{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.5043731778425657,
  "eval_steps": 500,
  "global_step": 516,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0029154518950437317,
      "grad_norm": 1.96997298809509,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.4888,
      "step": 1
    },
    {
      "epoch": 0.0058309037900874635,
      "grad_norm": 2.0593671952568466,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.5633,
      "step": 2
    },
    {
      "epoch": 0.008746355685131196,
      "grad_norm": 2.0558980680243,
      "learning_rate": 3e-06,
      "loss": 1.4922,
      "step": 3
    },
    {
      "epoch": 0.011661807580174927,
      "grad_norm": 2.0407653033784907,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.5552,
      "step": 4
    },
    {
      "epoch": 0.014577259475218658,
      "grad_norm": 2.049565870762043,
      "learning_rate": 5e-06,
      "loss": 1.4963,
      "step": 5
    },
    {
      "epoch": 0.01749271137026239,
      "grad_norm": 1.8921551243504868,
      "learning_rate": 6e-06,
      "loss": 1.4756,
      "step": 6
    },
    {
      "epoch": 0.02040816326530612,
      "grad_norm": 1.9932142025756485,
      "learning_rate": 7e-06,
      "loss": 1.4733,
      "step": 7
    },
    {
      "epoch": 0.023323615160349854,
      "grad_norm": 1.8344452830038493,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.4998,
      "step": 8
    },
    {
      "epoch": 0.026239067055393587,
      "grad_norm": 3.1185523094664664,
      "learning_rate": 9e-06,
      "loss": 1.4562,
      "step": 9
    },
    {
      "epoch": 0.029154518950437316,
      "grad_norm": 1.3193772173204783,
      "learning_rate": 1e-05,
      "loss": 1.4078,
      "step": 10
    },
    {
      "epoch": 0.03206997084548105,
      "grad_norm": 1.4291215496905525,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 1.3631,
      "step": 11
    },
    {
      "epoch": 0.03498542274052478,
      "grad_norm": 1.0345538651419202,
      "learning_rate": 1.2e-05,
      "loss": 1.2687,
      "step": 12
    },
    {
      "epoch": 0.037900874635568516,
      "grad_norm": 0.8509765803387165,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 1.2788,
      "step": 13
    },
    {
      "epoch": 0.04081632653061224,
      "grad_norm": 0.7122306203690422,
      "learning_rate": 1.4e-05,
      "loss": 1.2479,
      "step": 14
    },
    {
      "epoch": 0.043731778425655975,
      "grad_norm": 0.6858784204503546,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 1.312,
      "step": 15
    },
    {
      "epoch": 0.04664723032069971,
      "grad_norm": 0.8402421437953252,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.2104,
      "step": 16
    },
    {
      "epoch": 0.04956268221574344,
      "grad_norm": 0.9216616450448899,
      "learning_rate": 1.7e-05,
      "loss": 1.2521,
      "step": 17
    },
    {
      "epoch": 0.052478134110787174,
      "grad_norm": 0.9921691551642605,
      "learning_rate": 1.8e-05,
      "loss": 1.2179,
      "step": 18
    },
    {
      "epoch": 0.05539358600583091,
      "grad_norm": 1.022423689479842,
      "learning_rate": 1.9e-05,
      "loss": 1.1792,
      "step": 19
    },
    {
      "epoch": 0.05830903790087463,
      "grad_norm": 1.0879189463724102,
      "learning_rate": 2e-05,
      "loss": 1.1985,
      "step": 20
    },
    {
      "epoch": 0.061224489795918366,
      "grad_norm": 1.0207736739226028,
      "learning_rate": 2.1000000000000002e-05,
      "loss": 1.2144,
      "step": 21
    },
    {
      "epoch": 0.0641399416909621,
      "grad_norm": 0.977515728831309,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 1.2368,
      "step": 22
    },
    {
      "epoch": 0.06705539358600583,
      "grad_norm": 0.8388691896742322,
      "learning_rate": 2.3e-05,
      "loss": 1.1545,
      "step": 23
    },
    {
      "epoch": 0.06997084548104957,
      "grad_norm": 0.7188235107709924,
      "learning_rate": 2.4e-05,
      "loss": 1.2304,
      "step": 24
    },
    {
      "epoch": 0.0728862973760933,
      "grad_norm": 0.6257931373002115,
      "learning_rate": 2.5e-05,
      "loss": 1.1733,
      "step": 25
    },
    {
      "epoch": 0.07580174927113703,
      "grad_norm": 0.5237685387486158,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 1.1693,
      "step": 26
    },
    {
      "epoch": 0.07871720116618076,
      "grad_norm": 0.5989713165204653,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 1.2331,
      "step": 27
    },
    {
      "epoch": 0.08163265306122448,
      "grad_norm": 0.5869524805948223,
      "learning_rate": 2.8e-05,
      "loss": 1.2142,
      "step": 28
    },
    {
      "epoch": 0.08454810495626822,
      "grad_norm": 0.6720149885989607,
      "learning_rate": 2.9e-05,
      "loss": 1.1472,
      "step": 29
    },
    {
      "epoch": 0.08746355685131195,
      "grad_norm": 0.73864045163312,
      "learning_rate": 3.0000000000000004e-05,
      "loss": 1.1908,
      "step": 30
    },
    {
      "epoch": 0.09037900874635568,
      "grad_norm": 0.6759314678600088,
      "learning_rate": 3.1e-05,
      "loss": 1.1971,
      "step": 31
    },
    {
      "epoch": 0.09329446064139942,
      "grad_norm": 0.7251126641398837,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.1809,
      "step": 32
    },
    {
      "epoch": 0.09620991253644315,
      "grad_norm": 0.6691450174305634,
      "learning_rate": 3.3e-05,
      "loss": 1.1753,
      "step": 33
    },
    {
      "epoch": 0.09912536443148688,
      "grad_norm": 0.5339684032344343,
      "learning_rate": 3.4e-05,
      "loss": 1.1597,
      "step": 34
    },
    {
      "epoch": 0.10204081632653061,
      "grad_norm": 0.4919690310909855,
      "learning_rate": 3.5000000000000004e-05,
      "loss": 1.1721,
      "step": 35
    },
    {
      "epoch": 0.10495626822157435,
      "grad_norm": 0.42018891979017214,
      "learning_rate": 3.6e-05,
      "loss": 1.1644,
      "step": 36
    },
    {
      "epoch": 0.10787172011661808,
      "grad_norm": 0.5490256316108622,
      "learning_rate": 3.7000000000000005e-05,
      "loss": 1.2463,
      "step": 37
    },
    {
      "epoch": 0.11078717201166181,
      "grad_norm": 0.5427250875445369,
      "learning_rate": 3.8e-05,
      "loss": 1.1137,
      "step": 38
    },
    {
      "epoch": 0.11370262390670553,
      "grad_norm": 0.5778225846177277,
      "learning_rate": 3.9e-05,
      "loss": 1.2072,
      "step": 39
    },
    {
      "epoch": 0.11661807580174927,
      "grad_norm": 0.693680585719681,
      "learning_rate": 4e-05,
      "loss": 1.1519,
      "step": 40
    },
    {
      "epoch": 0.119533527696793,
      "grad_norm": 0.6127902830311082,
      "learning_rate": 3.999976349852511e-05,
      "loss": 1.1104,
      "step": 41
    },
    {
      "epoch": 0.12244897959183673,
      "grad_norm": 0.6799487970334515,
      "learning_rate": 3.999905399969373e-05,
      "loss": 1.1175,
      "step": 42
    },
    {
      "epoch": 0.12536443148688048,
      "grad_norm": 0.5367363097182918,
      "learning_rate": 3.999787152028561e-05,
      "loss": 1.1483,
      "step": 43
    },
    {
      "epoch": 0.1282798833819242,
      "grad_norm": 0.4524657560624909,
      "learning_rate": 3.999621608826657e-05,
      "loss": 1.138,
      "step": 44
    },
    {
      "epoch": 0.13119533527696792,
      "grad_norm": 0.41206360481350807,
      "learning_rate": 3.999408774278781e-05,
      "loss": 1.1245,
      "step": 45
    },
    {
      "epoch": 0.13411078717201166,
      "grad_norm": 0.47061852405012233,
      "learning_rate": 3.999148653418503e-05,
      "loss": 1.1603,
      "step": 46
    },
    {
      "epoch": 0.13702623906705538,
      "grad_norm": 0.5047699458420934,
      "learning_rate": 3.998841252397718e-05,
      "loss": 1.087,
      "step": 47
    },
    {
      "epoch": 0.13994169096209913,
      "grad_norm": 0.45543822046591975,
      "learning_rate": 3.998486578486507e-05,
      "loss": 1.1162,
      "step": 48
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.5145420477808398,
      "learning_rate": 3.998084640072959e-05,
      "loss": 1.1669,
      "step": 49
    },
    {
      "epoch": 0.1457725947521866,
      "grad_norm": 0.44889190383338007,
      "learning_rate": 3.997635446662978e-05,
      "loss": 1.0908,
      "step": 50
    },
    {
      "epoch": 0.14868804664723032,
      "grad_norm": 0.448875120724629,
      "learning_rate": 3.997139008880053e-05,
      "loss": 1.1508,
      "step": 51
    },
    {
      "epoch": 0.15160349854227406,
      "grad_norm": 0.4559094928660873,
      "learning_rate": 3.996595338465012e-05,
      "loss": 1.0421,
      "step": 52
    },
    {
      "epoch": 0.15451895043731778,
      "grad_norm": 0.41039500403883783,
      "learning_rate": 3.9960044482757406e-05,
      "loss": 1.0969,
      "step": 53
    },
    {
      "epoch": 0.15743440233236153,
      "grad_norm": 2.195181984076079,
      "learning_rate": 3.995366352286878e-05,
      "loss": 1.1174,
      "step": 54
    },
    {
      "epoch": 0.16034985422740525,
      "grad_norm": 0.45015457594488156,
      "learning_rate": 3.994681065589489e-05,
      "loss": 1.1393,
      "step": 55
    },
    {
      "epoch": 0.16326530612244897,
      "grad_norm": 0.41283257576743904,
