677852,
      "loss": 0.8337,
      "step": 420
    },
    {
      "epoch": 1.0527467375166055,
      "grad_norm": 0.20829133689403534,
      "learning_rate": 0.0001302013422818792,
      "loss": 0.8658,
      "step": 421
    },
    {
      "epoch": 1.0552473235914668,
      "grad_norm": 0.2128250151872635,
      "learning_rate": 0.00013003355704697988,
      "loss": 0.9182,
      "step": 422
    },
    {
      "epoch": 1.057747909666328,
      "grad_norm": 0.21892035007476807,
      "learning_rate": 0.00012986577181208056,
      "loss": 0.8941,
      "step": 423
    },
    {
      "epoch": 1.0602484957411893,
      "grad_norm": 0.21170388162136078,
      "learning_rate": 0.0001296979865771812,
      "loss": 0.8941,
      "step": 424
    },
    {
      "epoch": 1.0627490818160505,
      "grad_norm": 0.22825805842876434,
      "learning_rate": 0.0001295302013422819,
      "loss": 0.8802,
      "step": 425
    },
    {
      "epoch": 1.065249667890912,
      "grad_norm": 0.22174450755119324,
      "learning_rate": 0.00012936241610738254,
      "loss": 0.8551,
      "step": 426
    },
    {
      "epoch": 1.0677502539657733,
      "grad_norm": 0.21162670850753784,
      "learning_rate": 0.00012919463087248322,
      "loss": 0.8937,
      "step": 427
    },
    {
      "epoch": 1.0702508400406345,
      "grad_norm": 0.21269601583480835,
      "learning_rate": 0.0001290268456375839,
      "loss": 0.8639,
      "step": 428
    },
    {
      "epoch": 1.0727514261154958,
      "grad_norm": 0.21762597560882568,
      "learning_rate": 0.00012885906040268456,
      "loss": 0.844,
      "step": 429
    },
    {
      "epoch": 1.075252012190357,
      "grad_norm": 0.22435954213142395,
      "learning_rate": 0.00012869127516778524,
      "loss": 0.9042,
      "step": 430
    },
    {
      "epoch": 1.0777525982652185,
      "grad_norm": 0.21457557380199432,
      "learning_rate": 0.00012852348993288592,
      "loss": 0.8402,
      "step": 431
    },
    {
      "epoch": 1.0802531843400798,
      "grad_norm": 0.21020552515983582,
      "learning_rate": 0.0001283557046979866,
      "loss": 0.9129,
      "step": 432
    },
    {
      "epoch": 1.082753770414941,
      "grad_norm": 0.21104837954044342,
      "learning_rate": 0.00012818791946308725,
      "loss": 0.9079,
      "step": 433
    },
    {
      "epoch": 1.0852543564898023,
      "grad_norm": 0.21720872819423676,
      "learning_rate": 0.00012802013422818793,
      "loss": 0.858,
      "step": 434
    },
    {
      "epoch": 1.0877549425646635,
      "grad_norm": 0.21718966960906982,
      "learning_rate": 0.0001278523489932886,
      "loss": 0.9565,
      "step": 435
    },
    {
      "epoch": 1.0902555286395248,
      "grad_norm": 0.21655264496803284,
      "learning_rate": 0.00012768456375838926,
      "loss": 0.8807,
      "step": 436
    },
    {
      "epoch": 1.0927561147143863,
      "grad_norm": 0.22126564383506775,
      "learning_rate": 0.00012751677852348994,
      "loss": 0.8452,
      "step": 437
    },
    {
      "epoch": 1.0952567007892475,
      "grad_norm": 0.20520944893360138,
      "learning_rate": 0.0001273489932885906,
      "loss": 0.8467,
      "step": 438
    },
    {
      "epoch": 1.0977572868641088,
      "grad_norm": 0.21571533381938934,
      "learning_rate": 0.0001271812080536913,
      "loss": 0.8682,
      "step": 439
    },
    {
      "epoch": 1.10025787293897,
      "grad_norm": 0.22515913844108582,
      "learning_rate": 0.00012701342281879195,
      "loss": 0.862,
      "step": 440
    },
    {
