{
  "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": 0.7594180107116699,
      "learning_rate": 4e-05,
      "loss": 2.0425,
      "step": 1
    },
    {
      "epoch": 0.005001172149722591,
      "grad_norm": 0.7701483964920044,
      "learning_rate": 8e-05,
      "loss": 2.0851,
      "step": 2
    },
    {
      "epoch": 0.007501758224583887,
      "grad_norm": 0.7642767429351807,
      "learning_rate": 0.00012,
      "loss": 2.0201,
      "step": 3
    },
    {
      "epoch": 0.010002344299445182,
      "grad_norm": 0.8546866774559021,
      "learning_rate": 0.00016,
      "loss": 1.9645,
      "step": 4
    },
    {
      "epoch": 0.012502930374306479,
      "grad_norm": 0.8759480714797974,
      "learning_rate": 0.0002,
      "loss": 1.8278,
      "step": 5
    },
    {
      "epoch": 0.015003516449167774,
      "grad_norm": 0.7554371953010559,
      "learning_rate": 0.0001998322147651007,
      "loss": 1.5279,
      "step": 6
    },
    {
      "epoch": 0.01750410252402907,
      "grad_norm": 0.9531473517417908,
      "learning_rate": 0.00019966442953020134,
      "loss": 1.3597,
      "step": 7
    },
    {
      "epoch": 0.020004688598890364,
      "grad_norm": 0.8676754236221313,
      "learning_rate": 0.00019949664429530202,
      "loss": 1.1228,
      "step": 8
    },
    {
      "epoch": 0.02250527467375166,
      "grad_norm": 0.7342363595962524,
      "learning_rate": 0.00019932885906040267,
      "loss": 0.9392,
      "step": 9
    },
    {
      "epoch": 0.025005860748612958,
      "grad_norm": 0.5210846066474915,
      "learning_rate": 0.00019916107382550338,
      "loss": 0.8306,
      "step": 10
    },
    {
      "epoch": 0.02750644682347425,
      "grad_norm": 0.33346614241600037,
      "learning_rate": 0.00019899328859060403,
      "loss": 0.7801,
      "step": 11
    },
    {
      "epoch": 0.030007032898335548,
      "grad_norm": 0.3581950068473816,
      "learning_rate": 0.00019882550335570471,
      "loss": 0.7862,
      "step": 12
    },
    {
      "epoch": 0.032507618973196845,
      "grad_norm": 0.49463245272636414,
      "learning_rate": 0.0001986577181208054,
      "loss": 0.7424,
      "step": 13
    },
    {
      "epoch": 0.03500820504805814,
      "grad_norm": 0.5055575370788574,
      "learning_rate": 0.00019848993288590605,
      "loss": 0.7309,
      "step": 14
    },
    {
      "epoch": 0.03750879112291943,
      "grad_norm": 0.4792090058326721,
      "learning_rate": 0.00019832214765100673,
      "loss": 0.7158,
      "step": 15
    },
    {
      "epoch": 0.04000937719778073,
      "grad_norm": 0.6231745481491089,
      "learning_rate": 0.00019815436241610738,
      "loss": 0.7298,
      "step": 16
    },
    {
      "epoch": 0.042509963272642025,
      "grad_norm": 0.587597668170929,
      "learning_rate": 0.00019798657718120806,
      "loss": 0.6779,
      "step": 17
    },
    {
      "epoch": 0.04501054934750332,
      "grad_norm": 0.6789360642433167,
      "learning_rate": 0.0001978187919463087,
      "loss": 0.6621,
      "step": 18
    },
    {
      "epoch": 0.04751113542236462,
      "grad_norm": 0.7238547801971436,
      "learning_rate": 0.00019765100671140942,
      "loss": 0.6643,
      "step": 19
    },
    {
      "epoch": 0.050011721497225915,
      "grad_norm": 0.44374287128448486,
      "learning_rate": 0.00019748322147651007,
      "loss": 0.6295,
      "step": 20
    },
    {
      "epoch": 0.052512307572087205,
      "grad_norm": 0.16430321335792542,
      "learning_rate": 0.00019731543624161075,
      "loss": 0.65,
      "step": 21
    },
    {
      "epoch": 0.0550128936469485,
      "grad_norm": 0.1478523313999176,
      "learning_rate": 0.00019714765100671143,
      "loss": 0.6412,
      "step": 22
    },
    {
      "epoch": 0.0575134797218098,
      "grad_norm": 0.15282399952411652,
      "learning_rate": 0.00019697986577181208,
      "loss": 0.624,
      "step": 23
    },
    {
      "epoch": 0.060014065796671096,
      "grad_norm": 0.15637804567813873,
      "learning_rate": 0.00019681208053691276,
      "loss": 0.633,
      "step": 24
    },
    {
      "epoch": 0.06251465187153239,
      "grad_norm": 0.1476782113313675,
      "learning_rate": 0.00019664429530201342,
      "loss": 0.6406,
      "step": 25
    },
    {
      "epoch": 0.06501523794639369,
      "grad_norm": 0.14628452062606812,
      "learning_rate": 0.0001964765100671141,
      "loss": 0.6197,
      "step": 26
    },
    {
      "epoch": 0.06751582402125499,
      "grad_norm": 0.14777548611164093,
      "learning_rate": 0.00019630872483221478,
      "loss": 0.6153,
      "step": 27
    },
    {
      "epoch": 0.07001641009611628,
      "grad_norm": 0.13805972039699554,
      "learning_rate": 0.00019614093959731546,
      "loss": 0.6014,
      "step": 28
    },
    {
      "epoch": 0.07251699617097758,
      "grad_norm": 0.1502184271812439,
      "learning_rate": 0.00019597315436241613,
      "loss": 0.5974,
      "step": 29
    },
    {
      "epoch": 0.07501758224583886,
      "grad_norm": 0.13858534395694733,
      "learning_rate": 0.0001958053691275168,
      "loss": 0.6144,
      "step": 30
    },
    {
      "epoch": 0.07751816832070016,
      "grad_norm": 0.14372514188289642,
      "learning_rate": 0.00019563758389261747,
      "loss": 0.5941,
      "step": 31
    },
    {
      "epoch": 0.08001875439556146,
      "grad_norm": 0.13981372117996216,
      "learning_rate": 0.00019546979865771812,
      "loss": 0.5945,
      "step": 32
    },
    {
      "epoch": 0.08251934047042275,
      "grad_norm": 0.14265769720077515,
      "learning_rate": 0.0001953020134228188,
      "loss": 0.5848,
      "step": 33
    },
    {
      "epoch": 0.08501992654528405,
      "grad_norm": 0.12909187376499176,
      "learning_rate": 0.00019513422818791945,
      "loss": 0.5802,
      "step": 34
    },
    {
      "epoch": 0.08752051262014535,
      "grad_norm": 0.14645205438137054,
      "learning_rate": 0.00019496644295302013,
      "loss": 0.5689,
      "step": 35
    },
    {
      "epoch": 0.09002109869500664,
      "grad_norm": 0.1427399069070816,
      "learning_rate": 0.0001947986577181208,
      "loss": 0.5726,
      "step": 36
    },
    {
      "epoch": 0.09252168476986794,
      "grad_norm": 0.14320509135723114,
      "learning_rate": 0.0001946308724832215,
      "loss": 0.5544,
      "step": 37
    },
    {
      "epoch": 0.09502227084472924,
      "grad_norm": 0.13662615418434143,
      "learning_rate": 0.00019446308724832217,
      "loss": 0.5793,
      "step": 38
    },
    {
      "epoch": 0.09752285691959053,
      "grad_norm": 0.13153070211410522,
      "learning_rate": 0.00019429530201342282,
      "loss": 0.5846,
      "step": 39
    },
    {
      "epoch": 0.10002344299445183,
      "grad_norm": 0.16413502395153046,
      "learning_rate": 0.0001941275167785235,
      "loss": 0.5574,
      "step": 40
    },
    {
      "epoch": 0.10252402906931311,
      "grad_norm": 0.1483771800994873,
      "learning_rate": 0.00019395973154362416,
      "loss": 0.5716,
      "step": 41
    },
    {
      "epoch": 0.10502461514417441,
      "grad_norm": 0.14123424887657166,
      "learning_rate": 0.00019379194630872484,
      "loss": 0.5619,
      "step": 42
    },
    {
      "epoch": 0.10752520121903571,
      "grad_norm": 0.15064753592014313,
      "learning_rate": 0.00019362416107382552,
      "loss": 0.5769,
      "step": 43
    },
    {
      "epoch": 0.110025787293897,
      "grad_norm": 0.15008266270160675,
      "learning_rate": 0.00019345637583892617,
      "loss": 0.555,
      "step": 44
    },
    {
      "epoch": 0.1125263733687583,
      "grad_norm": 0.14735136926174164,
      "learning_rate": 0.00019328859060402688,
      "loss": 0.5331,
      "step": 45
    },
    {
      "epoch": 0.1150269594436196,
      "grad_norm": 0.13642771542072296,
      "learning_rate": 0.00019312080536912753,
      "loss": 0.5397,
      "step": 46
    },
    {
      "epoch": 0.1175275455184809,
      "grad_norm": 0.1735912710428238,
      "learning_rate": 0.0001929530201342282,
      "loss": 0.5451,
      "step": 47
    },
    {
      "epoch": 0.12002813159334219,
      "grad_norm": 0.1445857733488083,
      "learning_rate": 0.00019278523489932886,
      "loss": 0.5739,
      "step": 48
    },
    {
      "epoch": 0.12252871766820349,
      "grad_norm": 0.1417866051197052,
      "learning_rate": 0.00019261744966442954,
      "loss": 0.5435,
      "step": 49
    },
    {
      "epoch": 0.12502930374306478,
      "grad_norm": 0.17940974235534668,
      "learning_rate": 0.00019244966442953022,
      "loss": 0.5602,
      "step": 50
    },
    {
      "epoch": 0.12752988981792607,
      "grad_norm": 0.14657525718212128,
      "learning_rate": 0.00019228187919463087,
      "loss": 0.5227,
      "step": 51
    },
    {
      "epoch": 0.13003047589278738,
      "grad_norm": 0.1798638254404068,
      "learning_rate": 0.00019211409395973155,
      "loss": 0.5395,
      "step": 52
    },
    {
      "epoch": 0.13253106196764866,
      "grad_norm": 0.145979106426239,
      "learning_rate": 0.0001919463087248322,
      "loss": 0.5485,
      "step": 53
    },
    {
      "epoch": 0.13503164804250997,
      "grad_norm": 0.14515143632888794,
      "learning_rate": 0.0001917785234899329,
      "loss": 0.5341,
      "step": 54
    },
    {
      "epoch": 0.13753223411737125,
      "grad_norm": 0.14358939230442047,
      "learning_rate": 0.00019161073825503357,
      "loss": 0.5211,
      "step": 55
    },
    {
      "epoch": 0.14003282019223257,
      "grad_norm": 0.14795799553394318,
      "learning_rate": 0.00019144295302013425,
      "loss": 0.5294,
      "step": 56
    },
    {
      "epoch": 0.14253340626709385,
      "grad_norm": 0.14450453221797943,
      "learning_rate": 0.0001912751677852349,
      "loss": 0.5273,
      "step": 57
    },
    {
      "epoch": 0.14503399234195516,
      "grad_norm": 0.15771551430225372,
      "learning_rate": 0.00019110738255033558,
      "loss": 0.5412,
      "step": 58
    },
    {
      "epoch": 0.14753457841681644,
      "grad_norm": 0.18084295094013214,
      "learning_rate": 0.00019093959731543626,
      "loss": 0.5385,
      "step": 59
    },
    {
      "epoch": 0.15003516449167772,
      "grad_norm": 0.1659678816795349,
      "learning_rate": 0.0001907718120805369,
      "loss": 0.5401,
      "step": 60
    },
    {
      "epoch": 0.15253575056653904,
      "grad_norm": 0.15592657029628754,
      "learning_rate": 0.0001906040268456376,
      "loss": 0.5358,
      "step": 61
    },
    {
      "epoch": 0.15503633664140032,
      "grad_norm": 0.19171522557735443,
      "learning_rate": 0.00019043624161073827,
      "loss": 0.5589,
      "step": 62
    },
    {
      "epoch": 0.15753692271626163,
      "grad_norm": 0.17024098336696625,
      "learning_rate": 0.00019026845637583895,
      "loss": 0.5399,
      "step": 63
    },