      "learning_rate": 3.993948604390704e-05,
      "loss": 1.1162,
      "step": 56
    },
    {
      "epoch": 0.1661807580174927,
      "grad_norm": 0.469276947594031,
      "learning_rate": 3.99316898601334e-05,
      "loss": 1.1258,
      "step": 57
    },
    {
      "epoch": 0.16909620991253643,
      "grad_norm": 0.8079999817536038,
      "learning_rate": 3.992342228895486e-05,
      "loss": 1.127,
      "step": 58
    },
    {
      "epoch": 0.17201166180758018,
      "grad_norm": 0.4553362658754828,
      "learning_rate": 3.991468352590069e-05,
      "loss": 1.0919,
      "step": 59
    },
    {
      "epoch": 0.1749271137026239,
      "grad_norm": 0.4361094059704535,
      "learning_rate": 3.990547377764394e-05,
      "loss": 1.1087,
      "step": 60
    },
    {
      "epoch": 0.17784256559766765,
      "grad_norm": 0.41551312925162287,
      "learning_rate": 3.9895793261996506e-05,
      "loss": 1.101,
      "step": 61
    },
    {
      "epoch": 0.18075801749271136,
      "grad_norm": 0.3955618751805837,
      "learning_rate": 3.9885642207904004e-05,
      "loss": 1.0936,
      "step": 62
    },
    {
      "epoch": 0.1836734693877551,
      "grad_norm": 0.43720530414654624,
      "learning_rate": 3.9875020855440374e-05,
      "loss": 1.133,
      "step": 63
    },
    {
      "epoch": 0.18658892128279883,
      "grad_norm": 0.4347111246810371,
      "learning_rate": 3.986392945580216e-05,
      "loss": 1.1389,
      "step": 64
    },
    {
      "epoch": 0.18950437317784258,
      "grad_norm": 0.44850787138923726,
      "learning_rate": 3.9852368271302604e-05,
      "loss": 1.1137,
      "step": 65
    },
    {
      "epoch": 0.1924198250728863,
      "grad_norm": 0.38905578160555143,
      "learning_rate": 3.984033757536542e-05,
      "loss": 1.1007,
      "step": 66
    },
    {
      "epoch": 0.19533527696793002,
      "grad_norm": 0.4073765119693394,
      "learning_rate": 3.982783765251834e-05,
      "loss": 1.0624,
      "step": 67
    },
    {
      "epoch": 0.19825072886297376,
      "grad_norm": 0.4520768326268948,
      "learning_rate": 3.981486879838639e-05,
      "loss": 1.1307,
      "step": 68
    },
    {
      "epoch": 0.20116618075801748,
      "grad_norm": 0.4766094918337742,
      "learning_rate": 3.980143131968488e-05,
      "loss": 1.1057,
      "step": 69
    },
    {
      "epoch": 0.20408163265306123,
      "grad_norm": 0.3857556379543063,
      "learning_rate": 3.978752553421216e-05,
      "loss": 1.0811,
      "step": 70
    },
    {
      "epoch": 0.20699708454810495,
      "grad_norm": 0.4117513969256482,
      "learning_rate": 3.977315177084211e-05,
      "loss": 1.1368,
      "step": 71
    },
    {
      "epoch": 0.2099125364431487,
      "grad_norm": 0.4331294683046506,
      "learning_rate": 3.975831036951635e-05,
      "loss": 1.1067,
      "step": 72
    },
    {
      "epoch": 0.21282798833819241,
      "grad_norm": 0.4181099883703104,
      "learning_rate": 3.974300168123622e-05,
      "loss": 1.1078,
      "step": 73
    },
    {
      "epoch": 0.21574344023323616,
      "grad_norm": 0.5193623846316575,
      "learning_rate": 3.972722606805445e-05,
      "loss": 1.0217,
      "step": 74
    },
    {
      "epoch": 0.21865889212827988,
      "grad_norm": 0.42748682578145775,
      "learning_rate": 3.9710983903066616e-05,
      "loss": 1.1183,
      "step": 75
    },
    {
      "epoch": 0.22157434402332363,
      "grad_norm": 0.40340255468232195,
      "learning_rate": 3.9694275570402316e-05,
      "loss": 1.0175,
      "step": 76
    },
    {
      "epoch": 0.22448979591836735,
      "grad_norm": 0.6901116231810781,
      "learning_rate": 3.9677101465216085e-05,
      "loss": 1.1436,
      "step": 77
    },
    {
      "epoch": 0.22740524781341107,
      "grad_norm": 0.4470827057095483,
      "learning_rate": 3.965946199367804e-05,
      "loss": 1.1026,
      "step": 78
    },
    {
      "epoch": 0.2303206997084548,
      "grad_norm": 1.4507030226182656,
      "learning_rate": 3.964135757296428e-05,
      "loss": 1.0932,
      "step": 79
    },
    {
      "epoch": 0.23323615160349853,
      "grad_norm": 0.40183625780568555,
      "learning_rate": 3.9622788631247045e-05,
      "loss": 1.1108,
      "step": 80
    },
    {
      "epoch": 0.23615160349854228,
      "grad_norm": 0.4083797606486713,
      "learning_rate": 3.960375560768452e-05,
      "loss": 1.1263,
      "step": 81
    },
    {
      "epoch": 0.239067055393586,
      "grad_norm": 0.3982498098365359,
      "learning_rate": 3.958425895241054e-05,
      "loss": 1.1237,
      "step": 82
    },
    {
      "epoch": 0.24198250728862974,
      "grad_norm": 0.4059963555050571,
      "learning_rate": 3.9564299126523867e-05,
      "loss": 1.068,
      "step": 83
    },
    {
      "epoch": 0.24489795918367346,
      "grad_norm": 0.38793892556447224,
      "learning_rate": 3.954387660207733e-05,
      "loss": 1.1354,
      "step": 84
    },
    {
      "epoch": 0.2478134110787172,
      "grad_norm": 0.3941774269738573,
      "learning_rate": 3.952299186206664e-05,
      "loss": 1.0097,
      "step": 85
    },
    {
      "epoch": 0.25072886297376096,
      "grad_norm": 0.43220005658120336,
      "learning_rate": 3.950164540041898e-05,
      "loss": 1.0977,
      "step": 86
    },
    {
      "epoch": 0.2536443148688047,
      "grad_norm": 0.36583877050224667,
      "learning_rate": 3.9479837721981315e-05,
      "loss": 1.0613,
      "step": 87
    },
    {
      "epoch": 0.2565597667638484,
      "grad_norm": 0.3968503378403748,
      "learning_rate": 3.9457569342508474e-05,
      "loss": 1.1081,
      "step": 88
    },
    {
      "epoch": 0.2594752186588921,
      "grad_norm": 0.36657514937570074,
      "learning_rate": 3.943484078865089e-05,
      "loss": 1.0638,
      "step": 89
    },
    {
      "epoch": 0.26239067055393583,
      "grad_norm": 0.3990173761473332,
      "learning_rate": 3.9411652597942224e-05,
      "loss": 1.1051,
      "step": 90
    },
    {
      "epoch": 0.2653061224489796,
      "grad_norm": 0.41741218758949744,
      "learning_rate": 3.938800531878661e-05,
      "loss": 1.0402,
      "step": 91
    },
    {
      "epoch": 0.26822157434402333,
      "grad_norm": 0.35100087055896617,
      "learning_rate": 3.936389951044569e-05,
      "loss": 1.036,
      "step": 92
    },
    {
      "epoch": 0.27113702623906705,
      "grad_norm": 0.3939910877708907,
      "learning_rate": 3.933933574302538e-05,
      "loss": 1.0915,
      "step": 93
    },
    {
      "epoch": 0.27405247813411077,
      "grad_norm": 0.48903634568290555,
      "learning_rate": 3.93143145974624e-05,
      "loss": 1.1166,
      "step": 94
    },
    {
      "epoch": 0.27696793002915454,
      "grad_norm": 0.47943406165195734,
      "learning_rate": 3.928883666551054e-05,
      "loss": 1.0421,
      "step": 95
    },
    {
      "epoch": 0.27988338192419826,
      "grad_norm": 0.4240913146011234,
      "learning_rate": 3.926290254972665e-05,
      "loss": 1.0877,
      "step": 96
    },
    {
      "epoch": 0.282798833819242,
      "grad_norm": 0.417735312873443,
      "learning_rate": 3.923651286345638e-05,
      "loss": 1.0495,
      "step": 97
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.4027791781208716,
      "learning_rate": 3.920966823081972e-05,
      "loss": 1.11,
      "step": 98
    },
    {
      "epoch": 0.2886297376093295,
      "grad_norm": 0.4021123805362925,
      "learning_rate": 3.9182369286696185e-05,
      "loss": 1.0656,
      "step": 99
    },
    {
      "epoch": 0.2915451895043732,
      "grad_norm": 0.41657372958369593,
      "learning_rate": 3.915461667670982e-05,
      "loss": 1.0953,
      "step": 100
    },
    {
      "epoch": 0.2944606413994169,
      "grad_norm": 0.4549189185164727,
      "learning_rate": 3.9126411057213954e-05,
      "loss": 1.0427,
      "step": 101
    },
    {
      "epoch": 0.29737609329446063,
      "grad_norm": 0.3909314378908402,
      "learning_rate": 3.909775309527564e-05,
      "loss": 1.0578,
      "step": 102
    },
    {
      "epoch": 0.30029154518950435,
      "grad_norm": 0.40901980161241175,
      "learning_rate": 3.906864346865992e-05,
      "loss": 1.0074,
      "step": 103
    },
    {
      "epoch": 0.3032069970845481,
      "grad_norm": 0.4009430285161083,
      "learning_rate": 3.903908286581374e-05,
      "loss": 1.0633,
      "step": 104
    },
    {
      "epoch": 0.30612244897959184,
      "grad_norm": 0.4413234724998126,
      "learning_rate": 3.900907198584974e-05,
      "loss": 1.0645,
      "step": 105
    },
    {
      "epoch": 0.30903790087463556,
      "grad_norm": 0.4146515624534,
      "learning_rate": 3.8978611538529626e-05,
      "loss": 1.0773,
      "step": 106
    },
    {
      "epoch": 0.3119533527696793,
      "grad_norm": 0.39991789210919104,
      "learning_rate": 3.8947702244247485e-05,
      "loss": 1.0766,
      "step": 107
    },
    {
      "epoch": 0.31486880466472306,
      "grad_norm": 0.4296757215583828,
      "learning_rate": 3.8916344834012695e-05,
      "loss": 1.0449,
      "step": 108
    },
    {
      "epoch": 0.3177842565597668,
      "grad_norm": 0.40497448422268767,
      "learning_rate": 3.8884540049432626e-05,
      "loss": 1.0504,
      "step": 109
    },
    {