      "epoch": 1.1027584590138313,
      "grad_norm": 0.2109398990869522,
      "learning_rate": 0.00012684563758389263,
      "loss": 0.8754,
      "step": 441
    },
    {
      "epoch": 1.1052590450886925,
      "grad_norm": 0.21629829704761505,
      "learning_rate": 0.00012667785234899329,
      "loss": 0.8876,
      "step": 442
    },
    {
      "epoch": 1.107759631163554,
      "grad_norm": 0.22433191537857056,
      "learning_rate": 0.00012651006711409397,
      "loss": 0.9026,
      "step": 443
    },
    {
      "epoch": 1.1102602172384153,
      "grad_norm": 0.2074134796857834,
      "learning_rate": 0.00012634228187919465,
      "loss": 0.8615,
      "step": 444
    },
    {
      "epoch": 1.1127608033132765,
      "grad_norm": 0.20749977231025696,
      "learning_rate": 0.0001261744966442953,
      "loss": 0.8419,
      "step": 445
    },
    {
      "epoch": 1.1152613893881378,
      "grad_norm": 0.22443081438541412,
      "learning_rate": 0.00012600671140939598,
      "loss": 0.8668,
      "step": 446
    },
    {
      "epoch": 1.117761975462999,
      "grad_norm": 0.21158166229724884,
      "learning_rate": 0.00012583892617449663,
      "loss": 0.8208,
      "step": 447
    },
    {
      "epoch": 1.1202625615378605,
      "grad_norm": 0.2097133845090866,
      "learning_rate": 0.00012567114093959734,
      "loss": 0.9029,
      "step": 448
    },
    {
      "epoch": 1.1227631476127218,
      "grad_norm": 0.22370265424251556,
      "learning_rate": 0.000125503355704698,
      "loss": 0.8474,
      "step": 449
    },
    {
      "epoch": 1.125263733687583,
      "grad_norm": 0.214742511510849,
      "learning_rate": 0.00012533557046979867,
      "loss": 0.8601,
      "step": 450
    },
    {
      "epoch": 1.1277643197624443,
      "grad_norm": 0.2197917401790619,
      "learning_rate": 0.00012516778523489935,
      "loss": 0.809,
      "step": 451
    },
    {
      "epoch": 1.1302649058373055,
      "grad_norm": 0.22799834609031677,
      "learning_rate": 0.000125,
      "loss": 0.8841,
      "step": 452
    },
    {
      "epoch": 1.132765491912167,
      "grad_norm": 0.22149550914764404,
      "learning_rate": 0.00012483221476510068,
      "loss": 0.9131,
      "step": 453
    },
    {
      "epoch": 1.1352660779870283,
      "grad_norm": 0.21215297281742096,
      "learning_rate": 0.00012466442953020134,
      "loss": 0.8944,
      "step": 454
    },
    {
      "epoch": 1.1377666640618895,
      "grad_norm": 0.22512802481651306,
      "learning_rate": 0.00012449664429530201,
      "loss": 0.8935,
      "step": 455
    },
    {
      "epoch": 1.1402672501367508,
      "grad_norm": 0.21118547022342682,
      "learning_rate": 0.00012432885906040267,
      "loss": 0.9184,
      "step": 456
    },
    {
      "epoch": 1.142767836211612,
      "grad_norm": 0.21238967776298523,
      "learning_rate": 0.00012416107382550337,
      "loss": 0.8627,
      "step": 457
    },
    {
      "epoch": 1.1452684222864733,
      "grad_norm": 0.22024264931678772,
      "learning_rate": 0.00012399328859060403,
      "loss": 0.8885,
      "step": 458
    },
    {
      "epoch": 1.1477690083613348,
      "grad_norm": 0.21847938001155853,
      "learning_rate": 0.0001238255033557047,
      "loss": 0.8765,
      "step": 459
    },
    {
      "epoch": 1.150269594436196,
      "grad_norm": 0.21836036443710327,
      "learning_rate": 0.0001236577181208054,
      "loss": 0.8597,
      "step": 460
    },
    {
      "epoch": 1.1527701805110573,
      "grad_norm": 0.2130286544561386,