    {
      "epoch": 0.1600375087911229,
      "grad_norm": 0.16276618838310242,
      "learning_rate": 0.0001901006711409396,
      "loss": 0.5271,
      "step": 64
    },
    {
      "epoch": 0.16253809486598422,
      "grad_norm": 0.1863684058189392,
      "learning_rate": 0.00018993288590604028,
      "loss": 0.5356,
      "step": 65
    },
    {
      "epoch": 0.1650386809408455,
      "grad_norm": 0.15433144569396973,
      "learning_rate": 0.00018976510067114096,
      "loss": 0.5101,
      "step": 66
    },
    {
      "epoch": 0.16753926701570682,
      "grad_norm": 0.1568458527326584,
      "learning_rate": 0.00018959731543624161,
      "loss": 0.5178,
      "step": 67
    },
    {
      "epoch": 0.1700398530905681,
      "grad_norm": 0.19393286108970642,
      "learning_rate": 0.0001894295302013423,
      "loss": 0.5261,
      "step": 68
    },
    {
      "epoch": 0.1725404391654294,
      "grad_norm": 0.15781769156455994,
      "learning_rate": 0.00018926174496644295,
      "loss": 0.5106,
      "step": 69
    },
    {
      "epoch": 0.1750410252402907,
      "grad_norm": 0.1883280724287033,
      "learning_rate": 0.00018909395973154363,
      "loss": 0.5336,
      "step": 70
    },
    {
      "epoch": 0.17754161131515198,
      "grad_norm": 0.184098020195961,
      "learning_rate": 0.0001889261744966443,
      "loss": 0.5079,
      "step": 71
    },
    {
      "epoch": 0.1800421973900133,
      "grad_norm": 0.1611829400062561,
      "learning_rate": 0.000188758389261745,
      "loss": 0.5002,
      "step": 72
    },
    {
      "epoch": 0.18254278346487457,
      "grad_norm": 0.21065734326839447,
      "learning_rate": 0.00018859060402684564,
      "loss": 0.5238,
      "step": 73
    },
    {
      "epoch": 0.18504336953973588,
      "grad_norm": 0.16418707370758057,
      "learning_rate": 0.00018842281879194632,
      "loss": 0.5183,
      "step": 74
    },
    {
      "epoch": 0.18754395561459716,
      "grad_norm": 0.17874297499656677,
      "learning_rate": 0.000188255033557047,
      "loss": 0.5206,
      "step": 75
    },
    {
      "epoch": 0.19004454168945847,
      "grad_norm": 0.18666118383407593,
      "learning_rate": 0.00018808724832214765,
      "loss": 0.5143,
      "step": 76
    },
    {
      "epoch": 0.19254512776431976,
      "grad_norm": 0.15301728248596191,
      "learning_rate": 0.00018791946308724833,
      "loss": 0.5038,
      "step": 77
    },
    {
      "epoch": 0.19504571383918107,
      "grad_norm": 0.1661822497844696,
      "learning_rate": 0.00018775167785234898,
      "loss": 0.5182,
      "step": 78
    },
    {
      "epoch": 0.19754629991404235,
      "grad_norm": 0.1866961419582367,
      "learning_rate": 0.00018758389261744966,
      "loss": 0.521,
      "step": 79
    },
    {
      "epoch": 0.20004688598890366,
      "grad_norm": 0.178809255361557,
      "learning_rate": 0.00018741610738255034,
      "loss": 0.5088,
      "step": 80
    },
    {
      "epoch": 0.20254747206376494,
      "grad_norm": 0.16507765650749207,
      "learning_rate": 0.00018724832214765102,
      "loss": 0.4998,
      "step": 81
    },
    {
      "epoch": 0.20504805813862623,
      "grad_norm": 0.18188826739788055,
      "learning_rate": 0.0001870805369127517,
      "loss": 0.4959,
      "step": 82
    },
    {
      "epoch": 0.20754864421348754,
      "grad_norm": 0.18728744983673096,
      "learning_rate": 0.00018691275167785236,
      "loss": 0.5192,
      "step": 83
    },
    {
      "epoch": 0.21004923028834882,
      "grad_norm": 0.16816700994968414,
      "learning_rate": 0.00018674496644295304,
      "loss": 0.5021,
      "step": 84
    },
    {
      "epoch": 0.21254981636321013,
      "grad_norm": 0.14855366945266724,
      "learning_rate": 0.0001865771812080537,
      "loss": 0.4962,
      "step": 85
    },
    {
      "epoch": 0.21505040243807141,
      "grad_norm": 0.16501812636852264,
      "learning_rate": 0.00018640939597315437,
      "loss": 0.4927,
      "step": 86
    },
    {
      "epoch": 0.21755098851293272,
      "grad_norm": 0.1743089109659195,
      "learning_rate": 0.00018624161073825502,
      "loss": 0.5142,
      "step": 87
    },
    {
      "epoch": 0.220051574587794,
      "grad_norm": 0.1650586873292923,
      "learning_rate": 0.0001860738255033557,
      "loss": 0.4933,
      "step": 88
    },
    {
      "epoch": 0.22255216066265532,
      "grad_norm": 0.16853803396224976,
      "learning_rate": 0.00018590604026845638,
      "loss": 0.5043,
      "step": 89
    },
    {
      "epoch": 0.2250527467375166,
      "grad_norm": 0.16465862095355988,
      "learning_rate": 0.00018573825503355706,
      "loss": 0.5064,
      "step": 90
    },
    {
      "epoch": 0.2275533328123779,
      "grad_norm": 0.17402450740337372,
      "learning_rate": 0.00018557046979865774,
      "loss": 0.5129,
      "step": 91
    },
    {
      "epoch": 0.2300539188872392,
      "grad_norm": 0.16535209119319916,
      "learning_rate": 0.0001854026845637584,
      "loss": 0.4878,
      "step": 92
    },
    {
      "epoch": 0.2325545049621005,
      "grad_norm": 0.19670793414115906,
      "learning_rate": 0.00018523489932885907,
      "loss": 0.4835,
      "step": 93
    },
    {
      "epoch": 0.2350550910369618,
      "grad_norm": 0.15545278787612915,
      "learning_rate": 0.00018506711409395973,
      "loss": 0.4938,
      "step": 94
    },
    {
      "epoch": 0.23755567711182307,
      "grad_norm": 0.17252099514007568,
      "learning_rate": 0.0001848993288590604,
      "loss": 0.5035,
      "step": 95
    },
    {
      "epoch": 0.24005626318668438,
      "grad_norm": 0.20185311138629913,
      "learning_rate": 0.00018473154362416109,
      "loss": 0.5079,
      "step": 96
    },
    {
      "epoch": 0.24255684926154567,
      "grad_norm": 0.1610802859067917,
      "learning_rate": 0.00018456375838926174,
      "loss": 0.4946,
      "step": 97
    },
    {
      "epoch": 0.24505743533640698,
      "grad_norm": 0.2017122060060501,
      "learning_rate": 0.00018439597315436244,
      "loss": 0.496,
      "step": 98
    },
    {
      "epoch": 0.24755802141126826,
      "grad_norm": 0.16128034889698029,
      "learning_rate": 0.0001842281879194631,
      "loss": 0.4813,
      "step": 99
    },
    {
      "epoch": 0.25005860748612957,
      "grad_norm": 0.22258538007736206,
      "learning_rate": 0.00018406040268456378,
      "loss": 0.494,
      "step": 100
    },
    {
      "epoch": 0.2525591935609909,
      "grad_norm": 0.18942825496196747,
      "learning_rate": 0.00018389261744966443,
      "loss": 0.489,
      "step": 101
    },
    {
      "epoch": 0.25505977963585214,
      "grad_norm": 0.17586448788642883,
      "learning_rate": 0.0001837248322147651,
      "loss": 0.487,
      "step": 102
    },
    {
      "epoch": 0.25756036571071345,
      "grad_norm": 0.2008223831653595,
      "learning_rate": 0.0001835570469798658,
      "loss": 0.494,
      "step": 103
    },
    {
      "epoch": 0.26006095178557476,
      "grad_norm": 0.1799156367778778,
      "learning_rate": 0.00018338926174496644,
      "loss": 0.5082,
      "step": 104
    },
    {
      "epoch": 0.26256153786043607,
      "grad_norm": 0.17686983942985535,
      "learning_rate": 0.00018322147651006712,
      "loss": 0.4727,
      "step": 105
    },
    {
      "epoch": 0.2650621239352973,
      "grad_norm": 0.22485797107219696,
      "learning_rate": 0.0001830536912751678,
      "loss": 0.5017,
      "step": 106
    },
    {
      "epoch": 0.26756271001015863,
      "grad_norm": 0.16205894947052002,
      "learning_rate": 0.00018288590604026848,
      "loss": 0.4744,
      "step": 107
    },
    {
      "epoch": 0.27006329608501994,
      "grad_norm": 0.16790597140789032,
      "learning_rate": 0.00018271812080536913,
      "loss": 0.4773,
      "step": 108
    },
    {
      "epoch": 0.2725638821598812,
      "grad_norm": 0.17916059494018555,
      "learning_rate": 0.00018255033557046981,
      "loss": 0.4779,
      "step": 109
    },
    {
      "epoch": 0.2750644682347425,
      "grad_norm": 0.17400622367858887,
      "learning_rate": 0.00018238255033557047,
      "loss": 0.4977,
      "step": 110
    },
    {
      "epoch": 0.2775650543096038,
      "grad_norm": 0.16923707723617554,
      "learning_rate": 0.00018221476510067115,
      "loss": 0.4933,
      "step": 111
    },
    {
      "epoch": 0.28006564038446513,
      "grad_norm": 0.17827562987804413,
      "learning_rate": 0.00018204697986577183,
      "loss": 0.4888,
      "step": 112
    },
    {
      "epoch": 0.2825662264593264,
      "grad_norm": 0.1732293665409088,
      "learning_rate": 0.00018187919463087248,
      "loss": 0.5098,
      "step": 113
    },
    {
      "epoch": 0.2850668125341877,
      "grad_norm": 0.17349784076213837,
      "learning_rate": 0.00018171140939597316,
      "loss": 0.4924,
      "step": 114
    },
    {
      "epoch": 0.287567398609049,
      "grad_norm": 0.20687106251716614,
      "learning_rate": 0.00018154362416107384,
      "loss": 0.5006,
      "step": 115
    },
    {
      "epoch": 0.2900679846839103,
      "grad_norm": 0.15973134338855743,
      "learning_rate": 0.00018137583892617452,
      "loss": 0.4909,
      "step": 116
    },
    {
      "epoch": 0.2925685707587716,
      "grad_norm": 0.21071845293045044,
      "learning_rate": 0.00018120805369127517,
      "loss": 0.4763,
      "step": 117
    },
    {
      "epoch": 0.2950691568336329,
      "grad_norm": 0.19466304779052734,
      "learning_rate": 0.00018104026845637585,
      "loss": 0.4896,
      "step": 118
    },
    {
      "epoch": 0.2975697429084942,
      "grad_norm": 0.19403570890426636,
      "learning_rate": 0.00018087248322147653,
      "loss": 0.4902,
      "step": 119
    },
    {
      "epoch": 0.30007032898335545,
      "grad_norm": 0.219278946518898,
      "learning_rate": 0.00018070469798657718,
      "loss": 0.4883,
      "step": 120
    },
    {
      "epoch": 0.30257091505821676,
      "grad_norm": 0.17110252380371094,
      "learning_rate": 0.00018053691275167786,
      "loss": 0.5022,
      "step": 121
    },
    {
      "epoch": 0.30507150113307807,
      "grad_norm": 0.2356841117143631,
      "learning_rate": 0.00018036912751677852,
      "loss": 0.4794,
      "step": 122
    },
    {
      "epoch": 0.3075720872079394,
      "grad_norm": 0.17025519907474518,
      "learning_rate": 0.0001802013422818792,
      "loss": 0.4828,
      "step": 123
    },
    {
      "epoch": 0.31007267328280064,
      "grad_norm": 0.2149350345134735,
      "learning_rate": 0.00018003355704697988,
      "loss": 0.464,
      "step": 124
    },
    {
      "epoch": 0.31257325935766195,
      "grad_norm": 0.17595884203910828,
      "learning_rate": 0.00017986577181208056,
      "loss": 0.4682,
      "step": 125
    },
    {
      "epoch": 0.31507384543252326,
      "grad_norm": 0.17032761871814728,