      "epoch": 0.3206997084548105,
      "grad_norm": 0.42461898148240107,
      "learning_rate": 3.885228864269511e-05,
      "loss": 1.046,
      "step": 110
    },
    {
      "epoch": 0.3236151603498542,
      "grad_norm": 0.388986879558302,
      "learning_rate": 3.88195913765507e-05,
      "loss": 1.0737,
      "step": 111
    },
    {
      "epoch": 0.32653061224489793,
      "grad_norm": 0.3941352715173726,
      "learning_rate": 3.878644902429454e-05,
      "loss": 1.0322,
      "step": 112
    },
    {
      "epoch": 0.3294460641399417,
      "grad_norm": 0.42215837837057424,
      "learning_rate": 3.875286236974816e-05,
      "loss": 1.0645,
      "step": 113
    },
    {
      "epoch": 0.3323615160349854,
      "grad_norm": 0.4610458683962393,
      "learning_rate": 3.871883220724089e-05,
      "loss": 1.0884,
      "step": 114
    },
    {
      "epoch": 0.33527696793002915,
      "grad_norm": 0.4346091661281081,
      "learning_rate": 3.868435934159109e-05,
      "loss": 1.1111,
      "step": 115
    },
    {
      "epoch": 0.33819241982507287,
      "grad_norm": 0.37427705436326664,
      "learning_rate": 3.864944458808712e-05,
      "loss": 1.0629,
      "step": 116
    },
    {
      "epoch": 0.34110787172011664,
      "grad_norm": 0.4316114239509569,
      "learning_rate": 3.8614088772468055e-05,
      "loss": 1.0964,
      "step": 117
    },
    {
      "epoch": 0.34402332361516036,
      "grad_norm": 0.4597612055828575,
      "learning_rate": 3.857829273090414e-05,
      "loss": 1.0467,
      "step": 118
    },
    {
      "epoch": 0.3469387755102041,
      "grad_norm": 0.41631549856597405,
      "learning_rate": 3.854205730997704e-05,
      "loss": 1.0786,
      "step": 119
    },
    {
      "epoch": 0.3498542274052478,
      "grad_norm": 0.3829026297223422,
      "learning_rate": 3.850538336665981e-05,
      "loss": 1.045,
      "step": 120
    },
    {
      "epoch": 0.35276967930029157,
      "grad_norm": 0.4046975211753129,
      "learning_rate": 3.846827176829662e-05,
      "loss": 1.0549,
      "step": 121
    },
    {
      "epoch": 0.3556851311953353,
      "grad_norm": 0.406694717694253,
      "learning_rate": 3.843072339258223e-05,
      "loss": 1.0579,
      "step": 122
    },
    {
      "epoch": 0.358600583090379,
      "grad_norm": 0.3868374046092744,
      "learning_rate": 3.839273912754128e-05,
      "loss": 1.0588,
      "step": 123
    },
    {
      "epoch": 0.36151603498542273,
      "grad_norm": 0.399700910407372,
      "learning_rate": 3.8354319871507224e-05,
      "loss": 1.0572,
      "step": 124
    },
    {
      "epoch": 0.36443148688046645,
      "grad_norm": 0.4404105487294615,
      "learning_rate": 3.8315466533101154e-05,
      "loss": 1.0646,
      "step": 125
    },
    {
      "epoch": 0.3673469387755102,
      "grad_norm": 0.38113631041534785,
      "learning_rate": 3.827618003121023e-05,
      "loss": 1.0137,
      "step": 126
    },
    {
      "epoch": 0.37026239067055394,
      "grad_norm": 0.4572696347195023,
      "learning_rate": 3.823646129496604e-05,
      "loss": 1.0825,
      "step": 127
    },
    {
      "epoch": 0.37317784256559766,
      "grad_norm": 0.44338604907070756,
      "learning_rate": 3.8196311263722545e-05,
      "loss": 1.0494,
      "step": 128
    },
    {
      "epoch": 0.3760932944606414,
      "grad_norm": 0.38848719927969894,
      "learning_rate": 3.8155730887033895e-05,
      "loss": 1.0524,
      "step": 129
    },
    {
      "epoch": 0.37900874635568516,
      "grad_norm": 0.7734150201362632,
      "learning_rate": 3.8114721124631994e-05,
      "loss": 0.996,
      "step": 130
    },
    {
      "epoch": 0.3819241982507289,
      "grad_norm": 0.4333233633929747,
      "learning_rate": 3.8073282946403774e-05,
      "loss": 1.0789,
      "step": 131
    },
    {
      "epoch": 0.3848396501457726,
      "grad_norm": 0.392992047366071,
      "learning_rate": 3.803141733236826e-05,
      "loss": 1.0326,
      "step": 132
    },
    {
      "epoch": 0.3877551020408163,
      "grad_norm": 0.48279560465143584,
      "learning_rate": 3.798912527265339e-05,
      "loss": 1.1128,
      "step": 133
    },
    {
      "epoch": 0.39067055393586003,
      "grad_norm": 0.4560757196728328,
      "learning_rate": 3.794640776747262e-05,
      "loss": 1.0439,
      "step": 134
    },
    {
      "epoch": 0.3935860058309038,
      "grad_norm": 0.4445942243776014,
      "learning_rate": 3.790326582710125e-05,
      "loss": 1.0763,
      "step": 135
    },
    {
      "epoch": 0.3965014577259475,
      "grad_norm": 0.4140118456428661,
      "learning_rate": 3.785970047185253e-05,
      "loss": 1.038,
      "step": 136
    },
    {
      "epoch": 0.39941690962099125,
      "grad_norm": 0.3965741184815775,
      "learning_rate": 3.781571273205354e-05,
      "loss": 1.0569,
      "step": 137
    },
    {
      "epoch": 0.40233236151603496,
      "grad_norm": 0.43946120665541893,
      "learning_rate": 3.777130364802081e-05,
      "loss": 1.0645,
      "step": 138
    },
    {
      "epoch": 0.40524781341107874,
      "grad_norm": 0.428032341240665,
      "learning_rate": 3.772647427003573e-05,
      "loss": 1.0923,
      "step": 139
    },
    {
      "epoch": 0.40816326530612246,
      "grad_norm": 0.4135938868702008,
      "learning_rate": 3.76812256583197e-05,
      "loss": 1.0019,
      "step": 140
    },
    {
      "epoch": 0.4110787172011662,
      "grad_norm": 0.42079943542215226,
      "learning_rate": 3.763555888300906e-05,
      "loss": 1.0245,
      "step": 141
    },
    {
      "epoch": 0.4139941690962099,
      "grad_norm": 0.4104835573072325,
      "learning_rate": 3.758947502412978e-05,
      "loss": 1.0125,
      "step": 142
    },
    {
      "epoch": 0.41690962099125367,
      "grad_norm": 0.4999660587761059,
      "learning_rate": 3.754297517157193e-05,
      "loss": 1.0287,
      "step": 143
    },
    {
      "epoch": 0.4198250728862974,
      "grad_norm": 0.45879131535359835,
      "learning_rate": 3.749606042506387e-05,
      "loss": 0.9914,
      "step": 144
    },
    {
      "epoch": 0.4227405247813411,
      "grad_norm": 0.4356982931966008,
      "learning_rate": 3.744873189414627e-05,
      "loss": 1.062,
      "step": 145
    },
    {
      "epoch": 0.42565597667638483,
      "grad_norm": 0.39205637695442735,
      "learning_rate": 3.740099069814588e-05,
      "loss": 1.0553,
      "step": 146
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.39862366256178505,
      "learning_rate": 3.735283796614903e-05,
      "loss": 1.0295,
      "step": 147
    },
    {
      "epoch": 0.4314868804664723,
      "grad_norm": 0.4565309577821647,
      "learning_rate": 3.730427483697491e-05,
      "loss": 0.994,
      "step": 148
    },
    {
      "epoch": 0.43440233236151604,
      "grad_norm": 0.37911610010778896,
      "learning_rate": 3.725530245914871e-05,
      "loss": 0.988,
      "step": 149
    },
    {
      "epoch": 0.43731778425655976,
      "grad_norm": 0.38802243711360784,
      "learning_rate": 3.7205921990874375e-05,
      "loss": 1.0003,
      "step": 150
    },
    {
      "epoch": 0.4402332361516035,
      "grad_norm": 0.3779749391776368,
      "learning_rate": 3.715613460000727e-05,
      "loss": 1.0399,
      "step": 151
    },
    {
      "epoch": 0.44314868804664725,
      "grad_norm": 0.3737638848515894,
      "learning_rate": 3.7105941464026535e-05,
      "loss": 0.9976,
      "step": 152
    },
    {
      "epoch": 0.446064139941691,
      "grad_norm": 0.39445068206910416,
      "learning_rate": 3.705534377000723e-05,
      "loss": 1.0081,
      "step": 153
    },
    {
      "epoch": 0.4489795918367347,
      "grad_norm": 0.3970018541475319,
      "learning_rate": 3.700434271459229e-05,
      "loss": 1.0622,
      "step": 154
    },
    {
      "epoch": 0.4518950437317784,
      "grad_norm": 0.41614934053800634,
      "learning_rate": 3.695293950396419e-05,
      "loss": 1.0184,
      "step": 155
    },
    {
      "epoch": 0.45481049562682213,
      "grad_norm": 0.42879970357635455,
      "learning_rate": 3.6901135353816444e-05,
      "loss": 1.0692,
      "step": 156
    },
    {
      "epoch": 0.4577259475218659,
      "grad_norm": 0.3956188265745643,
      "learning_rate": 3.684893148932484e-05,
      "loss": 1.0436,
      "step": 157
    },
    {
      "epoch": 0.4606413994169096,
      "grad_norm": 0.351056787493942,
      "learning_rate": 3.679632914511849e-05,
      "loss": 1.0084,
      "step": 158
    },
    {
      "epoch": 0.46355685131195334,
      "grad_norm": 0.42154821635414025,
      "learning_rate": 3.6743329565250575e-05,
      "loss": 0.965,
      "step": 159
    },
    {
      "epoch": 0.46647230320699706,
      "grad_norm": 0.425347734771129,
      "learning_rate": 3.668993400316898e-05,
      "loss": 1.0146,
      "step": 160
    },
    {
      "epoch": 0.46938775510204084,
      "grad_norm": 0.3719982532012811,
      "learning_rate": 3.663614372168663e-05,
      "loss": 1.0177,
      "step": 161
    },
    {
      "epoch": 0.47230320699708456,
      "grad_norm": 0.4400972270054467,
      "learning_rate": 3.658195999295161e-05,
      "loss": 1.0366,
      "step": 162
    },
    {
      "epoch": 0.4752186588921283,
      "grad_norm": 0.3605242363140329,