      "learning_rate": 0.00012348993288590604,
      "loss": 0.8768,
      "step": 461
    },
    {
      "epoch": 1.1552707665859185,
      "grad_norm": 0.21369999647140503,
      "learning_rate": 0.00012332214765100672,
      "loss": 0.8017,
      "step": 462
    },
    {
      "epoch": 1.1577713526607798,
      "grad_norm": 0.2259240299463272,
      "learning_rate": 0.00012315436241610737,
      "loss": 0.8715,
      "step": 463
    },
    {
      "epoch": 1.160271938735641,
      "grad_norm": 0.21691924333572388,
      "learning_rate": 0.00012298657718120805,
      "loss": 0.9279,
      "step": 464
    },
    {
      "epoch": 1.1627725248105025,
      "grad_norm": 0.20966695249080658,
      "learning_rate": 0.00012281879194630873,
      "loss": 0.8204,
      "step": 465
    },
    {
      "epoch": 1.1652731108853638,
      "grad_norm": 0.2113383263349533,
      "learning_rate": 0.0001226510067114094,
      "loss": 0.8876,
      "step": 466
    },
    {
      "epoch": 1.167773696960225,
      "grad_norm": 0.2332780808210373,
      "learning_rate": 0.0001224832214765101,
      "loss": 0.8446,
      "step": 467
    },
    {
      "epoch": 1.1702742830350863,
      "grad_norm": 0.21881066262722015,
      "learning_rate": 0.00012231543624161074,
      "loss": 0.8721,
      "step": 468
    },
    {
      "epoch": 1.1727748691099475,
      "grad_norm": 0.21677622199058533,
      "learning_rate": 0.00012214765100671142,
      "loss": 0.8083,
      "step": 469
    },
    {
      "epoch": 1.175275455184809,
      "grad_norm": 0.22742587327957153,
      "learning_rate": 0.00012197986577181209,
      "loss": 0.8901,
      "step": 470
    },
    {
      "epoch": 1.1777760412596703,
      "grad_norm": 0.21044526994228363,
      "learning_rate": 0.00012181208053691276,
      "loss": 0.8411,
      "step": 471
    },
    {
      "epoch": 1.1802766273345315,
      "grad_norm": 0.2221437394618988,
      "learning_rate": 0.00012164429530201342,
      "loss": 0.8908,
      "step": 472
    },
    {
      "epoch": 1.1827772134093928,
      "grad_norm": 0.22299771010875702,
      "learning_rate": 0.00012147651006711409,
      "loss": 0.8717,
      "step": 473
    },
    {
      "epoch": 1.185277799484254,
      "grad_norm": 0.2145218700170517,
      "learning_rate": 0.00012130872483221478,
      "loss": 0.8593,
      "step": 474
    },
    {
      "epoch": 1.1877783855591155,
      "grad_norm": 0.2120436728000641,
      "learning_rate": 0.00012114093959731545,
      "loss": 0.8369,
      "step": 475
    },
    {
      "epoch": 1.1902789716339768,
      "grad_norm": 0.24196121096611023,
      "learning_rate": 0.00012097315436241611,
      "loss": 0.8599,
      "step": 476
    },
    {
      "epoch": 1.192779557708838,
      "grad_norm": 0.2327934354543686,
      "learning_rate": 0.0001208053691275168,
      "loss": 0.8856,
      "step": 477
    },
    {
      "epoch": 1.1952801437836993,
      "grad_norm": 0.2271525263786316,
      "learning_rate": 0.00012063758389261746,
      "loss": 0.8695,
      "step": 478
    },
    {
      "epoch": 1.1977807298585605,
      "grad_norm": 0.22260010242462158,
      "learning_rate": 0.00012046979865771813,
      "loss": 0.8731,
      "step": 479
    },
    {
      "epoch": 1.2002813159334218,
      "grad_norm": 0.21468815207481384,
      "learning_rate": 0.00012030201342281879,
      "loss": 0.9019,
      "step": 480
    },
    {
      "epoch": 1.2027819020082833,
      "grad_norm": 0.20896653831005096,
      "learning_rate": 0.00012013422818791946,