      "learning_rate": 0.0001796979865771812,
      "loss": 0.4594,
      "step": 126
    },
    {
      "epoch": 0.31757443150738457,
      "grad_norm": 0.15546788275241852,
      "learning_rate": 0.0001795302013422819,
      "loss": 0.4835,
      "step": 127
    },
    {
      "epoch": 0.3200750175822458,
      "grad_norm": 0.18081508576869965,
      "learning_rate": 0.00017936241610738257,
      "loss": 0.477,
      "step": 128
    },
    {
      "epoch": 0.32257560365710714,
      "grad_norm": 0.1631155163049698,
      "learning_rate": 0.00017919463087248322,
      "loss": 0.4768,
      "step": 129
    },
    {
      "epoch": 0.32507618973196845,
      "grad_norm": 0.17103877663612366,
      "learning_rate": 0.0001790268456375839,
      "loss": 0.4725,
      "step": 130
    },
    {
      "epoch": 0.3275767758068297,
      "grad_norm": 0.15857450664043427,
      "learning_rate": 0.00017885906040268455,
      "loss": 0.4777,
      "step": 131
    },
    {
      "epoch": 0.330077361881691,
      "grad_norm": 0.1584555059671402,
      "learning_rate": 0.00017869127516778523,
      "loss": 0.4619,
      "step": 132
    },
    {
      "epoch": 0.3325779479565523,
      "grad_norm": 0.18434159457683563,
      "learning_rate": 0.0001785234899328859,
      "loss": 0.4947,
      "step": 133
    },
    {
      "epoch": 0.33507853403141363,
      "grad_norm": 0.17680639028549194,
      "learning_rate": 0.0001783557046979866,
      "loss": 0.4877,
      "step": 134
    },
    {
      "epoch": 0.3375791201062749,
      "grad_norm": 0.17073361575603485,
      "learning_rate": 0.00017818791946308727,
      "loss": 0.4607,
      "step": 135
    },
    {
      "epoch": 0.3400797061811362,
      "grad_norm": 0.15861110389232635,
      "learning_rate": 0.00017802013422818792,
      "loss": 0.4866,
      "step": 136
    },
    {
      "epoch": 0.3425802922559975,
      "grad_norm": 0.16533519327640533,
      "learning_rate": 0.0001778523489932886,
      "loss": 0.4844,
      "step": 137
    },
    {
      "epoch": 0.3450808783308588,
      "grad_norm": 0.1725560426712036,
      "learning_rate": 0.00017768456375838926,
      "loss": 0.4997,
      "step": 138
    },
    {
      "epoch": 0.3475814644057201,
      "grad_norm": 0.16393449902534485,
      "learning_rate": 0.00017751677852348994,
      "loss": 0.4751,
      "step": 139
    },
    {
      "epoch": 0.3500820504805814,
      "grad_norm": 0.16054843366146088,
      "learning_rate": 0.00017734899328859062,
      "loss": 0.4762,
      "step": 140
    },
    {
      "epoch": 0.3525826365554427,
      "grad_norm": 0.17005555331707,
      "learning_rate": 0.0001771812080536913,
      "loss": 0.4669,
      "step": 141
    },
    {
      "epoch": 0.35508322263030395,
      "grad_norm": 0.17783407866954803,
      "learning_rate": 0.00017701342281879198,
      "loss": 0.4824,
      "step": 142
    },
    {
      "epoch": 0.35758380870516526,
      "grad_norm": 0.16758868098258972,
      "learning_rate": 0.00017684563758389263,
      "loss": 0.4742,
      "step": 143
    },
    {
      "epoch": 0.3600843947800266,
      "grad_norm": 0.15669575333595276,
      "learning_rate": 0.0001766778523489933,
      "loss": 0.4594,
      "step": 144
    },
    {
      "epoch": 0.3625849808548879,
      "grad_norm": 0.17958584427833557,
      "learning_rate": 0.00017651006711409396,
      "loss": 0.4786,
      "step": 145
    },
    {
      "epoch": 0.36508556692974914,
      "grad_norm": 0.19689996540546417,
      "learning_rate": 0.00017634228187919464,
      "loss": 0.4858,
      "step": 146
    },
    {
      "epoch": 0.36758615300461045,
      "grad_norm": 0.17314714193344116,
      "learning_rate": 0.0001761744966442953,
      "loss": 0.4773,
      "step": 147
    },
    {
      "epoch": 0.37008673907947176,
      "grad_norm": 0.1754344254732132,
      "learning_rate": 0.00017600671140939597,
      "loss": 0.4848,
      "step": 148
    },
    {
      "epoch": 0.37258732515433307,
      "grad_norm": 0.16518406569957733,
      "learning_rate": 0.00017583892617449665,
      "loss": 0.4593,
      "step": 149
    },
    {
      "epoch": 0.3750879112291943,
      "grad_norm": 0.16496793925762177,
      "learning_rate": 0.00017567114093959733,
      "loss": 0.4755,
      "step": 150
    },
    {
      "epoch": 0.37758849730405564,
      "grad_norm": 0.1820346862077713,
      "learning_rate": 0.000175503355704698,
      "loss": 0.4758,
      "step": 151
    },
    {
      "epoch": 0.38008908337891695,
      "grad_norm": 0.1669500470161438,
      "learning_rate": 0.00017533557046979867,
      "loss": 0.4834,
      "step": 152
    },
    {
      "epoch": 0.3825896694537782,
      "grad_norm": 0.18701374530792236,
      "learning_rate": 0.00017516778523489935,
      "loss": 0.4613,
      "step": 153
    },
    {
      "epoch": 0.3850902555286395,
      "grad_norm": 0.1735297441482544,
      "learning_rate": 0.000175,
      "loss": 0.4742,
      "step": 154
    },
    {
      "epoch": 0.3875908416035008,
      "grad_norm": 0.17582108080387115,
      "learning_rate": 0.00017483221476510068,
      "loss": 0.4712,
      "step": 155
    },
    {
      "epoch": 0.39009142767836213,
      "grad_norm": 0.17562179267406464,
      "learning_rate": 0.00017466442953020136,
      "loss": 0.4543,
      "step": 156
    },
    {
      "epoch": 0.3925920137532234,
      "grad_norm": 0.1820077896118164,
      "learning_rate": 0.000174496644295302,
      "loss": 0.4624,
      "step": 157
    },
    {
      "epoch": 0.3950925998280847,
      "grad_norm": 0.19618383049964905,
      "learning_rate": 0.0001743288590604027,
      "loss": 0.48,
      "step": 158
    },
    {
      "epoch": 0.397593185902946,
      "grad_norm": 0.20992861688137054,
      "learning_rate": 0.00017416107382550337,
      "loss": 0.4806,
      "step": 159
    },
    {
      "epoch": 0.4000937719778073,
      "grad_norm": 0.17106316983699799,
      "learning_rate": 0.00017399328859060405,
      "loss": 0.4666,
      "step": 160
    },
    {
      "epoch": 0.4025943580526686,
      "grad_norm": 0.20506031811237335,
      "learning_rate": 0.0001738255033557047,
      "loss": 0.465,
      "step": 161
    },
    {
      "epoch": 0.4050949441275299,
      "grad_norm": 0.16451655328273773,
      "learning_rate": 0.00017365771812080538,
      "loss": 0.492,
      "step": 162
    },
    {
      "epoch": 0.4075955302023912,
      "grad_norm": 0.17921902239322662,
      "learning_rate": 0.00017348993288590604,
      "loss": 0.4786,
      "step": 163
    },
    {
      "epoch": 0.41009611627725245,
      "grad_norm": 0.19945573806762695,
      "learning_rate": 0.00017332214765100671,
      "loss": 0.4578,
      "step": 164
    },
    {
      "epoch": 0.41259670235211376,
      "grad_norm": 0.1591523438692093,
      "learning_rate": 0.0001731543624161074,
      "loss": 0.4698,
      "step": 165
    },
    {
      "epoch": 0.4150972884269751,
      "grad_norm": 0.2252337783575058,
      "learning_rate": 0.00017298657718120805,
      "loss": 0.4669,
      "step": 166
    },
    {
      "epoch": 0.4175978745018364,
      "grad_norm": 0.17984913289546967,
      "learning_rate": 0.00017281879194630873,
      "loss": 0.4672,
      "step": 167
    },
    {
      "epoch": 0.42009846057669764,
      "grad_norm": 0.1938534379005432,
      "learning_rate": 0.0001726510067114094,
      "loss": 0.4718,
      "step": 168
    },
    {
      "epoch": 0.42259904665155895,
      "grad_norm": 0.18750695884227753,
      "learning_rate": 0.0001724832214765101,
      "loss": 0.4747,
      "step": 169
    },
    {
      "epoch": 0.42509963272642026,
      "grad_norm": 0.17218442261219025,
      "learning_rate": 0.00017231543624161074,
      "loss": 0.4637,
      "step": 170
    },
    {
      "epoch": 0.4276002188012816,
      "grad_norm": 0.1735689640045166,
      "learning_rate": 0.00017214765100671142,
      "loss": 0.4842,
      "step": 171
    },
    {
      "epoch": 0.43010080487614283,
      "grad_norm": 0.18109886348247528,
      "learning_rate": 0.0001719798657718121,
      "loss": 0.4927,
      "step": 172
    },
    {
      "epoch": 0.43260139095100414,
      "grad_norm": 0.18199589848518372,
      "learning_rate": 0.00017181208053691275,
      "loss": 0.4677,
      "step": 173
    },
    {
      "epoch": 0.43510197702586545,
      "grad_norm": 0.1843508929014206,
      "learning_rate": 0.00017164429530201343,
      "loss": 0.4521,
      "step": 174
    },
    {
      "epoch": 0.43760256310072676,
      "grad_norm": 0.1735106110572815,
      "learning_rate": 0.00017147651006711408,
      "loss": 0.4761,
      "step": 175
    },
    {
      "epoch": 0.440103149175588,
      "grad_norm": 0.16991625726222992,
      "learning_rate": 0.0001713087248322148,
      "loss": 0.4507,
      "step": 176
    },
    {
      "epoch": 0.4426037352504493,
      "grad_norm": 0.16398338973522186,
      "learning_rate": 0.00017114093959731544,
      "loss": 0.46,
      "step": 177
    },
    {
      "epoch": 0.44510432132531064,
      "grad_norm": 0.18237490952014923,
      "learning_rate": 0.00017097315436241612,
      "loss": 0.4627,
      "step": 178
    },
    {
      "epoch": 0.4476049074001719,
      "grad_norm": 0.174173042178154,
      "learning_rate": 0.0001708053691275168,
      "loss": 0.4514,
      "step": 179
    },
    {
      "epoch": 0.4501054934750332,
      "grad_norm": 0.1653733253479004,
      "learning_rate": 0.00017063758389261746,
      "loss": 0.4551,
      "step": 180
    },
    {
      "epoch": 0.4526060795498945,
      "grad_norm": 0.19772449135780334,
      "learning_rate": 0.00017046979865771814,
      "loss": 0.4463,
      "step": 181
    },
    {
      "epoch": 0.4551066656247558,
      "grad_norm": 0.1714743971824646,
      "learning_rate": 0.0001703020134228188,
      "loss": 0.4673,
      "step": 182
    },
    {
      "epoch": 0.4576072516996171,
      "grad_norm": 0.181261345744133,
      "learning_rate": 0.00017013422818791947,
      "loss": 0.4556,
      "step": 183
    },
    {
      "epoch": 0.4601078377744784,
      "grad_norm": 0.15487723052501678,
      "learning_rate": 0.00016996644295302012,
      "loss": 0.4568,
      "step": 184
    },
    {
      "epoch": 0.4626084238493397,
      "grad_norm": 0.16992811858654022,
      "learning_rate": 0.00016979865771812083,
      "loss": 0.4686,
      "step": 185
    },
    {
      "epoch": 0.465109009924201,
      "grad_norm": 0.1934443712234497,
      "learning_rate": 0.00016963087248322148,
      "loss": 0.4695,
      "step": 186
    },
    {
      "epoch": 0.46760959599906227,
      "grad_norm": 0.16562269628047943,
      "learning_rate": 0.00016946308724832216,
      "loss": 0.449,
      "step": 187
    },
    {
      "epoch": 0.4701101820739236,
      "grad_norm": 0.19825531542301178,
      "learning_rate": 0.00016929530201342284,
      "loss": 0.4623,
      "step": 188