      "learning_rate": 3.65273840984171e-05,
      "loss": 1.0381,
      "step": 163
    },
    {
      "epoch": 0.478134110787172,
      "grad_norm": 0.4066779201514536,
      "learning_rate": 3.647241732881104e-05,
      "loss": 0.9926,
      "step": 164
    },
    {
      "epoch": 0.48104956268221577,
      "grad_norm": 0.38383029098926946,
      "learning_rate": 3.641706098410566e-05,
      "loss": 1.0053,
      "step": 165
    },
    {
      "epoch": 0.4839650145772595,
      "grad_norm": 0.4540301261066676,
      "learning_rate": 3.6361316373486666e-05,
      "loss": 1.0027,
      "step": 166
    },
    {
      "epoch": 0.4868804664723032,
      "grad_norm": 0.4766965097228693,
      "learning_rate": 3.630518481532232e-05,
      "loss": 1.0226,
      "step": 167
    },
    {
      "epoch": 0.4897959183673469,
      "grad_norm": 0.3664211009679597,
      "learning_rate": 3.624866763713225e-05,
      "loss": 1.0028,
      "step": 168
    },
    {
      "epoch": 0.49271137026239065,
      "grad_norm": 0.4328310790493932,
      "learning_rate": 3.619176617555606e-05,
      "loss": 1.1124,
      "step": 169
    },
    {
      "epoch": 0.4956268221574344,
      "grad_norm": 0.5130318141830079,
      "learning_rate": 3.613448177632171e-05,
      "loss": 1.0168,
      "step": 170
    },
    {
      "epoch": 0.49854227405247814,
      "grad_norm": 0.431130968592827,
      "learning_rate": 3.607681579421369e-05,
      "loss": 1.0359,
      "step": 171
    },
    {
      "epoch": 0.5014577259475219,
      "grad_norm": 0.38524112616777045,
      "learning_rate": 3.6018769593040973e-05,
      "loss": 1.0614,
      "step": 172
    },
    {
      "epoch": 0.5043731778425656,
      "grad_norm": 0.35453421271369107,
      "learning_rate": 3.5960344545604796e-05,
      "loss": 1.0441,
      "step": 173
    },
    {
      "epoch": 0.5072886297376094,
      "grad_norm": 0.41976737591927166,
      "learning_rate": 3.590154203366613e-05,
      "loss": 1.0446,
      "step": 174
    },
    {
      "epoch": 0.5102040816326531,
      "grad_norm": 0.4259982924631218,
      "learning_rate": 3.584236344791306e-05,
      "loss": 1.0136,
      "step": 175
    },
    {
      "epoch": 0.5131195335276968,
      "grad_norm": 0.4149244827409494,
      "learning_rate": 3.578281018792788e-05,
      "loss": 1.0287,
      "step": 176
    },
    {
      "epoch": 0.5160349854227405,
      "grad_norm": 0.4611231037315541,
      "learning_rate": 3.572288366215395e-05,
      "loss": 1.0915,
      "step": 177
    },
    {
      "epoch": 0.5189504373177842,
      "grad_norm": 0.41755776438019643,
      "learning_rate": 3.566258528786246e-05,
      "loss": 1.0648,
      "step": 178
    },
    {
      "epoch": 0.521865889212828,
      "grad_norm": 0.3849110884427409,
      "learning_rate": 3.560191649111885e-05,
      "loss": 1.0319,
      "step": 179
    },
    {
      "epoch": 0.5247813411078717,
      "grad_norm": 0.40902570967880714,
      "learning_rate": 3.554087870674911e-05,
      "loss": 1.0379,
      "step": 180
    },
    {
      "epoch": 0.5276967930029155,
      "grad_norm": 0.3840959826247132,
      "learning_rate": 3.547947337830584e-05,
      "loss": 0.9727,
      "step": 181
    },
    {
      "epoch": 0.5306122448979592,
      "grad_norm": 0.5183637429811634,
      "learning_rate": 3.541770195803412e-05,
      "loss": 1.0227,
      "step": 182
    },
    {
      "epoch": 0.5335276967930029,
      "grad_norm": 0.4257410447947219,
      "learning_rate": 3.5355565906837155e-05,
      "loss": 0.9984,
      "step": 183
    },
    {
      "epoch": 0.5364431486880467,
      "grad_norm": 0.4384769899775353,
      "learning_rate": 3.5293066694241705e-05,
      "loss": 1.0336,
      "step": 184
    },
    {
      "epoch": 0.5393586005830904,
      "grad_norm": 0.3758195750644803,
      "learning_rate": 3.523020579836338e-05,
      "loss": 1.0325,
      "step": 185
    },
    {
      "epoch": 0.5422740524781341,
      "grad_norm": 0.42491607255874136,
      "learning_rate": 3.5166984705871634e-05,
      "loss": 1.0012,
      "step": 186
    },
    {
      "epoch": 0.5451895043731778,
      "grad_norm": 0.4013799418461195,
      "learning_rate": 3.510340491195462e-05,
      "loss": 1.0595,
      "step": 187
    },
    {
      "epoch": 0.5481049562682215,
      "grad_norm": 0.38755015550966654,
      "learning_rate": 3.5039467920283854e-05,
      "loss": 1.0258,
      "step": 188
    },
    {
      "epoch": 0.5510204081632653,
      "grad_norm": 0.419454333619642,
      "learning_rate": 3.497517524297862e-05,
      "loss": 0.997,
      "step": 189
    },
    {
      "epoch": 0.5539358600583091,
      "grad_norm": 0.4030099888296478,
      "learning_rate": 3.49105284005702e-05,
      "loss": 1.0641,
      "step": 190
    },
    {
      "epoch": 0.5568513119533528,
      "grad_norm": 0.4308216911553141,
      "learning_rate": 3.4845528921965975e-05,
      "loss": 1.0773,
      "step": 191
    },
    {
      "epoch": 0.5597667638483965,
      "grad_norm": 0.4109261330841367,
      "learning_rate": 3.478017834441319e-05,
      "loss": 1.0348,
      "step": 192
    },
    {
      "epoch": 0.5626822157434402,
      "grad_norm": 0.4391746023600184,
      "learning_rate": 3.471447821346264e-05,
      "loss": 1.0143,
      "step": 193
    },
    {
      "epoch": 0.565597667638484,
      "grad_norm": 0.4231633568942445,
      "learning_rate": 3.464843008293211e-05,
      "loss": 1.0658,
      "step": 194
    },
    {
      "epoch": 0.5685131195335277,
      "grad_norm": 0.4185436344137551,
      "learning_rate": 3.458203551486964e-05,
      "loss": 1.0132,
      "step": 195
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.3689812388040208,
      "learning_rate": 3.4515296079516547e-05,
      "loss": 0.9811,
      "step": 196
    },
    {
      "epoch": 0.5743440233236151,
      "grad_norm": 0.38614461808327916,
      "learning_rate": 3.4448213355270327e-05,
      "loss": 1.0357,
      "step": 197
    },
    {
      "epoch": 0.577259475218659,
      "grad_norm": 0.46524563397545066,
      "learning_rate": 3.43807889286473e-05,
      "loss": 1.0115,
      "step": 198
    },
    {
      "epoch": 0.5801749271137027,
      "grad_norm": 0.41968912546661996,
      "learning_rate": 3.43130243942451e-05,
      "loss": 1.0687,
      "step": 199
    },
    {
      "epoch": 0.5830903790087464,
      "grad_norm": 0.4467937397647347,
      "learning_rate": 3.424492135470496e-05,
      "loss": 1.0688,
      "step": 200
    },
    {
      "epoch": 0.5860058309037901,
      "grad_norm": 0.6603485797707492,
      "learning_rate": 3.4176481420673806e-05,
      "loss": 1.0105,
      "step": 201
    },
    {
      "epoch": 0.5889212827988338,
      "grad_norm": 0.47934564972994936,
      "learning_rate": 3.410770621076618e-05,
      "loss": 1.0196,
      "step": 202
    },
    {
      "epoch": 0.5918367346938775,
      "grad_norm": 0.42028075345133814,
      "learning_rate": 3.403859735152593e-05,
      "loss": 1.0335,
      "step": 203
    },
    {
      "epoch": 0.5947521865889213,
      "grad_norm": 0.41920419384521423,
      "learning_rate": 3.3969156477387775e-05,
      "loss": 1.0102,
      "step": 204
    },
    {
      "epoch": 0.597667638483965,
      "grad_norm": 0.4314609472381487,
      "learning_rate": 3.389938523063864e-05,
      "loss": 1.026,
      "step": 205
    },
    {
      "epoch": 0.6005830903790087,
      "grad_norm": 0.400148137177815,
      "learning_rate": 3.382928526137878e-05,
      "loss": 1.0375,
      "step": 206
    },
    {
      "epoch": 0.6034985422740525,
      "grad_norm": 0.4149559442787825,
      "learning_rate": 3.375885822748282e-05,
      "loss": 0.9966,
      "step": 207
    },
    {
      "epoch": 0.6064139941690962,
      "grad_norm": 0.43073644415383394,
      "learning_rate": 3.36881057945605e-05,
      "loss": 1.0549,
      "step": 208
    },
    {
      "epoch": 0.60932944606414,
      "grad_norm": 0.44927459389603297,
      "learning_rate": 3.361702963591729e-05,
      "loss": 1.0263,
      "step": 209
    },
    {
      "epoch": 0.6122448979591837,
      "grad_norm": 0.3832872805795473,
      "learning_rate": 3.354563143251483e-05,
      "loss": 1.0359,
      "step": 210
    },
    {
      "epoch": 0.6151603498542274,
      "grad_norm": 0.3750674262349031,
      "learning_rate": 3.347391287293115e-05,
      "loss": 1.0246,
      "step": 211
    },
    {
      "epoch": 0.6180758017492711,
      "grad_norm": 0.4356003464009786,
      "learning_rate": 3.340187565332077e-05,
      "loss": 1.0415,
      "step": 212
    },
    {
      "epoch": 0.6209912536443148,
      "grad_norm": 0.3832024635421635,
      "learning_rate": 3.332952147737456e-05,
      "loss": 0.9936,
      "step": 213
    },
    {
      "epoch": 0.6239067055393586,
      "grad_norm": 0.39631432623065777,
      "learning_rate": 3.325685205627944e-05,
      "loss": 1.0409,
      "step": 214
    },
    {
      "epoch": 0.6268221574344023,
      "grad_norm": 0.4960530056723912,
      "learning_rate": 3.318386910867796e-05,
      "loss": 0.9819,
      "step": 215
    },
    {
      "epoch": 0.6297376093294461,
      "grad_norm": 0.48098440810607934,
      "learning_rate": 3.3110574360627574e-05,
      "loss": 1.0366,
      "step": 216
    },
    {