      "loss": 0.8784,
      "step": 481
    },
    {
      "epoch": 1.2052824880831445,
      "grad_norm": 0.2142104059457779,
      "learning_rate": 0.00011996644295302013,
      "loss": 0.8668,
      "step": 482
    },
    {
      "epoch": 1.2077830741580058,
      "grad_norm": 0.2258850336074829,
      "learning_rate": 0.00011979865771812082,
      "loss": 0.8904,
      "step": 483
    },
    {
      "epoch": 1.210283660232867,
      "grad_norm": 0.21830275654792786,
      "learning_rate": 0.00011963087248322149,
      "loss": 0.8879,
      "step": 484
    },
    {
      "epoch": 1.2127842463077283,
      "grad_norm": 0.2106282114982605,
      "learning_rate": 0.00011946308724832216,
      "loss": 0.8283,
      "step": 485
    },
    {
      "epoch": 1.2152848323825896,
      "grad_norm": 0.21384255588054657,
      "learning_rate": 0.00011929530201342283,
      "loss": 0.8397,
      "step": 486
    },
    {
      "epoch": 1.217785418457451,
      "grad_norm": 0.22718624770641327,
      "learning_rate": 0.0001191275167785235,
      "loss": 0.8968,
      "step": 487
    },
    {
      "epoch": 1.2202860045323123,
      "grad_norm": 0.21989531815052032,
      "learning_rate": 0.00011895973154362416,
      "loss": 0.8884,
      "step": 488
    },
    {
      "epoch": 1.2227865906071735,
      "grad_norm": 0.224409282207489,
      "learning_rate": 0.00011879194630872483,
      "loss": 0.9135,
      "step": 489
    },
    {
      "epoch": 1.2252871766820348,
      "grad_norm": 0.21789176762104034,
      "learning_rate": 0.0001186241610738255,
      "loss": 0.8462,
      "step": 490
    },
    {
      "epoch": 1.227787762756896,
      "grad_norm": 0.21743899583816528,
      "learning_rate": 0.00011845637583892618,
      "loss": 0.8244,
      "step": 491
    },
    {
      "epoch": 1.2302883488317575,
      "grad_norm": 0.22736044228076935,
      "learning_rate": 0.00011828859060402686,
      "loss": 0.9055,
      "step": 492
    },
    {
      "epoch": 1.2327889349066188,
      "grad_norm": 0.22548165917396545,
      "learning_rate": 0.00011812080536912754,
      "loss": 0.821,
      "step": 493
    },
    {
      "epoch": 1.23528952098148,
      "grad_norm": 0.22150689363479614,
      "learning_rate": 0.0001179530201342282,
      "loss": 0.8681,
      "step": 494
    },
    {
      "epoch": 1.2377901070563413,
      "grad_norm": 0.21708747744560242,
      "learning_rate": 0.00011778523489932887,
      "loss": 0.8926,
      "step": 495
    },
    {
      "epoch": 1.2402906931312025,
      "grad_norm": 0.21993860602378845,
      "learning_rate": 0.00011761744966442953,
      "loss": 0.8876,
      "step": 496
    },
    {
      "epoch": 1.242791279206064,
      "grad_norm": 0.21238721907138824,
      "learning_rate": 0.0001174496644295302,
      "loss": 0.8245,
      "step": 497
    },
    {
      "epoch": 1.2452918652809253,
      "grad_norm": 0.22117340564727783,
      "learning_rate": 0.00011728187919463087,
      "loss": 0.9044,
      "step": 498
    },
    {
      "epoch": 1.2477924513557865,
      "grad_norm": 0.21898695826530457,
      "learning_rate": 0.00011711409395973155,
      "loss": 0.9172,
      "step": 499
    },
    {
      "epoch": 1.2502930374306478,
      "grad_norm": 0.22206924855709076,
      "learning_rate": 0.00011694630872483221,
      "loss": 0.8968,
      "step": 500
    }
  ],
  "logging_steps": 1,
  "max_steps": 1197,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1784404499503923e+18,
  "train_batch_size": 5,
  "trial_name": null,
  "trial_params": null
}