    },
    {
      "epoch": 0.4726107681487849,
      "grad_norm": 0.1690351963043213,
      "learning_rate": 0.0001691275167785235,
      "loss": 0.4584,
      "step": 189
    },
    {
      "epoch": 0.47511135422364614,
      "grad_norm": 0.1793663501739502,
      "learning_rate": 0.00016895973154362417,
      "loss": 0.4598,
      "step": 190
    },
    {
      "epoch": 0.47761194029850745,
      "grad_norm": 0.1759204864501953,
      "learning_rate": 0.00016879194630872483,
      "loss": 0.4601,
      "step": 191
    },
    {
      "epoch": 0.48011252637336876,
      "grad_norm": 0.16646680235862732,
      "learning_rate": 0.0001686241610738255,
      "loss": 0.4662,
      "step": 192
    },
    {
      "epoch": 0.4826131124482301,
      "grad_norm": 0.1967586725950241,
      "learning_rate": 0.00016845637583892619,
      "loss": 0.4782,
      "step": 193
    },
    {
      "epoch": 0.48511369852309133,
      "grad_norm": 0.16055084764957428,
      "learning_rate": 0.00016828859060402686,
      "loss": 0.4603,
      "step": 194
    },
    {
      "epoch": 0.48761428459795264,
      "grad_norm": 0.2091376930475235,
      "learning_rate": 0.00016812080536912754,
      "loss": 0.4591,
      "step": 195
    },
    {
      "epoch": 0.49011487067281395,
      "grad_norm": 0.17712931334972382,
      "learning_rate": 0.0001679530201342282,
      "loss": 0.4405,
      "step": 196
    },
    {
      "epoch": 0.49261545674767526,
      "grad_norm": 0.16605544090270996,
      "learning_rate": 0.00016778523489932888,
      "loss": 0.4502,
      "step": 197
    },
    {
      "epoch": 0.4951160428225365,
      "grad_norm": 0.18599025905132294,
      "learning_rate": 0.00016761744966442953,
      "loss": 0.449,
      "step": 198
    },
    {
      "epoch": 0.49761662889739783,
      "grad_norm": 0.17631739377975464,
      "learning_rate": 0.0001674496644295302,
      "loss": 0.4646,
      "step": 199
    },
    {
      "epoch": 0.5001172149722591,
      "grad_norm": 0.17810176312923431,
      "learning_rate": 0.00016728187919463086,
      "loss": 0.4538,
      "step": 200
    },
    {
      "epoch": 0.5026178010471204,
      "grad_norm": 0.18166030943393707,
      "learning_rate": 0.00016711409395973154,
      "loss": 0.4596,
      "step": 201
    },
    {
      "epoch": 0.5051183871219818,
      "grad_norm": 0.1877959668636322,
      "learning_rate": 0.00016694630872483222,
      "loss": 0.4421,
      "step": 202
    },
    {
      "epoch": 0.507618973196843,
      "grad_norm": 0.16203252971172333,
      "learning_rate": 0.0001667785234899329,
      "loss": 0.4435,
      "step": 203
    },
    {
      "epoch": 0.5101195592717043,
      "grad_norm": 0.22125209867954254,
      "learning_rate": 0.00016661073825503358,
      "loss": 0.4568,
      "step": 204
    },
    {
      "epoch": 0.5126201453465656,
      "grad_norm": 0.16617968678474426,
      "learning_rate": 0.00016644295302013423,
      "loss": 0.4524,
      "step": 205
    },
    {
      "epoch": 0.5151207314214269,
      "grad_norm": 0.1956106424331665,
      "learning_rate": 0.00016627516778523491,
      "loss": 0.4568,
      "step": 206
    },
    {
      "epoch": 0.5176213174962881,
      "grad_norm": 0.17417706549167633,
      "learning_rate": 0.00016610738255033557,
      "loss": 0.4393,
      "step": 207
    },
    {
      "epoch": 0.5201219035711495,
      "grad_norm": 0.1713646799325943,
      "learning_rate": 0.00016593959731543625,
      "loss": 0.443,
      "step": 208
    },
    {
      "epoch": 0.5226224896460108,
      "grad_norm": 0.18685942888259888,
      "learning_rate": 0.00016577181208053693,
      "loss": 0.4451,
      "step": 209
    },
    {
      "epoch": 0.5251230757208721,
      "grad_norm": 0.17455795407295227,
      "learning_rate": 0.00016560402684563758,
      "loss": 0.4538,
      "step": 210
    },
    {
      "epoch": 0.5276236617957334,
      "grad_norm": 0.17413204908370972,
      "learning_rate": 0.00016543624161073829,
      "loss": 0.4453,
      "step": 211
    },
    {
      "epoch": 0.5301242478705946,
      "grad_norm": 0.16172130405902863,
      "learning_rate": 0.00016526845637583894,
      "loss": 0.4584,
      "step": 212
    },
    {
      "epoch": 0.532624833945456,
      "grad_norm": 0.16567657887935638,
      "learning_rate": 0.00016510067114093962,
      "loss": 0.4429,
      "step": 213
    },
    {
      "epoch": 0.5351254200203173,
      "grad_norm": 0.17749889194965363,
      "learning_rate": 0.00016493288590604027,
      "loss": 0.4395,
      "step": 214
    },
    {
      "epoch": 0.5376260060951785,
      "grad_norm": 0.16244365274906158,
      "learning_rate": 0.00016476510067114095,
      "loss": 0.455,
      "step": 215
    },
    {
      "epoch": 0.5401265921700399,
      "grad_norm": 0.16314131021499634,
      "learning_rate": 0.0001645973154362416,
      "loss": 0.4383,
      "step": 216
    },
    {
      "epoch": 0.5426271782449011,
      "grad_norm": 0.16629692912101746,
      "learning_rate": 0.00016442953020134228,
      "loss": 0.4391,
      "step": 217
    },
    {
      "epoch": 0.5451277643197624,
      "grad_norm": 0.18032211065292358,
      "learning_rate": 0.00016426174496644296,
      "loss": 0.4502,
      "step": 218
    },
    {
      "epoch": 0.5476283503946238,
      "grad_norm": 0.1673993170261383,
      "learning_rate": 0.00016409395973154362,
      "loss": 0.4518,
      "step": 219
    },
    {
      "epoch": 0.550128936469485,
      "grad_norm": 0.17051811516284943,
      "learning_rate": 0.00016392617449664432,
      "loss": 0.4658,
      "step": 220
    },
    {
      "epoch": 0.5526295225443464,
      "grad_norm": 0.17144182324409485,
      "learning_rate": 0.00016375838926174498,
      "loss": 0.455,
      "step": 221
    },
    {
      "epoch": 0.5551301086192076,
      "grad_norm": 0.16543865203857422,
      "learning_rate": 0.00016359060402684566,
      "loss": 0.4524,
      "step": 222
    },
    {
      "epoch": 0.5576306946940689,
      "grad_norm": 0.1819363236427307,
      "learning_rate": 0.0001634228187919463,
      "loss": 0.4374,
      "step": 223
    },
    {
      "epoch": 0.5601312807689303,
      "grad_norm": 0.1822425127029419,
      "learning_rate": 0.000163255033557047,
      "loss": 0.4437,
      "step": 224
    },
    {
      "epoch": 0.5626318668437915,
      "grad_norm": 0.17073342204093933,
      "learning_rate": 0.00016308724832214767,
      "loss": 0.4654,
      "step": 225
    },
    {
      "epoch": 0.5651324529186528,
      "grad_norm": 0.1630779355764389,
      "learning_rate": 0.00016291946308724832,
      "loss": 0.4577,
      "step": 226
    },
    {
      "epoch": 0.5676330389935141,
      "grad_norm": 0.17408612370491028,
      "learning_rate": 0.000162751677852349,
      "loss": 0.445,
      "step": 227
    },
    {
      "epoch": 0.5701336250683754,
      "grad_norm": 0.2113485187292099,
      "learning_rate": 0.00016258389261744965,
      "loss": 0.4486,
      "step": 228
    },
    {
      "epoch": 0.5726342111432366,
      "grad_norm": 0.16299131512641907,
      "learning_rate": 0.00016241610738255036,
      "loss": 0.4508,
      "step": 229
    },
    {
      "epoch": 0.575134797218098,
      "grad_norm": 0.20489177107810974,
      "learning_rate": 0.000162248322147651,
      "loss": 0.4742,
      "step": 230
    },
    {
      "epoch": 0.5776353832929593,
      "grad_norm": 0.1746734082698822,
      "learning_rate": 0.0001620805369127517,
      "loss": 0.4382,
      "step": 231
    },
    {
      "epoch": 0.5801359693678206,
      "grad_norm": 0.1877690851688385,
      "learning_rate": 0.00016191275167785237,
      "loss": 0.4483,
      "step": 232
    },
    {
      "epoch": 0.5826365554426819,
      "grad_norm": 0.19249488413333893,
      "learning_rate": 0.00016174496644295302,
      "loss": 0.4458,
      "step": 233
    },
    {
      "epoch": 0.5851371415175431,
      "grad_norm": 0.1570655256509781,
      "learning_rate": 0.0001615771812080537,
      "loss": 0.4474,
      "step": 234
    },
    {
      "epoch": 0.5876377275924045,
      "grad_norm": 0.188018798828125,
      "learning_rate": 0.00016140939597315436,
      "loss": 0.4345,
      "step": 235
    },
    {
      "epoch": 0.5901383136672658,
      "grad_norm": 0.20541886985301971,
      "learning_rate": 0.00016124161073825504,
      "loss": 0.462,
      "step": 236
    },
    {
      "epoch": 0.592638899742127,
      "grad_norm": 0.17590679228305817,
      "learning_rate": 0.0001610738255033557,
      "loss": 0.4613,
      "step": 237
    },
    {
      "epoch": 0.5951394858169884,
      "grad_norm": 0.21810193359851837,
      "learning_rate": 0.0001609060402684564,
      "loss": 0.4319,
      "step": 238
    },
    {
      "epoch": 0.5976400718918496,
      "grad_norm": 0.20115698873996735,
      "learning_rate": 0.00016073825503355705,
      "loss": 0.4347,
      "step": 239
    },
    {
      "epoch": 0.6001406579667109,
      "grad_norm": 0.17849840223789215,
      "learning_rate": 0.00016057046979865773,
      "loss": 0.4478,
      "step": 240
    },
    {
      "epoch": 0.6026412440415723,
      "grad_norm": 0.1893172413110733,
      "learning_rate": 0.0001604026845637584,
      "loss": 0.451,
      "step": 241
    },
    {
      "epoch": 0.6051418301164335,
      "grad_norm": 0.19342820346355438,
      "learning_rate": 0.00016023489932885906,
      "loss": 0.4513,
      "step": 242
    },
    {
      "epoch": 0.6076424161912949,
      "grad_norm": 0.19177012145519257,
      "learning_rate": 0.00016006711409395974,
      "loss": 0.4487,
      "step": 243
    },
    {
      "epoch": 0.6101430022661561,
      "grad_norm": 0.2117731124162674,
      "learning_rate": 0.0001598993288590604,
      "loss": 0.4461,
      "step": 244
    },
    {
      "epoch": 0.6126435883410174,
      "grad_norm": 0.16634789109230042,
      "learning_rate": 0.00015973154362416107,
      "loss": 0.4482,
      "step": 245
    },
    {
      "epoch": 0.6151441744158788,
      "grad_norm": 0.19687195122241974,
      "learning_rate": 0.00015956375838926175,
      "loss": 0.4445,
      "step": 246
    },
    {
      "epoch": 0.61764476049074,
      "grad_norm": 0.17551076412200928,
      "learning_rate": 0.00015939597315436243,
      "loss": 0.445,
      "step": 247
    },
    {
      "epoch": 0.6201453465656013,
      "grad_norm": 0.16498766839504242,
      "learning_rate": 0.0001592281879194631,
      "loss": 0.4397,
      "step": 248
    },
    {
      "epoch": 0.6226459326404626,
      "grad_norm": 0.17818611860275269,
      "learning_rate": 0.00015906040268456377,
      "loss": 0.4466,
      "step": 249
    },
    {
      "epoch": 0.6251465187153239,
      "grad_norm": 0.205690398812294,
      "learning_rate": 0.00015889261744966445,
      "loss": 0.4448,
      "step": 250
    },
    {
      "epoch": 0.6276471047901852,
      "grad_norm": 0.17474979162216187,