      "epoch": 0.6326530612244898,
      "grad_norm": 0.40495158253103936,
      "learning_rate": 3.30369695455599e-05,
      "loss": 1.0169,
      "step": 217
    },
    {
      "epoch": 0.6355685131195336,
      "grad_norm": 0.4136840317080595,
      "learning_rate": 3.296305640423965e-05,
      "loss": 1.0089,
      "step": 218
    },
    {
      "epoch": 0.6384839650145773,
      "grad_norm": 0.41071579187843577,
      "learning_rate": 3.288883668472353e-05,
      "loss": 1.0245,
      "step": 219
    },
    {
      "epoch": 0.641399416909621,
      "grad_norm": 0.44228843130743967,
      "learning_rate": 3.2814312142318863e-05,
      "loss": 1.0143,
      "step": 220
    },
    {
      "epoch": 0.6443148688046647,
      "grad_norm": 0.5009960405186326,
      "learning_rate": 3.273948453954205e-05,
      "loss": 1.0122,
      "step": 221
    },
    {
      "epoch": 0.6472303206997084,
      "grad_norm": 0.5126441090651163,
      "learning_rate": 3.2664355646076944e-05,
      "loss": 0.989,
      "step": 222
    },
    {
      "epoch": 0.6501457725947521,
      "grad_norm": 0.4071977138096943,
      "learning_rate": 3.2588927238732946e-05,
      "loss": 1.0441,
      "step": 223
    },
    {
      "epoch": 0.6530612244897959,
      "grad_norm": 0.38486281815191886,
      "learning_rate": 3.2513201101403025e-05,
      "loss": 1.0152,
      "step": 224
    },
    {
      "epoch": 0.6559766763848397,
      "grad_norm": 0.38571804075512084,
      "learning_rate": 3.24371790250215e-05,
      "loss": 1.0474,
      "step": 225
    },
    {
      "epoch": 0.6588921282798834,
      "grad_norm": 0.35752894010390635,
      "learning_rate": 3.236086280752167e-05,
      "loss": 0.9813,
      "step": 226
    },
    {
      "epoch": 0.6618075801749271,
      "grad_norm": 0.5079505809169615,
      "learning_rate": 3.2284254253793364e-05,
      "loss": 1.0358,
      "step": 227
    },
    {
      "epoch": 0.6647230320699709,
      "grad_norm": 0.41139665258470137,
      "learning_rate": 3.220735517564015e-05,
      "loss": 1.0367,
      "step": 228
    },
    {
      "epoch": 0.6676384839650146,
      "grad_norm": 0.38126553570378735,
      "learning_rate": 3.213016739173658e-05,
      "loss": 0.9482,
      "step": 229
    },
    {
      "epoch": 0.6705539358600583,
      "grad_norm": 0.4144347872593754,
      "learning_rate": 3.205269272758513e-05,
      "loss": 1.0193,
      "step": 230
    },
    {
      "epoch": 0.673469387755102,
      "grad_norm": 0.5096571232126209,
      "learning_rate": 3.197493301547302e-05,
      "loss": 0.9819,
      "step": 231
    },
    {
      "epoch": 0.6763848396501457,
      "grad_norm": 0.36383462161136243,
      "learning_rate": 3.189689009442894e-05,
      "loss": 0.9914,
      "step": 232
    },
    {
      "epoch": 0.6793002915451894,
      "grad_norm": 0.46095765518459053,
      "learning_rate": 3.181856581017946e-05,
      "loss": 0.9897,
      "step": 233
    },
    {
      "epoch": 0.6822157434402333,
      "grad_norm": 0.44886312747350354,
      "learning_rate": 3.173996201510545e-05,
      "loss": 1.0335,
      "step": 234
    },
    {
      "epoch": 0.685131195335277,
      "grad_norm": 0.45631056555707983,
      "learning_rate": 3.1661080568198266e-05,
      "loss": 1.0346,
      "step": 235
    },
    {
      "epoch": 0.6880466472303207,
      "grad_norm": 0.4136610032658645,
      "learning_rate": 3.158192333501577e-05,
      "loss": 1.0104,
      "step": 236
    },
    {
      "epoch": 0.6909620991253644,
      "grad_norm": 0.4367296982258636,
      "learning_rate": 3.150249218763818e-05,
      "loss": 1.0428,
      "step": 237
    },
    {
      "epoch": 0.6938775510204082,
      "grad_norm": 0.4306434247011164,
      "learning_rate": 3.142278900462387e-05,
      "loss": 1.0455,
      "step": 238
    },
    {
      "epoch": 0.6967930029154519,
      "grad_norm": 0.4253113476475862,
      "learning_rate": 3.134281567096485e-05,
      "loss": 1.0496,
      "step": 239
    },
    {
      "epoch": 0.6997084548104956,
      "grad_norm": 0.48183974058742907,
      "learning_rate": 3.1262574078042285e-05,
      "loss": 1.0465,
      "step": 240
    },
    {
      "epoch": 0.7026239067055393,
      "grad_norm": 0.4119086984528717,
      "learning_rate": 3.1182066123581654e-05,
      "loss": 0.9854,
      "step": 241
    },
    {
      "epoch": 0.7055393586005831,
      "grad_norm": 0.341284639409196,
      "learning_rate": 3.110129371160797e-05,
      "loss": 0.9783,
      "step": 242
    },
    {
      "epoch": 0.7084548104956269,
      "grad_norm": 0.42056610876171097,
      "learning_rate": 3.102025875240068e-05,
      "loss": 1.0271,
      "step": 243
    },
    {
      "epoch": 0.7113702623906706,
      "grad_norm": 0.4231983208975138,
      "learning_rate": 3.093896316244855e-05,
      "loss": 1.0432,
      "step": 244
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.37689276896375645,
      "learning_rate": 3.085740886440422e-05,
      "loss": 0.9554,
      "step": 245
    },
    {
      "epoch": 0.717201166180758,
      "grad_norm": 0.5479879616689535,
      "learning_rate": 3.077559778703891e-05,
      "loss": 0.9957,
      "step": 246
    },
    {
      "epoch": 0.7201166180758017,
      "grad_norm": 0.36933525591223165,
      "learning_rate": 3.069353186519665e-05,
      "loss": 0.9806,
      "step": 247
    },
    {
      "epoch": 0.7230320699708455,
      "grad_norm": 0.41541742087484357,
      "learning_rate": 3.06112130397486e-05,
      "loss": 1.0019,
      "step": 248
    },
    {
      "epoch": 0.7259475218658892,
      "grad_norm": 0.4030147243701519,
      "learning_rate": 3.052864325754712e-05,
      "loss": 0.9609,
      "step": 249
    },
    {
      "epoch": 0.7288629737609329,
      "grad_norm": 0.38097239049076487,
      "learning_rate": 3.0445824471379735e-05,
      "loss": 0.9906,
      "step": 250
    },
    {
      "epoch": 0.7317784256559767,
      "grad_norm": 0.35094313646523306,
      "learning_rate": 3.036275863992296e-05,
      "loss": 1.0152,
      "step": 251
    },
    {
      "epoch": 0.7346938775510204,
      "grad_norm": 0.39936296801568144,
      "learning_rate": 3.0279447727695955e-05,
      "loss": 1.0211,
      "step": 252
    },
    {
      "epoch": 0.7376093294460642,
      "grad_norm": 0.3910974776654842,
      "learning_rate": 3.0195893705014085e-05,
      "loss": 1.0504,
      "step": 253
    },
    {
      "epoch": 0.7405247813411079,
      "grad_norm": 0.43816416675730724,
      "learning_rate": 3.01120985479423e-05,
      "loss": 1.0076,
      "step": 254
    },
    {
      "epoch": 0.7434402332361516,
      "grad_norm": 0.36698284475827536,
      "learning_rate": 3.002806423824843e-05,
      "loss": 0.9635,
      "step": 255
    },
    {
      "epoch": 0.7463556851311953,
      "grad_norm": 0.39228423379591765,
      "learning_rate": 2.9943792763356305e-05,
      "loss": 0.9619,
      "step": 256
    },
    {
      "epoch": 0.749271137026239,
      "grad_norm": 0.36070109767376196,
      "learning_rate": 2.9859286116298714e-05,
      "loss": 0.9851,
      "step": 257
    },
    {
      "epoch": 0.7521865889212828,
      "grad_norm": 0.37912953951949635,
      "learning_rate": 2.977454629567034e-05,
      "loss": 0.9898,
      "step": 258
    },
    {
      "epoch": 0.7551020408163265,
      "grad_norm": 0.37387389967325224,
      "learning_rate": 2.968957530558043e-05,
      "loss": 0.9977,
      "step": 259
    },
    {
      "epoch": 0.7580174927113703,
      "grad_norm": 0.39972986361258667,
      "learning_rate": 2.960437515560544e-05,
      "loss": 0.9856,
      "step": 260
    },
    {
      "epoch": 0.760932944606414,
      "grad_norm": 0.3826342975930071,
      "learning_rate": 2.9518947860741476e-05,
      "loss": 0.9588,
      "step": 261
    },
    {
      "epoch": 0.7638483965014577,
      "grad_norm": 0.3576332727935384,
      "learning_rate": 2.943329544135666e-05,
      "loss": 0.9893,
      "step": 262
    },
    {
      "epoch": 0.7667638483965015,
      "grad_norm": 0.464371743364152,
      "learning_rate": 2.9347419923143355e-05,
      "loss": 1.0135,
      "step": 263
    },
    {
      "epoch": 0.7696793002915452,
      "grad_norm": 0.4133741281825162,
      "learning_rate": 2.9261323337070212e-05,
      "loss": 0.9489,
      "step": 264
    },
    {
      "epoch": 0.7725947521865889,
      "grad_norm": 0.48836679547916445,
      "learning_rate": 2.9175007719334213e-05,
      "loss": 0.9644,
      "step": 265
    },
    {
      "epoch": 0.7755102040816326,
      "grad_norm": 0.3887248594130963,
      "learning_rate": 2.9088475111312434e-05,
      "loss": 0.9809,
      "step": 266
    },
    {
      "epoch": 0.7784256559766763,
      "grad_norm": 0.3918471548750329,
      "learning_rate": 2.900172755951382e-05,
      "loss": 0.9602,
      "step": 267
    },
    {
      "epoch": 0.7813411078717201,
      "grad_norm": 0.4366666865657208,
      "learning_rate": 2.891476711553077e-05,
      "loss": 1.0474,
      "step": 268
    },
    {
      "epoch": 0.7842565597667639,
      "grad_norm": 0.38108127915752593,
      "learning_rate": 2.88275958359906e-05,
      "loss": 0.9794,
      "step": 269
    },
    {
      "epoch": 0.7871720116618076,
      "grad_norm": 0.3996038721397645,
      "learning_rate": 2.8740215782506937e-05,
      "loss": 1.0089,
      "step": 270
    },
    {
      "epoch": 0.7900874635568513,
      "grad_norm": 0.4000788473276949,
      "learning_rate": 2.8652629021630928e-05,
      "loss": 0.9935,
      "step": 271
    },
    {
      "epoch": 0.793002915451895,
      "grad_norm": 0.4311799335652256,
      "learning_rate": 2.8564837624802394e-05,
      "loss": 1.0085,
      "step": 272
    },
    {
      "epoch": 0.7959183673469388,
      "grad_norm": 0.43802025453013554,
      "learning_rate": 2.8476843668300805e-05,
      "loss": 0.9818,
      "step": 273
    },
    {
      "epoch": 0.7988338192419825,
      "grad_norm": 0.39878597038821745,
      "learning_rate": 2.838864923319622e-05,
      "loss": 1.031,
      "step": 274
    },
    {
      "epoch": 0.8017492711370262,
      "grad_norm": 0.38849018574168676,
      "learning_rate": 2.830025640530004e-05,
      "loss": 0.9949,
      "step": 275
    },
    {
      "epoch": 0.8046647230320699,
      "grad_norm": 0.3700883289439985,
      "learning_rate": 2.821166727511567e-05,
      "loss": 0.9896,
      "step": 276
    },
    {
      "epoch": 0.8075801749271136,
      "grad_norm": 0.3722364712124695,
      "learning_rate": 2.8122883937789117e-05,
      "loss": 0.9941,
      "step": 277
    },
    {
      "epoch": 0.8104956268221575,
      "grad_norm": 0.4096031852809965,
      "learning_rate": 2.8033908493059394e-05,
      "loss": 1.0378,
      "step": 278
    },
    {
      "epoch": 0.8134110787172012,
      "grad_norm": 0.37372263404365025,
      "learning_rate": 2.7944743045208897e-05,
      "loss": 1.0253,
      "step": 279
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 0.38881406149093034,
      "learning_rate": 2.785538970301361e-05,
      "loss": 0.9663,
      "step": 280
    },
    {
      "epoch": 0.8192419825072886,
      "grad_norm": 0.42459440488854533,
      "learning_rate": 2.7765850579693274e-05,
      "loss": 1.0034,
      "step": 281
    },
    {
      "epoch": 0.8221574344023324,
      "grad_norm": 0.4143201974978241,
      "learning_rate": 2.767612779286134e-05,
      "loss": 1.0368,
      "step": 282
    },
    {
      "epoch": 0.8250728862973761,
      "grad_norm": 0.38362731189430754,
      "learning_rate": 2.758622346447496e-05,
      "loss": 1.0208,
      "step": 283
    },
    {
      "epoch": 0.8279883381924198,
      "grad_norm": 0.41169832196779926,
      "learning_rate": 2.7496139720784763e-05,
      "loss": 1.0006,
      "step": 284
    },
    {
      "epoch": 0.8309037900874635,
      "grad_norm": 0.34751593366178846,
      "learning_rate": 2.7405878692284572e-05,
      "loss": 1.0251,
      "step": 285
    },
    {
      "epoch": 0.8338192419825073,
      "grad_norm": 0.4058210036935123,
      "learning_rate": 2.7315442513661014e-05,
      "loss": 1.0361,
      "step": 286
    },
    {
      "epoch": 0.8367346938775511,
      "grad_norm": 0.4401679580816322,
      "learning_rate": 2.7224833323743064e-05,
      "loss": 1.0272,
      "step": 287
    },
    {
      "epoch": 0.8396501457725948,
      "grad_norm": 0.4057761916028717,
      "learning_rate": 2.713405326545142e-05,
      "loss": 1.0383,
      "step": 288
    },
    {
      "epoch": 0.8425655976676385,
      "grad_norm": 0.4245290759312782,
      "learning_rate": 2.7043104485747852e-05,
      "loss": 1.0464,
      "step": 289
    },
    {
      "epoch": 0.8454810495626822,
      "grad_norm": 0.4038361202180251,
      "learning_rate": 2.6951989135584417e-05,
      "loss": 0.988,
      "step": 290
    },
    {
      "epoch": 0.8483965014577259,
      "grad_norm": 0.36810376807434014,
      "learning_rate": 2.686070936985258e-05,
      "loss": 0.9561,
      "step": 291
    },
    {
      "epoch": 0.8513119533527697,
      "grad_norm": 0.37195307131485894,
      "learning_rate": 2.6769267347332265e-05,
      "loss": 0.9575,
      "step": 292
    },
    {
      "epoch": 0.8542274052478134,
      "grad_norm": 0.390443868115284,
      "learning_rate": 2.6677665230640798e-05,
      "loss": 0.9699,
      "step": 293
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.4042815574880434,
      "learning_rate": 2.6585905186181738e-05,
      "loss": 1.042,
      "step": 294
    },
    {
      "epoch": 0.8600583090379009,
      "grad_norm": 0.3959869863268726,
      "learning_rate": 2.6493989384093674e-05,
      "loss": 0.9752,
      "step": 295
    },
    {
      "epoch": 0.8629737609329446,
      "grad_norm": 0.3618071430236251,
      "learning_rate": 2.6401919998198883e-05,
      "loss": 1.0231,
      "step": 296
    },
    {
      "epoch": 0.8658892128279884,
      "grad_norm": 0.4176948830244882,
      "learning_rate": 2.630969920595192e-05,
      "loss": 0.9362,
      "step": 297
    },
    {
      "epoch": 0.8688046647230321,
      "grad_norm": 0.3791793063855236,
      "learning_rate": 2.6217329188388127e-05,
      "loss": 0.999,
      "step": 298
    },
    {
      "epoch": 0.8717201166180758,
      "grad_norm": 0.37050615706622725,
      "learning_rate": 2.612481213007204e-05,
      "loss": 0.9698,
      "step": 299
    },
    {
      "epoch": 0.8746355685131195,
      "grad_norm": 0.4262982030520383,
      "learning_rate": 2.603215021904573e-05,
      "loss": 1.0253,
      "step": 300
    },
    {
      "epoch": 0.8775510204081632,
      "grad_norm": 0.4100689842059256,
      "learning_rate": 2.5939345646777066e-05,
      "loss": 1.0282,
      "step": 301
    },
    {
      "epoch": 0.880466472303207,
      "grad_norm": 0.42174481372887873,
      "learning_rate": 2.5846400608107864e-05,
      "loss": 0.9907,
      "step": 302
    },
    {
      "epoch": 0.8833819241982507,
      "grad_norm": 0.4314163530656172,
      "learning_rate": 2.5753317301201998e-05,
      "loss": 1.0558,
      "step": 303
    },
    {
      "epoch": 0.8862973760932945,
      "grad_norm": 0.4010560503450353,
      "learning_rate": 2.5660097927493407e-05,
      "loss": 0.9557,
      "step": 304
    },
    {
      "epoch": 0.8892128279883382,
      "grad_norm": 0.4395765405207931,
      "learning_rate": 2.5566744691634027e-05,
      "loss": 1.0059,
      "step": 305
    },
    {
      "epoch": 0.892128279883382,
      "grad_norm": 0.4082847256609399,
      "learning_rate": 2.5473259801441663e-05,
      "loss": 1.0103,
      "step": 306
    },
    {
      "epoch": 0.8950437317784257,
      "grad_norm": 0.4083786483549625,
      "learning_rate": 2.537964546784774e-05,
      "loss": 0.986,
      "step": 307
    },
    {
      "epoch": 0.8979591836734694,
      "grad_norm": 0.37572180654125914,
      "learning_rate": 2.5285903904845066e-05,
      "loss": 0.9896,
      "step": 308
    },
    {
      "epoch": 0.9008746355685131,
      "grad_norm": 0.4027132060553977,
      "learning_rate": 2.5192037329435426e-05,
      "loss": 0.979,
      "step": 309
    },
    {
      "epoch": 0.9037900874635568,
      "grad_norm": 0.36888494424117924,
      "learning_rate": 2.5098047961577177e-05,
      "loss": 0.9471,
      "step": 310
    },
    {
      "epoch": 0.9067055393586005,
      "grad_norm": 0.3786111360905341,
      "learning_rate": 2.500393802413273e-05,
      "loss": 0.9892,
      "step": 311
    },
    {
      "epoch": 0.9096209912536443,
      "grad_norm": 0.45712819166253305,
      "learning_rate": 2.4909709742815986e-05,
      "loss": 1.01,
      "step": 312
    },
    {
      "epoch": 0.9125364431486881,
      "grad_norm": 0.3842470085901606,
      "learning_rate": 2.4815365346139696e-05,
      "loss": 0.9778,
      "step": 313
    },
    {
      "epoch": 0.9154518950437318,
      "grad_norm": 0.433547968789441,
      "learning_rate": 2.4720907065362752e-05,
      "loss": 1.0222,
      "step": 314
    },
    {
      "epoch": 0.9183673469387755,
      "grad_norm": 0.4391573887982836,
      "learning_rate": 2.4626337134437437e-05,
      "loss": 1.0405,
      "step": 315
    },
    {
      "epoch": 0.9212827988338192,
      "grad_norm": 0.39208976407075724,
      "learning_rate": 2.4531657789956547e-05,
      "loss": 1.0437,
      "step": 316
    },
    {
      "epoch": 0.924198250728863,
      "grad_norm": 0.3768972618887708,
      "learning_rate": 2.4436871271100556e-05,
      "loss": 1.0207,
      "step": 317
    },
    {
      "epoch": 0.9271137026239067,
      "grad_norm": 0.43610556057213695,
      "learning_rate": 2.4341979819584625e-05,
      "loss": 0.9861,
      "step": 318
    },
    {
      "epoch": 0.9300291545189504,
      "grad_norm": 0.363583976831923,
      "learning_rate": 2.4246985679605554e-05,
      "loss": 0.9383,
      "step": 319
    },
    {
      "epoch": 0.9329446064139941,
      "grad_norm": 0.37854946885829915,
      "learning_rate": 2.4151891097788775e-05,
      "loss": 1.0158,
      "step": 320
    },
    {
      "epoch": 0.9358600583090378,
      "grad_norm": 0.37464026411645185,
      "learning_rate": 2.4056698323135176e-05,
      "loss": 0.9712,
      "step": 321
    },
    {
      "epoch": 0.9387755102040817,
      "grad_norm": 0.43100644059903814,
      "learning_rate": 2.3961409606967925e-05,
      "loss": 1.0003,
      "step": 322
    },
    {
      "epoch": 0.9416909620991254,
      "grad_norm": 0.38980347880232474,
      "learning_rate": 2.3866027202879192e-05,
      "loss": 0.914,
      "step": 323
    },
    {