      "learning_rate": 0.0001587248322147651,
      "loss": 0.4293,
      "step": 251
    },
    {
      "epoch": 0.6301476908650465,
      "grad_norm": 0.21222396194934845,
      "learning_rate": 0.00015855704697986578,
      "loss": 0.4368,
      "step": 252
    },
    {
      "epoch": 0.6326482769399078,
      "grad_norm": 0.1702364981174469,
      "learning_rate": 0.00015838926174496643,
      "loss": 0.4283,
      "step": 253
    },
    {
      "epoch": 0.6351488630147691,
      "grad_norm": 0.1743675321340561,
      "learning_rate": 0.0001582214765100671,
      "loss": 0.4619,
      "step": 254
    },
    {
      "epoch": 0.6376494490896304,
      "grad_norm": 0.17541950941085815,
      "learning_rate": 0.0001580536912751678,
      "loss": 0.4344,
      "step": 255
    },
    {
      "epoch": 0.6401500351644916,
      "grad_norm": 0.154206320643425,
      "learning_rate": 0.00015788590604026847,
      "loss": 0.4299,
      "step": 256
    },
    {
      "epoch": 0.642650621239353,
      "grad_norm": 0.16429094970226288,
      "learning_rate": 0.00015771812080536915,
      "loss": 0.4367,
      "step": 257
    },
    {
      "epoch": 0.6451512073142143,
      "grad_norm": 0.21027475595474243,
      "learning_rate": 0.0001575503355704698,
      "loss": 0.4668,
      "step": 258
    },
    {
      "epoch": 0.6476517933890755,
      "grad_norm": 0.16886752843856812,
      "learning_rate": 0.00015738255033557048,
      "loss": 0.4521,
      "step": 259
    },
    {
      "epoch": 0.6501523794639369,
      "grad_norm": 0.17572204768657684,
      "learning_rate": 0.00015721476510067114,
      "loss": 0.4235,
      "step": 260
    },
    {
      "epoch": 0.6526529655387981,
      "grad_norm": 0.1727110594511032,
      "learning_rate": 0.00015704697986577181,
      "loss": 0.4611,
      "step": 261
    },
    {
      "epoch": 0.6551535516136594,
      "grad_norm": 0.16705434024333954,
      "learning_rate": 0.0001568791946308725,
      "loss": 0.4488,
      "step": 262
    },
    {
      "epoch": 0.6576541376885208,
      "grad_norm": 0.17407532036304474,
      "learning_rate": 0.00015671140939597315,
      "loss": 0.4524,
      "step": 263
    },
    {
      "epoch": 0.660154723763382,
      "grad_norm": 0.17913798987865448,
      "learning_rate": 0.00015654362416107385,
      "loss": 0.4479,
      "step": 264
    },
    {
      "epoch": 0.6626553098382434,
      "grad_norm": 0.1647716462612152,
      "learning_rate": 0.0001563758389261745,
      "loss": 0.4231,
      "step": 265
    },
    {
      "epoch": 0.6651558959131046,
      "grad_norm": 0.20202037692070007,
      "learning_rate": 0.0001562080536912752,
      "loss": 0.4341,
      "step": 266
    },
    {
      "epoch": 0.6676564819879659,
      "grad_norm": 0.16514341533184052,
      "learning_rate": 0.00015604026845637584,
      "loss": 0.4298,
      "step": 267
    },
    {
      "epoch": 0.6701570680628273,
      "grad_norm": 0.18647202849388123,
      "learning_rate": 0.00015587248322147652,
      "loss": 0.4459,
      "step": 268
    },
    {
      "epoch": 0.6726576541376885,
      "grad_norm": 0.1699058711528778,
      "learning_rate": 0.0001557046979865772,
      "loss": 0.45,
      "step": 269
    },
    {
      "epoch": 0.6751582402125498,
      "grad_norm": 0.15985633432865143,
      "learning_rate": 0.00015553691275167785,
      "loss": 0.434,
      "step": 270
    },
    {
      "epoch": 0.6776588262874111,
      "grad_norm": 0.18722815811634064,
      "learning_rate": 0.00015536912751677853,
      "loss": 0.4667,
      "step": 271
    },
    {
      "epoch": 0.6801594123622724,
      "grad_norm": 0.19050948321819305,
      "learning_rate": 0.00015520134228187918,
      "loss": 0.4518,
      "step": 272
    },
    {
      "epoch": 0.6826599984371337,
      "grad_norm": 0.16122502088546753,
      "learning_rate": 0.0001550335570469799,
      "loss": 0.4253,
      "step": 273
    },
    {
      "epoch": 0.685160584511995,
      "grad_norm": 0.19916869699954987,
      "learning_rate": 0.00015486577181208054,
      "loss": 0.4563,
      "step": 274
    },
    {
      "epoch": 0.6876611705868563,
      "grad_norm": 0.16123981773853302,
      "learning_rate": 0.00015469798657718122,
      "loss": 0.4341,
      "step": 275
    },
    {
      "epoch": 0.6901617566617176,
      "grad_norm": 0.1763208657503128,
      "learning_rate": 0.00015453020134228188,
      "loss": 0.437,
      "step": 276
    },
    {
      "epoch": 0.6926623427365789,
      "grad_norm": 0.17635302245616913,
      "learning_rate": 0.00015436241610738256,
      "loss": 0.4443,
      "step": 277
    },
    {
      "epoch": 0.6951629288114402,
      "grad_norm": 0.17334021627902985,
      "learning_rate": 0.00015419463087248324,
      "loss": 0.4571,
      "step": 278
    },
    {
      "epoch": 0.6976635148863015,
      "grad_norm": 0.1741616278886795,
      "learning_rate": 0.0001540268456375839,
      "loss": 0.4286,
      "step": 279
    },
    {
      "epoch": 0.7001641009611628,
      "grad_norm": 0.1762605905532837,
      "learning_rate": 0.00015385906040268457,
      "loss": 0.4433,
      "step": 280
    },
    {
      "epoch": 0.702664687036024,
      "grad_norm": 0.17451149225234985,
      "learning_rate": 0.00015369127516778522,
      "loss": 0.426,
      "step": 281
    },
    {
      "epoch": 0.7051652731108854,
      "grad_norm": 0.16833680868148804,
      "learning_rate": 0.00015352348993288593,
      "loss": 0.44,
      "step": 282
    },
    {
      "epoch": 0.7076658591857466,
      "grad_norm": 0.18105420470237732,
      "learning_rate": 0.00015335570469798658,
      "loss": 0.4415,
      "step": 283
    },
    {
      "epoch": 0.7101664452606079,
      "grad_norm": 0.16717125475406647,
      "learning_rate": 0.00015318791946308726,
      "loss": 0.4353,
      "step": 284
    },
    {
      "epoch": 0.7126670313354693,
      "grad_norm": 0.16678327322006226,
      "learning_rate": 0.00015302013422818794,
      "loss": 0.4171,
      "step": 285
    },
    {
      "epoch": 0.7151676174103305,
      "grad_norm": 0.16035279631614685,
      "learning_rate": 0.0001528523489932886,
      "loss": 0.4553,
      "step": 286
    },
    {
      "epoch": 0.7176682034851919,
      "grad_norm": 0.1686025708913803,
      "learning_rate": 0.00015268456375838927,
      "loss": 0.4301,
      "step": 287
    },
    {
      "epoch": 0.7201687895600531,
      "grad_norm": 0.16823913156986237,
      "learning_rate": 0.00015251677852348993,
      "loss": 0.4426,
      "step": 288
    },
    {
      "epoch": 0.7226693756349144,
      "grad_norm": 0.16710013151168823,
      "learning_rate": 0.0001523489932885906,
      "loss": 0.4258,
      "step": 289
    },
    {
      "epoch": 0.7251699617097758,
      "grad_norm": 0.16891926527023315,
      "learning_rate": 0.00015218120805369129,
      "loss": 0.4316,
      "step": 290
    },
    {
      "epoch": 0.727670547784637,
      "grad_norm": 0.18143802881240845,
      "learning_rate": 0.00015201342281879196,
      "loss": 0.4441,
      "step": 291
    },
    {
      "epoch": 0.7301711338594983,
      "grad_norm": 0.1883898675441742,
      "learning_rate": 0.00015184563758389262,
      "loss": 0.4428,
      "step": 292
    },
    {
      "epoch": 0.7326717199343596,
      "grad_norm": 0.19613900780677795,
      "learning_rate": 0.0001516778523489933,
      "loss": 0.443,
      "step": 293
    },
    {
      "epoch": 0.7351723060092209,
      "grad_norm": 0.16892360150814056,
      "learning_rate": 0.00015151006711409398,
      "loss": 0.4373,
      "step": 294
    },
    {
      "epoch": 0.7376728920840822,
      "grad_norm": 0.1972968578338623,
      "learning_rate": 0.00015134228187919463,
      "loss": 0.4349,
      "step": 295
    },
    {
      "epoch": 0.7401734781589435,
      "grad_norm": 0.1730852872133255,
      "learning_rate": 0.0001511744966442953,
      "loss": 0.4382,
      "step": 296
    },
    {
      "epoch": 0.7426740642338048,
      "grad_norm": 0.1790764033794403,
      "learning_rate": 0.00015100671140939596,
      "loss": 0.4348,
      "step": 297
    },
    {
      "epoch": 0.7451746503086661,
      "grad_norm": 0.20283092558383942,
      "learning_rate": 0.00015083892617449664,
      "loss": 0.4385,
      "step": 298
    },
    {
      "epoch": 0.7476752363835274,
      "grad_norm": 0.17277692258358002,
      "learning_rate": 0.00015067114093959732,
      "loss": 0.4465,
      "step": 299
    },
    {
      "epoch": 0.7501758224583887,
      "grad_norm": 0.19094397127628326,
      "learning_rate": 0.000150503355704698,
      "loss": 0.427,
      "step": 300
    },
    {
      "epoch": 0.75267640853325,
      "grad_norm": 0.17495505511760712,
      "learning_rate": 0.00015033557046979868,
      "loss": 0.4405,
      "step": 301
    },
    {
      "epoch": 0.7551769946081113,
      "grad_norm": 0.1863364279270172,
      "learning_rate": 0.00015016778523489933,
      "loss": 0.4349,
      "step": 302
    },
    {
      "epoch": 0.7576775806829725,
      "grad_norm": 0.185690775513649,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.4465,
      "step": 303
    },
    {
      "epoch": 0.7601781667578339,
      "grad_norm": 0.17615684866905212,
      "learning_rate": 0.00014983221476510067,
      "loss": 0.4521,
      "step": 304
    },
    {
      "epoch": 0.7626787528326952,
      "grad_norm": 0.16942819952964783,
      "learning_rate": 0.00014966442953020135,
      "loss": 0.4493,
      "step": 305
    },
    {
      "epoch": 0.7651793389075564,
      "grad_norm": 0.17781828343868256,
      "learning_rate": 0.00014949664429530203,
      "loss": 0.4497,
      "step": 306
    },
    {
      "epoch": 0.7676799249824178,
      "grad_norm": 0.1723792403936386,
      "learning_rate": 0.00014932885906040268,
      "loss": 0.4274,
      "step": 307
    },
    {
      "epoch": 0.770180511057279,
      "grad_norm": 0.17277772724628448,
      "learning_rate": 0.00014916107382550339,
      "loss": 0.4325,
      "step": 308
    },
    {
      "epoch": 0.7726810971321404,
      "grad_norm": 0.16546839475631714,
      "learning_rate": 0.00014899328859060404,
      "loss": 0.4449,
      "step": 309
    },
    {
      "epoch": 0.7751816832070016,
      "grad_norm": 0.1712421327829361,
      "learning_rate": 0.00014882550335570472,
      "loss": 0.4398,
      "step": 310
    },
    {
      "epoch": 0.7776822692818629,
      "grad_norm": 0.16765455901622772,
      "learning_rate": 0.00014865771812080537,
      "loss": 0.4114,
      "step": 311
    },
    {
      "epoch": 0.7801828553567243,
      "grad_norm": 0.16849608719348907,
      "learning_rate": 0.00014848993288590605,
      "loss": 0.4351,
      "step": 312
    },
    {
      "epoch": 0.7826834414315855,
      "grad_norm": 0.16892583668231964,
      "learning_rate": 0.0001483221476510067,
      "loss": 0.4381,
      "step": 313
    },
    {
      "epoch": 0.7851840275064468,
      "grad_norm": 0.16866593062877655,
      "learning_rate": 0.00014815436241610738,
      "loss": 0.4413,
      "step": 314
    },
    {
      "epoch": 0.7876846135813081,
      "grad_norm": 0.18011045455932617,
      "learning_rate": 0.00014798657718120806,
      "loss": 0.4219,
      "step": 315
    },
    {
      "epoch": 0.7901851996561694,
      "grad_norm": 0.17827914655208588,
      "learning_rate": 0.00014781879194630872,
      "loss": 0.4484,
      "step": 316
    },
    {
      "epoch": 0.7926857857310307,
      "grad_norm": 0.17511065304279327,
      "learning_rate": 0.00014765100671140942,
      "loss": 0.4246,
      "step": 317
    },
    {
      "epoch": 0.795186371805892,
      "grad_norm": 0.17613396048545837,
      "learning_rate": 0.00014748322147651008,
      "loss": 0.432,
      "step": 318
    },
    {
      "epoch": 0.7976869578807533,
      "grad_norm": 0.17050482332706451,
      "learning_rate": 0.00014731543624161076,
      "loss": 0.435,
      "step": 319
    },
    {
      "epoch": 0.8001875439556146,
      "grad_norm": 0.16121627390384674,
      "learning_rate": 0.0001471476510067114,
      "loss": 0.4171,
      "step": 320
    },
    {
      "epoch": 0.8026881300304759,
      "grad_norm": 0.172186940908432,
      "learning_rate": 0.0001469798657718121,
      "loss": 0.4235,
      "step": 321
    },
    {
      "epoch": 0.8051887161053372,
      "grad_norm": 0.16914747655391693,
      "learning_rate": 0.00014681208053691277,
      "loss": 0.4348,
      "step": 322
    },
    {
      "epoch": 0.8076893021801985,
      "grad_norm": 0.16869330406188965,
      "learning_rate": 0.00014664429530201342,
      "loss": 0.4436,
      "step": 323
    },
    {
      "epoch": 0.8101898882550598,
      "grad_norm": 0.16513273119926453,
      "learning_rate": 0.0001464765100671141,
      "loss": 0.4189,
      "step": 324
    },
    {
      "epoch": 0.812690474329921,
      "grad_norm": 0.17720884084701538,
      "learning_rate": 0.00014630872483221478,
      "loss": 0.4351,
      "step": 325
    },
    {
      "epoch": 0.8151910604047824,
      "grad_norm": 0.17662091553211212,
      "learning_rate": 0.00014614093959731546,
      "loss": 0.4325,
      "step": 326
    },
    {
      "epoch": 0.8176916464796437,
      "grad_norm": 0.1817537397146225,
      "learning_rate": 0.0001459731543624161,
      "loss": 0.4587,
      "step": 327
    },
    {
      "epoch": 0.8201922325545049,
      "grad_norm": 0.18581923842430115,
      "learning_rate": 0.0001458053691275168,
      "loss": 0.4397,
      "step": 328
    },
    {
      "epoch": 0.8226928186293663,
      "grad_norm": 0.17366306483745575,
      "learning_rate": 0.00014563758389261744,
      "loss": 0.4343,
      "step": 329
    },
    {
      "epoch": 0.8251934047042275,
      "grad_norm": 0.19753865897655487,
      "learning_rate": 0.00014546979865771812,
      "loss": 0.4268,
      "step": 330
    },
    {
      "epoch": 0.8276939907790889,
      "grad_norm": 0.1656249463558197,
      "learning_rate": 0.0001453020134228188,
      "loss": 0.4319,
      "step": 331
    },
    {
      "epoch": 0.8301945768539502,
      "grad_norm": 0.1635424792766571,
      "learning_rate": 0.00014513422818791946,
      "loss": 0.4461,
      "step": 332
    },
    {
      "epoch": 0.8326951629288114,
      "grad_norm": 0.19888846576213837,
      "learning_rate": 0.00014496644295302014,
      "loss": 0.4129,
      "step": 333
    },
    {
      "epoch": 0.8351957490036728,
      "grad_norm": 0.16208425164222717,
      "learning_rate": 0.00014479865771812082,
      "loss": 0.4337,
      "step": 334
    },
    {
      "epoch": 0.837696335078534,
      "grad_norm": 0.19178390502929688,
      "learning_rate": 0.0001446308724832215,
      "loss": 0.4344,
      "step": 335
    },
    {
      "epoch": 0.8401969211533953,
      "grad_norm": 0.17292825877666473,
      "learning_rate": 0.00014446308724832215,
      "loss": 0.4218,
      "step": 336
    },
    {
      "epoch": 0.8426975072282566,
      "grad_norm": 0.1647634506225586,
      "learning_rate": 0.00014429530201342283,
      "loss": 0.443,
      "step": 337
    },
    {
      "epoch": 0.8451980933031179,
      "grad_norm": 0.18745389580726624,
      "learning_rate": 0.0001441275167785235,
      "loss": 0.4292,
      "step": 338
    },
    {
      "epoch": 0.8476986793779792,
      "grad_norm": 0.20261400938034058,
      "learning_rate": 0.00014395973154362416,
      "loss": 0.4407,
      "step": 339
    },
    {
      "epoch": 0.8501992654528405,
      "grad_norm": 0.16733746230602264,
      "learning_rate": 0.00014379194630872484,
      "loss": 0.432,
      "step": 340
    },
    {
      "epoch": 0.8526998515277018,
      "grad_norm": 0.20043610036373138,
      "learning_rate": 0.0001436241610738255,
      "loss": 0.4403,
      "step": 341
    },
    {
      "epoch": 0.8552004376025631,
      "grad_norm": 0.18660157918930054,
      "learning_rate": 0.00014345637583892617,
      "loss": 0.4177,
      "step": 342
    },
    {
      "epoch": 0.8577010236774244,
      "grad_norm": 0.1695999950170517,
      "learning_rate": 0.00014328859060402685,
      "loss": 0.4173,
      "step": 343
    },
    {
      "epoch": 0.8602016097522857,
      "grad_norm": 0.19332537055015564,
      "learning_rate": 0.00014312080536912753,
      "loss": 0.4196,
      "step": 344
    },
    {
      "epoch": 0.862702195827147,
      "grad_norm": 0.17062701284885406,
      "learning_rate": 0.00014295302013422819,
      "loss": 0.4224,
      "step": 345
    },
    {
      "epoch": 0.8652027819020083,
      "grad_norm": 0.16863779723644257,
      "learning_rate": 0.00014278523489932887,
      "loss": 0.432,
      "step": 346
    },
    {
      "epoch": 0.8677033679768695,
      "grad_norm": 0.19555053114891052,
      "learning_rate": 0.00014261744966442955,
      "loss": 0.4361,
      "step": 347
    },
    {
      "epoch": 0.8702039540517309,
      "grad_norm": 0.1860707402229309,
      "learning_rate": 0.0001424496644295302,
      "loss": 0.43,
      "step": 348
    },
    {
      "epoch": 0.8727045401265922,
      "grad_norm": 0.16459205746650696,
      "learning_rate": 0.00014228187919463088,
      "loss": 0.4459,
      "step": 349
    },
    {
      "epoch": 0.8752051262014535,
      "grad_norm": 0.21114307641983032,
      "learning_rate": 0.00014211409395973153,
      "loss": 0.4382,
      "step": 350
    },
    {
      "epoch": 0.8777057122763148,
      "grad_norm": 0.1811704784631729,
      "learning_rate": 0.0001419463087248322,
      "loss": 0.4303,
      "step": 351
    },
    {
      "epoch": 0.880206298351176,
      "grad_norm": 0.20086246728897095,
      "learning_rate": 0.0001417785234899329,
      "loss": 0.413,
      "step": 352
    },
    {
      "epoch": 0.8827068844260374,
      "grad_norm": 0.17836225032806396,
      "learning_rate": 0.00014161073825503357,
      "loss": 0.4315,
      "step": 353
    },
    {
      "epoch": 0.8852074705008987,
      "grad_norm": 0.1710200011730194,
      "learning_rate": 0.00014144295302013425,
      "loss": 0.4331,
      "step": 354
    },
    {
      "epoch": 0.8877080565757599,
      "grad_norm": 0.17866557836532593,
      "learning_rate": 0.0001412751677852349,
      "loss": 0.4203,
      "step": 355
    },
    {
      "epoch": 0.8902086426506213,
      "grad_norm": 0.19929209351539612,
      "learning_rate": 0.00014110738255033558,
      "loss": 0.4251,
      "step": 356
    },
    {
      "epoch": 0.8927092287254825,
      "grad_norm": 0.1633501946926117,
      "learning_rate": 0.00014093959731543624,
      "loss": 0.4168,
      "step": 357
    },
    {
      "epoch": 0.8952098148003438,
      "grad_norm": 0.19982637465000153,
      "learning_rate": 0.00014077181208053691,
      "loss": 0.4279,
      "step": 358
    },
    {
      "epoch": 0.8977104008752052,
      "grad_norm": 0.2030080407857895,
      "learning_rate": 0.0001406040268456376,
      "loss": 0.4565,
      "step": 359
    },
    {
      "epoch": 0.9002109869500664,
      "grad_norm": 0.17041054368019104,
      "learning_rate": 0.00014043624161073827,
      "loss": 0.447,
      "step": 360
    },
    {
      "epoch": 0.9027115730249278,
      "grad_norm": 0.19890151917934418,
      "learning_rate": 0.00014026845637583895,
      "loss": 0.4212,
      "step": 361
    },
    {
      "epoch": 0.905212159099789,
      "grad_norm": 0.21048621833324432,
      "learning_rate": 0.0001401006711409396,
      "loss": 0.4271,
      "step": 362
    },
    {
      "epoch": 0.9077127451746503,
      "grad_norm": 0.16634558141231537,
      "learning_rate": 0.0001399328859060403,
      "loss": 0.4408,
      "step": 363
    },
    {
      "epoch": 0.9102133312495116,
      "grad_norm": 0.2424069195985794,
      "learning_rate": 0.00013976510067114094,
      "loss": 0.4445,
      "step": 364
    },
    {
      "epoch": 0.9127139173243729,
      "grad_norm": 0.16701576113700867,
      "learning_rate": 0.00013959731543624162,
      "loss": 0.4203,
      "step": 365
    },
    {
      "epoch": 0.9152145033992342,
      "grad_norm": 0.17247918248176575,
      "learning_rate": 0.00013942953020134227,
      "loss": 0.4283,
      "step": 366
    },
    {
      "epoch": 0.9177150894740955,
      "grad_norm": 0.19492937624454498,
      "learning_rate": 0.00013926174496644295,
      "loss": 0.4363,
      "step": 367
    },
    {
      "epoch": 0.9202156755489568,
      "grad_norm": 0.16968198120594025,
      "learning_rate": 0.00013909395973154363,
      "loss": 0.4157,
      "step": 368
    },
    {
      "epoch": 0.922716261623818,
      "grad_norm": 0.15889081358909607,
      "learning_rate": 0.0001389261744966443,
      "loss": 0.4557,
      "step": 369
    },
    {
      "epoch": 0.9252168476986794,
      "grad_norm": 0.20287366211414337,
      "learning_rate": 0.000138758389261745,
      "loss": 0.4316,
      "step": 370
    },
    {
      "epoch": 0.9277174337735407,
      "grad_norm": 0.18467019498348236,
      "learning_rate": 0.00013859060402684564,
      "loss": 0.4193,
      "step": 371
    },
    {
      "epoch": 0.930218019848402,
      "grad_norm": 0.16602379083633423,
      "learning_rate": 0.00013842281879194632,
      "loss": 0.4291,
      "step": 372
    },
    {
      "epoch": 0.9327186059232633,
      "grad_norm": 0.19791395962238312,
      "learning_rate": 0.00013825503355704698,
      "loss": 0.4242,
      "step": 373
    },
    {
      "epoch": 0.9352191919981245,
      "grad_norm": 0.17725242674350739,
      "learning_rate": 0.00013808724832214766,
      "loss": 0.4268,
      "step": 374
    },
    {
      "epoch": 0.9377197780729859,
      "grad_norm": 0.16493122279644012,
      "learning_rate": 0.00013791946308724834,
      "loss": 0.4289,
      "step": 375
    },
    {
      "epoch": 0.9402203641478472,
      "grad_norm": 0.1670459806919098,