      "epoch": 0.9446064139941691,
      "grad_norm": 0.48554638696145264,
      "learning_rate": 2.377055336667692e-05,
      "loss": 0.9585,
      "step": 324
    },
    {
      "epoch": 0.9475218658892128,
      "grad_norm": 0.36898646954208214,
      "learning_rate": 2.367499035633141e-05,
      "loss": 0.9835,
      "step": 325
    },
    {
      "epoch": 0.9504373177842566,
      "grad_norm": 0.4297200560129973,
      "learning_rate": 2.357934043192195e-05,
      "loss": 0.9952,
      "step": 326
    },
    {
      "epoch": 0.9533527696793003,
      "grad_norm": 0.39165249508490607,
      "learning_rate": 2.3483605855583362e-05,
      "loss": 0.9882,
      "step": 327
    },
    {
      "epoch": 0.956268221574344,
      "grad_norm": 0.41742394941388217,
      "learning_rate": 2.338778889145249e-05,
      "loss": 0.9717,
      "step": 328
    },
    {
      "epoch": 0.9591836734693877,
      "grad_norm": 0.3886638817329252,
      "learning_rate": 2.329189180561468e-05,
      "loss": 0.9663,
      "step": 329
    },
    {
      "epoch": 0.9620991253644315,
      "grad_norm": 0.4332990337620019,
      "learning_rate": 2.3195916866050144e-05,
      "loss": 0.9852,
      "step": 330
    },
    {
      "epoch": 0.9650145772594753,
      "grad_norm": 0.3704146023415907,
      "learning_rate": 2.3099866342580367e-05,
      "loss": 0.9486,
      "step": 331
    },
    {
      "epoch": 0.967930029154519,
      "grad_norm": 0.4371661371336054,
      "learning_rate": 2.300374250681439e-05,
      "loss": 0.9657,
      "step": 332
    },
    {
      "epoch": 0.9708454810495627,
      "grad_norm": 0.4303408791719072,
      "learning_rate": 2.2907547632095107e-05,
      "loss": 1.0448,
      "step": 333
    },
    {
      "epoch": 0.9737609329446064,
      "grad_norm": 0.3768181576852921,
      "learning_rate": 2.2811283993445496e-05,
      "loss": 0.9616,
      "step": 334
    },
    {
      "epoch": 0.9766763848396501,
      "grad_norm": 0.3724772962800981,
      "learning_rate": 2.2714953867514797e-05,
      "loss": 1.0466,
      "step": 335
    },
    {
      "epoch": 0.9795918367346939,
      "grad_norm": 0.363005384837364,
      "learning_rate": 2.261855953252471e-05,
      "loss": 0.9818,
      "step": 336
    },
    {
      "epoch": 0.9825072886297376,
      "grad_norm": 0.41490379204887295,
      "learning_rate": 2.252210326821547e-05,
      "loss": 1.0075,
      "step": 337
    },
    {
      "epoch": 0.9854227405247813,
      "grad_norm": 0.41297107841340125,
      "learning_rate": 2.2425587355791953e-05,
      "loss": 1.0264,
      "step": 338
    },
    {
      "epoch": 0.9883381924198251,
      "grad_norm": 0.4120966355909792,
      "learning_rate": 2.232901407786973e-05,
      "loss": 1.0295,
      "step": 339
    },
    {
      "epoch": 0.9912536443148688,
      "grad_norm": 0.4061162831072794,
      "learning_rate": 2.2232385718421053e-05,
      "loss": 0.9504,
      "step": 340
    },
    {
      "epoch": 0.9941690962099126,
      "grad_norm": 0.3885457702367736,
      "learning_rate": 2.2135704562720887e-05,
      "loss": 0.9139,
      "step": 341
    },
    {
      "epoch": 0.9970845481049563,
      "grad_norm": 0.43463625174294523,
      "learning_rate": 2.2038972897292813e-05,
      "loss": 0.9913,
      "step": 342
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.3538735883267368,
      "learning_rate": 2.1942193009854997e-05,
      "loss": 1.0211,
      "step": 343
    },
    {
      "epoch": 1.0029154518950438,
      "grad_norm": 0.3388449241745017,
      "learning_rate": 2.184536718926604e-05,
      "loss": 0.9067,
      "step": 344
    },
    {
      "epoch": 1.0058309037900874,
      "grad_norm": 0.3958357821808929,
      "learning_rate": 2.174849772547089e-05,
      "loss": 0.9061,
      "step": 345
    },
    {
      "epoch": 1.0087463556851313,
      "grad_norm": 0.41616322205845646,
      "learning_rate": 2.165158690944665e-05,
      "loss": 0.9362,
      "step": 346
    },
    {
      "epoch": 1.0116618075801749,
      "grad_norm": 0.35202048574980316,
      "learning_rate": 2.155463703314841e-05,
      "loss": 0.8766,
      "step": 347
    },
    {
      "epoch": 1.0145772594752187,
      "grad_norm": 0.34310062245683337,
      "learning_rate": 2.145765038945504e-05,
      "loss": 0.8642,
      "step": 348
    },
    {
      "epoch": 1.0174927113702623,
      "grad_norm": 0.3981059330195169,
      "learning_rate": 2.136062927211497e-05,
      "loss": 0.8645,
      "step": 349
    },
    {
      "epoch": 1.0204081632653061,
      "grad_norm": 0.3672358171644383,
      "learning_rate": 2.1263575975691942e-05,
      "loss": 0.9306,
      "step": 350
    },
    {
      "epoch": 1.0233236151603498,
      "grad_norm": 0.3973336252454919,
      "learning_rate": 2.116649279551072e-05,
      "loss": 0.929,
      "step": 351
    },
    {
      "epoch": 1.0262390670553936,
      "grad_norm": 0.3369031433982456,
      "learning_rate": 2.106938202760284e-05,
      "loss": 0.8762,
      "step": 352
    },
    {
      "epoch": 1.0291545189504374,
      "grad_norm": 0.4117171514208426,
      "learning_rate": 2.097224596865229e-05,
      "loss": 0.8893,
      "step": 353
    },
    {
      "epoch": 1.032069970845481,
      "grad_norm": 0.35518871719324885,
      "learning_rate": 2.0875086915941183e-05,
      "loss": 0.8674,
      "step": 354
    },
    {
      "epoch": 1.0349854227405249,
      "grad_norm": 0.3890457229678617,
      "learning_rate": 2.077790716729545e-05,
      "loss": 0.9484,
      "step": 355
    },
    {
      "epoch": 1.0379008746355685,
      "grad_norm": 0.39711639935921345,
      "learning_rate": 2.068070902103047e-05,
      "loss": 0.9082,
      "step": 356
    },
    {
      "epoch": 1.0408163265306123,
      "grad_norm": 0.371896748401522,
      "learning_rate": 2.0583494775896753e-05,
      "loss": 0.9356,
      "step": 357
    },
    {
      "epoch": 1.043731778425656,
      "grad_norm": 0.3487320833120989,
      "learning_rate": 2.048626673102552e-05,
      "loss": 0.8607,
      "step": 358
    },
    {
      "epoch": 1.0466472303206997,
      "grad_norm": 0.41218299978568584,
      "learning_rate": 2.0389027185874392e-05,
      "loss": 0.8836,
      "step": 359
    },
    {
      "epoch": 1.0495626822157433,
      "grad_norm": 0.37291671079144145,
      "learning_rate": 2.029177844017293e-05,
      "loss": 0.8612,
      "step": 360
    },
    {
      "epoch": 1.0524781341107872,
      "grad_norm": 0.4195454108396945,
      "learning_rate": 2.0194522793868323e-05,
      "loss": 0.9009,
      "step": 361
    },
    {
      "epoch": 1.055393586005831,
      "grad_norm": 0.3896114588981958,
      "learning_rate": 2.009726254707095e-05,
      "loss": 0.919,
      "step": 362
    },
    {
      "epoch": 1.0583090379008746,
      "grad_norm": 0.36497741633912156,
      "learning_rate": 2e-05,
      "loss": 0.9151,
      "step": 363
    },
    {
      "epoch": 1.0612244897959184,
      "grad_norm": 0.35583146774397306,
      "learning_rate": 1.9902737452929052e-05,
      "loss": 0.8999,
      "step": 364
    },
    {
      "epoch": 1.064139941690962,
      "grad_norm": 0.3456016725198812,
      "learning_rate": 1.9805477206131677e-05,
      "loss": 0.8859,
      "step": 365
    },
    {
      "epoch": 1.0670553935860059,
      "grad_norm": 0.5966960662679052,
      "learning_rate": 1.9708221559827073e-05,
      "loss": 0.9015,
      "step": 366
    },
    {
      "epoch": 1.0699708454810495,
      "grad_norm": 0.3671094566365045,
      "learning_rate": 1.9610972814125618e-05,
      "loss": 0.9176,
      "step": 367
    },
    {
      "epoch": 1.0728862973760933,
      "grad_norm": 0.4390906706069723,
      "learning_rate": 1.9513733268974485e-05,
      "loss": 0.9444,
      "step": 368
    },
    {
      "epoch": 1.075801749271137,
      "grad_norm": 0.34661948587313707,
      "learning_rate": 1.941650522410325e-05,
      "loss": 0.8723,
      "step": 369
    },
    {
      "epoch": 1.0787172011661808,
      "grad_norm": 0.39816272068553876,
      "learning_rate": 1.9319290978969532e-05,
      "loss": 0.9432,
      "step": 370
    },
    {
      "epoch": 1.0816326530612246,
      "grad_norm": 0.3484825048580216,
      "learning_rate": 1.9222092832704556e-05,
      "loss": 0.9161,
      "step": 371
    },
    {
      "epoch": 1.0845481049562682,
      "grad_norm": 0.36769340343082263,
      "learning_rate": 1.9124913084058817e-05,
      "loss": 0.8537,
      "step": 372
    },
    {
      "epoch": 1.087463556851312,
      "grad_norm": 0.647745516060205,
      "learning_rate": 1.9027754031347715e-05,
      "loss": 0.9043,
      "step": 373
    },
    {
      "epoch": 1.0903790087463556,
      "grad_norm": 0.39468021998569647,
      "learning_rate": 1.8930617972397162e-05,
      "loss": 0.9155,
      "step": 374
    },
    {
      "epoch": 1.0932944606413995,
      "grad_norm": 0.5047238810446275,
      "learning_rate": 1.8833507204489286e-05,
      "loss": 0.9116,
      "step": 375
    },
    {
      "epoch": 1.096209912536443,
      "grad_norm": 0.38578546256744967,
      "learning_rate": 1.873642402430806e-05,
      "loss": 0.9446,
      "step": 376
    },
    {
      "epoch": 1.099125364431487,
      "grad_norm": 0.37853911957080766,