      "learning_rate": 0.000137751677852349,
      "loss": 0.4393,
      "step": 376
    },
    {
      "epoch": 0.9427209502227084,
      "grad_norm": 0.19634924829006195,
      "learning_rate": 0.00013758389261744967,
      "loss": 0.4224,
      "step": 377
    },
    {
      "epoch": 0.9452215362975698,
      "grad_norm": 0.1566496044397354,
      "learning_rate": 0.00013741610738255035,
      "loss": 0.4306,
      "step": 378
    },
    {
      "epoch": 0.947722122372431,
      "grad_norm": 0.1697397530078888,
      "learning_rate": 0.00013724832214765103,
      "loss": 0.4159,
      "step": 379
    },
    {
      "epoch": 0.9502227084472923,
      "grad_norm": 0.18244680762290955,
      "learning_rate": 0.00013708053691275168,
      "loss": 0.4325,
      "step": 380
    },
    {
      "epoch": 0.9527232945221537,
      "grad_norm": 0.16451160609722137,
      "learning_rate": 0.00013691275167785236,
      "loss": 0.4224,
      "step": 381
    },
    {
      "epoch": 0.9552238805970149,
      "grad_norm": 0.20068246126174927,
      "learning_rate": 0.000136744966442953,
      "loss": 0.4217,
      "step": 382
    },
    {
      "epoch": 0.9577244666718763,
      "grad_norm": 0.19040897488594055,
      "learning_rate": 0.0001365771812080537,
      "loss": 0.4266,
      "step": 383
    },
    {
      "epoch": 0.9602250527467375,
      "grad_norm": 0.16136051714420319,
      "learning_rate": 0.00013640939597315437,
      "loss": 0.4267,
      "step": 384
    },
    {
      "epoch": 0.9627256388215988,
      "grad_norm": 0.1725684553384781,
      "learning_rate": 0.00013624161073825503,
      "loss": 0.4385,
      "step": 385
    },
    {
      "epoch": 0.9652262248964601,
      "grad_norm": 0.2096080183982849,
      "learning_rate": 0.0001360738255033557,
      "loss": 0.4163,
      "step": 386
    },
    {
      "epoch": 0.9677268109713214,
      "grad_norm": 0.16560566425323486,
      "learning_rate": 0.00013590604026845639,
      "loss": 0.4403,
      "step": 387
    },
    {
      "epoch": 0.9702273970461827,
      "grad_norm": 0.18897269666194916,
      "learning_rate": 0.00013573825503355706,
      "loss": 0.415,
      "step": 388
    },
    {
      "epoch": 0.972727983121044,
      "grad_norm": 0.18220849335193634,
      "learning_rate": 0.00013557046979865772,
      "loss": 0.4281,
      "step": 389
    },
    {
      "epoch": 0.9752285691959053,
      "grad_norm": 0.16022995114326477,
      "learning_rate": 0.0001354026845637584,
      "loss": 0.4101,
      "step": 390
    },
    {
      "epoch": 0.9777291552707665,
      "grad_norm": 0.17846792936325073,
      "learning_rate": 0.00013523489932885908,
      "loss": 0.4399,
      "step": 391
    },
    {
      "epoch": 0.9802297413456279,
      "grad_norm": 0.17017945647239685,
      "learning_rate": 0.00013506711409395973,
      "loss": 0.4176,
      "step": 392
    },
    {
      "epoch": 0.9827303274204892,
      "grad_norm": 0.1695704609155655,
      "learning_rate": 0.0001348993288590604,
      "loss": 0.4421,
      "step": 393
    },
    {
      "epoch": 0.9852309134953505,
      "grad_norm": 0.1747402846813202,
      "learning_rate": 0.00013473154362416106,
      "loss": 0.4268,
      "step": 394
    },
    {
      "epoch": 0.9877314995702118,
      "grad_norm": 0.1625954657793045,
      "learning_rate": 0.00013456375838926174,
      "loss": 0.4095,
      "step": 395
    },
    {
      "epoch": 0.990232085645073,
      "grad_norm": 0.1669810563325882,
      "learning_rate": 0.00013439597315436242,
      "loss": 0.4258,
      "step": 396
    },
    {
      "epoch": 0.9927326717199344,
      "grad_norm": 0.1578301340341568,
      "learning_rate": 0.0001342281879194631,
      "loss": 0.4155,
      "step": 397
    },
    {
      "epoch": 0.9952332577947957,
      "grad_norm": 0.17688880860805511,
      "learning_rate": 0.00013406040268456378,
      "loss": 0.4338,
      "step": 398
    },
    {
      "epoch": 0.9977338438696569,
      "grad_norm": 0.18112221360206604,
      "learning_rate": 0.00013389261744966443,
      "loss": 0.4057,
      "step": 399
    },
    {
      "epoch": 1.0002344299445183,
      "grad_norm": 0.1682415008544922,
      "learning_rate": 0.00013372483221476511,
      "loss": 0.4413,
      "step": 400
    },
    {
      "epoch": 1.0027350160193795,
      "grad_norm": 0.17804764211177826,
      "learning_rate": 0.00013355704697986577,
      "loss": 0.402,
      "step": 401
    },
    {
      "epoch": 1.0052356020942408,
      "grad_norm": 0.17376191914081573,
      "learning_rate": 0.00013338926174496645,
      "loss": 0.4052,
      "step": 402
    },
    {
      "epoch": 1.007736188169102,
      "grad_norm": 0.17517007887363434,
      "learning_rate": 0.0001332214765100671,
      "loss": 0.4019,
      "step": 403
    },
    {
      "epoch": 1.0102367742439635,
      "grad_norm": 0.1827448606491089,
      "learning_rate": 0.0001330536912751678,
      "loss": 0.3953,
      "step": 404
    },
    {
      "epoch": 1.0127373603188248,
      "grad_norm": 0.16910028457641602,
      "learning_rate": 0.00013288590604026846,
      "loss": 0.3991,
      "step": 405
    },
    {
      "epoch": 1.015237946393686,
      "grad_norm": 0.18308071792125702,
      "learning_rate": 0.00013271812080536914,
      "loss": 0.3878,
      "step": 406
    },
    {
      "epoch": 1.0177385324685473,
      "grad_norm": 0.20386648178100586,
      "learning_rate": 0.00013255033557046982,
      "loss": 0.402,
      "step": 407
    },
    {
      "epoch": 1.0202391185434085,
      "grad_norm": 0.16715078055858612,
      "learning_rate": 0.00013238255033557047,
      "loss": 0.4025,
      "step": 408
    },
    {
      "epoch": 1.02273970461827,
      "grad_norm": 0.18801377713680267,
      "learning_rate": 0.00013221476510067115,
      "loss": 0.4062,
      "step": 409
    },
    {
      "epoch": 1.0252402906931313,
      "grad_norm": 0.1752709448337555,
      "learning_rate": 0.0001320469798657718,
      "loss": 0.4003,
      "step": 410
    },
    {
      "epoch": 1.0277408767679925,
      "grad_norm": 0.16399900615215302,
      "learning_rate": 0.00013187919463087248,
      "loss": 0.396,
      "step": 411
    },
    {
      "epoch": 1.0302414628428538,
      "grad_norm": 0.2031196504831314,
      "learning_rate": 0.00013171140939597316,
      "loss": 0.4086,
      "step": 412
    },
    {
      "epoch": 1.032742048917715,
      "grad_norm": 0.17596857249736786,
      "learning_rate": 0.00013154362416107384,
      "loss": 0.394,
      "step": 413
    },
    {
      "epoch": 1.0352426349925763,
      "grad_norm": 0.1620572954416275,
      "learning_rate": 0.00013137583892617452,
      "loss": 0.3983,
      "step": 414
    },
    {
      "epoch": 1.0377432210674378,
      "grad_norm": 0.1825663447380066,
      "learning_rate": 0.00013120805369127518,
      "loss": 0.4103,
      "step": 415
    },
    {
      "epoch": 1.040243807142299,
      "grad_norm": 0.19497060775756836,
      "learning_rate": 0.00013104026845637586,
      "loss": 0.3989,
      "step": 416
    },
    {
      "epoch": 1.0427443932171603,
      "grad_norm": 0.1783512830734253,
      "learning_rate": 0.0001308724832214765,
      "loss": 0.3952,
      "step": 417
    },
    {
      "epoch": 1.0452449792920215,
      "grad_norm": 0.17473211884498596,
      "learning_rate": 0.0001307046979865772,
      "loss": 0.3901,
      "step": 418
    },
    {
      "epoch": 1.0477455653668828,
      "grad_norm": 0.1653796285390854,
      "learning_rate": 0.00013053691275167784,
      "loss": 0.38,
      "step": 419
    },
    {
      "epoch": 1.050246151441744,
      "grad_norm": 0.17586909234523773,
      "learning_rate": 0.00013036912751677852,
      "loss": 0.4026,
      "step": 420
    },
    {
      "epoch": 1.0527467375166055,
      "grad_norm": 0.16513925790786743,
      "learning_rate": 0.0001302013422818792,
      "loss": 0.3922,
      "step": 421
    },
    {
      "epoch": 1.0552473235914668,
      "grad_norm": 0.20568743348121643,
      "learning_rate": 0.00013003355704697988,
      "loss": 0.3996,
      "step": 422
    },
    {
      "epoch": 1.057747909666328,
      "grad_norm": 0.1725350171327591,
      "learning_rate": 0.00012986577181208056,
      "loss": 0.3912,
      "step": 423
    },
    {
      "epoch": 1.0602484957411893,
      "grad_norm": 0.17537754774093628,
      "learning_rate": 0.0001296979865771812,
      "loss": 0.3893,
      "step": 424
    },
    {
      "epoch": 1.0627490818160505,
      "grad_norm": 0.17607562243938446,
      "learning_rate": 0.0001295302013422819,
      "loss": 0.3894,
      "step": 425
    },
    {
      "epoch": 1.065249667890912,
      "grad_norm": 0.16470113396644592,
      "learning_rate": 0.00012936241610738254,
      "loss": 0.391,
      "step": 426
    },
    {
      "epoch": 1.0677502539657733,
      "grad_norm": 0.17240354418754578,
      "learning_rate": 0.00012919463087248322,
      "loss": 0.392,
      "step": 427
    },
    {
      "epoch": 1.0702508400406345,
      "grad_norm": 0.17529991269111633,
      "learning_rate": 0.0001290268456375839,
      "loss": 0.3953,
      "step": 428
    },
    {
      "epoch": 1.0727514261154958,
      "grad_norm": 0.17728881537914276,
      "learning_rate": 0.00012885906040268456,
      "loss": 0.3818,
      "step": 429
    },
    {
      "epoch": 1.075252012190357,
      "grad_norm": 0.17223317921161652,
      "learning_rate": 0.00012869127516778524,
      "loss": 0.3825,
      "step": 430
    },
    {
      "epoch": 1.0777525982652185,
      "grad_norm": 0.18325600028038025,
      "learning_rate": 0.00012852348993288592,
      "loss": 0.3927,
      "step": 431
    },
    {
      "epoch": 1.0802531843400798,
      "grad_norm": 0.17309826612472534,
      "learning_rate": 0.0001283557046979866,
      "loss": 0.3942,
      "step": 432
    },
    {
      "epoch": 1.082753770414941,
      "grad_norm": 0.1761365830898285,
      "learning_rate": 0.00012818791946308725,
      "loss": 0.3958,
      "step": 433
    },
    {
      "epoch": 1.0852543564898023,
      "grad_norm": 0.18157604336738586,
      "learning_rate": 0.00012802013422818793,
      "loss": 0.3894,
      "step": 434
    },
    {
      "epoch": 1.0877549425646635,
      "grad_norm": 0.17641478776931763,
      "learning_rate": 0.0001278523489932886,
      "loss": 0.3872,
      "step": 435
    },
    {
      "epoch": 1.0902555286395248,
      "grad_norm": 0.1755024641752243,
      "learning_rate": 0.00012768456375838926,
      "loss": 0.4044,
      "step": 436
    },
    {
      "epoch": 1.0927561147143863,
      "grad_norm": 0.17728440463542938,
      "learning_rate": 0.00012751677852348994,
      "loss": 0.4024,
      "step": 437
    },
    {
      "epoch": 1.0952567007892475,
      "grad_norm": 0.18590691685676575,
      "learning_rate": 0.0001273489932885906,
      "loss": 0.4054,
      "step": 438
    },
    {
      "epoch": 1.0977572868641088,
      "grad_norm": 0.16991455852985382,
      "learning_rate": 0.0001271812080536913,
      "loss": 0.3892,
      "step": 439
    },
    {
      "epoch": 1.10025787293897,
      "grad_norm": 0.18331153690814972,
      "learning_rate": 0.00012701342281879195,
      "loss": 0.3946,
      "step": 440
    },
    {
      "epoch": 1.1027584590138313,
      "grad_norm": 0.17147310078144073,
      "learning_rate": 0.00012684563758389263,
      "loss": 0.3841,
      "step": 441
    },
    {
      "epoch": 1.1052590450886925,
      "grad_norm": 0.1769578754901886,
      "learning_rate": 0.00012667785234899329,
      "loss": 0.4014,
      "step": 442
    },
    {
      "epoch": 1.107759631163554,
      "grad_norm": 0.1756420135498047,
      "learning_rate": 0.00012651006711409397,
      "loss": 0.4177,
      "step": 443
    },
    {
      "epoch": 1.1102602172384153,
      "grad_norm": 0.1766512542963028,
      "learning_rate": 0.00012634228187919465,
      "loss": 0.3983,
      "step": 444
    },
    {
      "epoch": 1.1127608033132765,
      "grad_norm": 0.16898678243160248,
      "learning_rate": 0.0001261744966442953,
      "loss": 0.3915,
      "step": 445
    },
    {
      "epoch": 1.1152613893881378,
      "grad_norm": 0.17253310978412628,
      "learning_rate": 0.00012600671140939598,
      "loss": 0.3954,
      "step": 446
    },
    {
      "epoch": 1.117761975462999,
      "grad_norm": 0.17454257607460022,
      "learning_rate": 0.00012583892617449663,
      "loss": 0.3984,
      "step": 447
    },
    {
      "epoch": 1.1202625615378605,
      "grad_norm": 0.17149844765663147,
      "learning_rate": 0.00012567114093959734,
      "loss": 0.3912,
      "step": 448
    },
    {
      "epoch": 1.1227631476127218,
      "grad_norm": 0.17389146983623505,
      "learning_rate": 0.000125503355704698,
      "loss": 0.4149,
      "step": 449
    },
    {
      "epoch": 1.125263733687583,
      "grad_norm": 0.16737361252307892,
      "learning_rate": 0.00012533557046979867,
      "loss": 0.3889,
      "step": 450
    },
    {
      "epoch": 1.1277643197624443,
      "grad_norm": 0.1793391853570938,
      "learning_rate": 0.00012516778523489935,
      "loss": 0.4098,
      "step": 451
    },
    {
      "epoch": 1.1302649058373055,
      "grad_norm": 0.18140512704849243,
      "learning_rate": 0.000125,
      "loss": 0.4167,
      "step": 452
    },
    {
      "epoch": 1.132765491912167,
      "grad_norm": 0.16896022856235504,
      "learning_rate": 0.00012483221476510068,
      "loss": 0.3959,
      "step": 453
    },
    {
      "epoch": 1.1352660779870283,
      "grad_norm": 0.18008409440517426,
      "learning_rate": 0.00012466442953020134,
      "loss": 0.3892,
      "step": 454
    },
    {
      "epoch": 1.1377666640618895,
      "grad_norm": 0.17115534842014313,
      "learning_rate": 0.00012449664429530201,
      "loss": 0.3937,
      "step": 455
    },
    {
      "epoch": 1.1402672501367508,
      "grad_norm": 0.18967628479003906,
      "learning_rate": 0.00012432885906040267,
      "loss": 0.3992,
      "step": 456
    },
    {
      "epoch": 1.142767836211612,
      "grad_norm": 0.18216951191425323,
      "learning_rate": 0.00012416107382550337,
      "loss": 0.4089,
      "step": 457
    },
    {
      "epoch": 1.1452684222864733,
      "grad_norm": 0.19067801535129547,
      "learning_rate": 0.00012399328859060403,
      "loss": 0.3811,
      "step": 458
    },
    {
      "epoch": 1.1477690083613348,
      "grad_norm": 0.17509539425373077,
      "learning_rate": 0.0001238255033557047,
      "loss": 0.3821,
      "step": 459
    },
    {
      "epoch": 1.150269594436196,
      "grad_norm": 0.16954122483730316,
      "learning_rate": 0.0001236577181208054,
      "loss": 0.3856,
      "step": 460
    },
    {
      "epoch": 1.1527701805110573,
      "grad_norm": 0.19434818625450134,
      "learning_rate": 0.00012348993288590604,
      "loss": 0.3823,
      "step": 461
    },
    {
      "epoch": 1.1552707665859185,
      "grad_norm": 0.1899290233850479,
      "learning_rate": 0.00012332214765100672,
      "loss": 0.3957,
      "step": 462
    },
    {
      "epoch": 1.1577713526607798,
      "grad_norm": 0.1762360781431198,
      "learning_rate": 0.00012315436241610737,
      "loss": 0.3802,
      "step": 463
    },
    {
      "epoch": 1.160271938735641,
      "grad_norm": 0.19524188339710236,
      "learning_rate": 0.00012298657718120805,
      "loss": 0.4001,
      "step": 464
    },
    {
      "epoch": 1.1627725248105025,
      "grad_norm": 0.17824076116085052,
      "learning_rate": 0.00012281879194630873,
      "loss": 0.4001,
      "step": 465
    },
    {
      "epoch": 1.1652731108853638,
      "grad_norm": 0.18208450078964233,
      "learning_rate": 0.0001226510067114094,
      "loss": 0.3961,
      "step": 466
    },
    {
      "epoch": 1.167773696960225,
      "grad_norm": 0.17536821961402893,
      "learning_rate": 0.0001224832214765101,
      "loss": 0.3976,
      "step": 467
    },
    {
      "epoch": 1.1702742830350863,
      "grad_norm": 0.17048102617263794,
      "learning_rate": 0.00012231543624161074,
      "loss": 0.3874,
      "step": 468
    },
    {
      "epoch": 1.1727748691099475,
      "grad_norm": 0.186661958694458,
      "learning_rate": 0.00012214765100671142,
      "loss": 0.4077,
      "step": 469
    },
    {
      "epoch": 1.175275455184809,
      "grad_norm": 0.17875522375106812,
      "learning_rate": 0.00012197986577181209,
      "loss": 0.3976,
      "step": 470
    },
    {
      "epoch": 1.1777760412596703,
      "grad_norm": 0.17223358154296875,
      "learning_rate": 0.00012181208053691276,
      "loss": 0.3941,
      "step": 471
    },
    {
      "epoch": 1.1802766273345315,
      "grad_norm": 0.1784411072731018,
      "learning_rate": 0.00012164429530201342,
      "loss": 0.3918,
      "step": 472
    },
    {
      "epoch": 1.1827772134093928,
      "grad_norm": 0.176781564950943,
      "learning_rate": 0.00012147651006711409,
      "loss": 0.3879,
      "step": 473
    },
    {
      "epoch": 1.185277799484254,
      "grad_norm": 0.18470625579357147,
      "learning_rate": 0.00012130872483221478,
      "loss": 0.3806,
      "step": 474
    },
    {
      "epoch": 1.1877783855591155,
      "grad_norm": 0.1847718358039856,
      "learning_rate": 0.00012114093959731545,
      "loss": 0.3999,
      "step": 475
    },
    {
      "epoch": 1.1902789716339768,
      "grad_norm": 0.18402062356472015,
      "learning_rate": 0.00012097315436241611,
      "loss": 0.3905,
      "step": 476
    },
    {
      "epoch": 1.192779557708838,
      "grad_norm": 0.1812908798456192,
      "learning_rate": 0.0001208053691275168,
      "loss": 0.3821,
      "step": 477
    },
    {
      "epoch": 1.1952801437836993,
      "grad_norm": 0.18111836910247803,
      "learning_rate": 0.00012063758389261746,
      "loss": 0.3902,
      "step": 478
    },
    {
      "epoch": 1.1977807298585605,
      "grad_norm": 0.17667655646800995,
      "learning_rate": 0.00012046979865771813,
      "loss": 0.3829,
      "step": 479
    },
    {
      "epoch": 1.2002813159334218,
      "grad_norm": 0.17511925101280212,
      "learning_rate": 0.00012030201342281879,
      "loss": 0.3882,
      "step": 480
    },
    {
      "epoch": 1.2027819020082833,
      "grad_norm": 0.1772802323102951,
      "learning_rate": 0.00012013422818791946,
      "loss": 0.3963,
      "step": 481
    },
    {
      "epoch": 1.2052824880831445,
      "grad_norm": 0.17284731566905975,
      "learning_rate": 0.00011996644295302013,
      "loss": 0.3918,
      "step": 482
    },
    {
      "epoch": 1.2077830741580058,
      "grad_norm": 0.18320755660533905,
      "learning_rate": 0.00011979865771812082,
      "loss": 0.4003,
      "step": 483
    },
    {
      "epoch": 1.210283660232867,
      "grad_norm": 0.1786193549633026,
      "learning_rate": 0.00011963087248322149,
      "loss": 0.4007,
      "step": 484
    },
    {
      "epoch": 1.2127842463077283,
      "grad_norm": 0.17019547522068024,
      "learning_rate": 0.00011946308724832216,
      "loss": 0.3973,
      "step": 485
    },
    {
      "epoch": 1.2152848323825896,
      "grad_norm": 0.187973752617836,
      "learning_rate": 0.00011929530201342283,
      "loss": 0.4242,
      "step": 486
    },
    {
      "epoch": 1.217785418457451,
      "grad_norm": 0.17459571361541748,
      "learning_rate": 0.0001191275167785235,
      "loss": 0.3957,
      "step": 487
    },
    {
      "epoch": 1.2202860045323123,
      "grad_norm": 0.186808243393898,
      "learning_rate": 0.00011895973154362416,
      "loss": 0.3809,
      "step": 488
    },
    {
      "epoch": 1.2227865906071735,
      "grad_norm": 0.1886894702911377,
      "learning_rate": 0.00011879194630872483,
      "loss": 0.3999,
      "step": 489
    },
    {
      "epoch": 1.2252871766820348,
      "grad_norm": 0.17145392298698425,
      "learning_rate": 0.0001186241610738255,
      "loss": 0.3792,
      "step": 490
    },
    {
      "epoch": 1.227787762756896,
      "grad_norm": 0.18122152984142303,
      "learning_rate": 0.00011845637583892618,
      "loss": 0.3954,
      "step": 491
    },
    {
      "epoch": 1.2302883488317575,
      "grad_norm": 0.194286048412323,
      "learning_rate": 0.00011828859060402686,
      "loss": 0.3825,
      "step": 492
    },
    {
      "epoch": 1.2327889349066188,
      "grad_norm": 0.17431862652301788,
      "learning_rate": 0.00011812080536912754,
      "loss": 0.3871,
      "step": 493
    },
    {
      "epoch": 1.23528952098148,
      "grad_norm": 0.19097591936588287,
      "learning_rate": 0.0001179530201342282,
      "loss": 0.4018,
      "step": 494
    },
    {
      "epoch": 1.2377901070563413,
      "grad_norm": 0.18145328760147095,
      "learning_rate": 0.00011778523489932887,
      "loss": 0.3874,
      "step": 495
    },
    {
      "epoch": 1.2402906931312025,
      "grad_norm": 0.1778709590435028,
      "learning_rate": 0.00011761744966442953,
      "loss": 0.3955,
      "step": 496
    },
    {
      "epoch": 1.242791279206064,
      "grad_norm": 0.20905902981758118,
      "learning_rate": 0.0001174496644295302,
      "loss": 0.398,
      "step": 497
    },
    {
      "epoch": 1.2452918652809253,
      "grad_norm": 0.19288387894630432,
      "learning_rate": 0.00011728187919463087,
      "loss": 0.4031,
      "step": 498
    },
    {
      "epoch": 1.2477924513557865,
      "grad_norm": 0.19638553261756897,
      "learning_rate": 0.00011711409395973155,
      "loss": 0.3967,
      "step": 499
    },
    {
      "epoch": 1.2502930374306478,
      "grad_norm": 0.18342918157577515,
      "learning_rate": 0.00011694630872483221,
      "loss": 0.3844,
      "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": 1.0433548385273856e+18,
  "train_batch_size": 5,
  "trial_name": null,
  "trial_params": null
}