      "learning_rate": 1.8639370727885032e-05,
      "loss": 0.9033,
      "step": 377
    },
    {
      "epoch": 1.1020408163265305,
      "grad_norm": 0.39191145713635545,
      "learning_rate": 1.8542349610544965e-05,
      "loss": 0.8971,
      "step": 378
    },
    {
      "epoch": 1.1049562682215743,
      "grad_norm": 0.42552186647920914,
      "learning_rate": 1.8445362966851603e-05,
      "loss": 0.9197,
      "step": 379
    },
    {
      "epoch": 1.1078717201166182,
      "grad_norm": 0.39878496811419945,
      "learning_rate": 1.8348413090553356e-05,
      "loss": 0.8382,
      "step": 380
    },
    {
      "epoch": 1.1107871720116618,
      "grad_norm": 0.3532504119440214,
      "learning_rate": 1.8251502274529113e-05,
      "loss": 0.8854,
      "step": 381
    },
    {
      "epoch": 1.1137026239067056,
      "grad_norm": 0.3794396182708985,
      "learning_rate": 1.815463281073396e-05,
      "loss": 0.9256,
      "step": 382
    },
    {
      "epoch": 1.1166180758017492,
      "grad_norm": 0.3690962462197968,
      "learning_rate": 1.8057806990145006e-05,
      "loss": 0.9126,
      "step": 383
    },
    {
      "epoch": 1.119533527696793,
      "grad_norm": 0.33118238380078774,
      "learning_rate": 1.796102710270719e-05,
      "loss": 0.8978,
      "step": 384
    },
    {
      "epoch": 1.1224489795918366,
      "grad_norm": 0.4017437985742156,
      "learning_rate": 1.7864295437279123e-05,
      "loss": 0.9122,
      "step": 385
    },
    {
      "epoch": 1.1253644314868805,
      "grad_norm": 0.3374384561910696,
      "learning_rate": 1.7767614281578957e-05,
      "loss": 0.8897,
      "step": 386
    },
    {
      "epoch": 1.128279883381924,
      "grad_norm": 0.38242886488399963,
      "learning_rate": 1.7670985922130278e-05,
      "loss": 0.8855,
      "step": 387
    },
    {
      "epoch": 1.131195335276968,
      "grad_norm": 0.3118608652607213,
      "learning_rate": 1.757441264420805e-05,
      "loss": 0.8872,
      "step": 388
    },
    {
      "epoch": 1.1341107871720117,
      "grad_norm": 0.38385193075347296,
      "learning_rate": 1.7477896731784533e-05,
      "loss": 0.9566,
      "step": 389
    },
    {
      "epoch": 1.1370262390670554,
      "grad_norm": 0.320934960093107,
      "learning_rate": 1.738144046747529e-05,
      "loss": 0.842,
      "step": 390
    },
    {
      "epoch": 1.1399416909620992,
      "grad_norm": 0.39934131018687274,
      "learning_rate": 1.7285046132485213e-05,
      "loss": 0.8921,
      "step": 391
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.501779773738352,
      "learning_rate": 1.7188716006554514e-05,
      "loss": 0.8642,
      "step": 392
    },
    {
      "epoch": 1.1457725947521866,
      "grad_norm": 0.3830686077134007,
      "learning_rate": 1.7092452367904903e-05,
      "loss": 0.8758,
      "step": 393
    },
    {
      "epoch": 1.1486880466472302,
      "grad_norm": 0.5008440591261429,
      "learning_rate": 1.6996257493185612e-05,
      "loss": 0.9021,
      "step": 394
    },
    {
      "epoch": 1.151603498542274,
      "grad_norm": 0.4511494170269456,
      "learning_rate": 1.6900133657419636e-05,
      "loss": 0.8622,
      "step": 395
    },
    {
      "epoch": 1.1545189504373177,
      "grad_norm": 0.2984119660617534,
      "learning_rate": 1.680408313394986e-05,
      "loss": 0.8524,
      "step": 396
    },
    {
      "epoch": 1.1574344023323615,
      "grad_norm": 0.3812683259088031,
      "learning_rate": 1.670810819438532e-05,
      "loss": 0.9313,
      "step": 397
    },
    {
      "epoch": 1.1603498542274053,
      "grad_norm": 0.37166040845388637,
      "learning_rate": 1.6612211108547516e-05,
      "loss": 0.8665,
      "step": 398
    },
    {
      "epoch": 1.163265306122449,
      "grad_norm": 0.351603148836399,
      "learning_rate": 1.6516394144416644e-05,
      "loss": 0.8902,
      "step": 399
    },
    {
      "epoch": 1.1661807580174928,
      "grad_norm": 0.610085385951358,
      "learning_rate": 1.6420659568078057e-05,
      "loss": 0.8881,
      "step": 400
    },
    {
      "epoch": 1.1690962099125364,
      "grad_norm": 0.3874546159794478,
      "learning_rate": 1.6325009643668592e-05,
      "loss": 0.8647,
      "step": 401
    },
    {
      "epoch": 1.1720116618075802,
      "grad_norm": 0.38491777769529806,
      "learning_rate": 1.6229446633323082e-05,
      "loss": 0.8673,
      "step": 402
    },
    {
      "epoch": 1.1749271137026238,
      "grad_norm": 0.48051830259266204,
      "learning_rate": 1.613397279712081e-05,
      "loss": 0.9143,
      "step": 403
    },
    {
      "epoch": 1.1778425655976676,
      "grad_norm": 0.7099012144404129,
      "learning_rate": 1.603859039303209e-05,
      "loss": 0.9074,
      "step": 404
    },
    {
      "epoch": 1.1807580174927113,
      "grad_norm": 0.32314820225527935,
      "learning_rate": 1.5943301676864827e-05,
      "loss": 0.8979,
      "step": 405
    },
    {
      "epoch": 1.183673469387755,
      "grad_norm": 0.5871998008882374,
      "learning_rate": 1.5848108902211228e-05,
      "loss": 0.8903,
      "step": 406
    },
    {
      "epoch": 1.186588921282799,
      "grad_norm": 0.3369401972398898,
      "learning_rate": 1.5753014320394452e-05,
      "loss": 0.8972,
      "step": 407
    },
    {
      "epoch": 1.1895043731778425,
      "grad_norm": 0.3531724159844245,
      "learning_rate": 1.565802018041538e-05,
      "loss": 0.8644,
      "step": 408
    },
    {
      "epoch": 1.1924198250728864,
      "grad_norm": 0.9398965424727117,
      "learning_rate": 1.556312872889944e-05,
      "loss": 0.9311,
      "step": 409
    },
    {
      "epoch": 1.19533527696793,
      "grad_norm": 0.3689024843304816,
      "learning_rate": 1.546834221004346e-05,
      "loss": 0.9241,
      "step": 410
    },
    {
      "epoch": 1.1982507288629738,
      "grad_norm": 0.43093464215869326,
      "learning_rate": 1.5373662865562577e-05,
      "loss": 0.8911,
      "step": 411
    },
    {
      "epoch": 1.2011661807580174,
      "grad_norm": 0.4465894257328085,
      "learning_rate": 1.5279092934637258e-05,
      "loss": 0.8496,
      "step": 412
    },
    {
      "epoch": 1.2040816326530612,
      "grad_norm": 0.34210040207353676,
      "learning_rate": 1.5184634653860309e-05,
      "loss": 0.8606,
      "step": 413
    },
    {
      "epoch": 1.2069970845481048,
      "grad_norm": 0.41093683620818694,
      "learning_rate": 1.5090290257184019e-05,
      "loss": 0.8848,
      "step": 414
    },
    {
      "epoch": 1.2099125364431487,
      "grad_norm": 0.35185182480819926,
      "learning_rate": 1.499606197586727e-05,
      "loss": 0.9152,
      "step": 415
    },
    {
      "epoch": 1.2128279883381925,
      "grad_norm": 0.38820257625897675,
      "learning_rate": 1.4901952038422832e-05,
      "loss": 0.8928,
      "step": 416
    },
    {
      "epoch": 1.215743440233236,
      "grad_norm": 0.371973353051329,
      "learning_rate": 1.480796267056458e-05,
      "loss": 0.8885,
      "step": 417
    },
    {
      "epoch": 1.21865889212828,
      "grad_norm": 0.4007535912082386,
      "learning_rate": 1.4714096095154942e-05,
      "loss": 0.867,
      "step": 418
    },
    {
      "epoch": 1.2215743440233235,
      "grad_norm": 0.3690054663984619,
      "learning_rate": 1.4620354532152268e-05,
      "loss": 0.889,
      "step": 419
    },
    {
      "epoch": 1.2244897959183674,
      "grad_norm": 0.37463553204342753,
      "learning_rate": 1.4526740198558345e-05,
      "loss": 0.8706,
      "step": 420
    },
    {
      "epoch": 1.227405247813411,
      "grad_norm": 0.4952730464254449,
      "learning_rate": 1.4433255308365973e-05,
      "loss": 0.8401,
      "step": 421
    },
    {
      "epoch": 1.2303206997084548,
      "grad_norm": 0.345766761417753,
      "learning_rate": 1.4339902072506591e-05,
      "loss": 0.8835,
      "step": 422
    },
    {
      "epoch": 1.2332361516034984,
      "grad_norm": 1.463217273899525,
      "learning_rate": 1.4246682698798012e-05,
      "loss": 0.8907,
      "step": 423
    },
    {
      "epoch": 1.2361516034985423,
      "grad_norm": 0.39821570357245056,
      "learning_rate": 1.4153599391892143e-05,
      "loss": 0.9214,
      "step": 424
    },
    {
      "epoch": 1.239067055393586,
      "grad_norm": 0.3433998600071002,
      "learning_rate": 1.4060654353222942e-05,
      "loss": 0.8962,
      "step": 425
    },
    {
      "epoch": 1.2419825072886297,
      "grad_norm": 0.4000515497205946,
      "learning_rate": 1.3967849780954277e-05,
      "loss": 0.9037,
      "step": 426
    },
    {
      "epoch": 1.2448979591836735,
      "grad_norm": 0.9571521264143225,
      "learning_rate": 1.3875187869927965e-05,
      "loss": 0.91,
      "step": 427
    },
    {
      "epoch": 1.2478134110787171,
      "grad_norm": 0.3733616626840636,
      "learning_rate": 1.3782670811611875e-05,
      "loss": 0.8817,
      "step": 428
    },
    {
      "epoch": 1.250728862973761,
      "grad_norm": 0.3642809314159708,
      "learning_rate": 1.3690300794048085e-05,
      "loss": 0.8813,
      "step": 429
    },
    {
      "epoch": 1.2536443148688048,
      "grad_norm": 0.3647741657803098,
      "learning_rate": 1.3598080001801126e-05,
      "loss": 0.9274,
      "step": 430
    },
    {
      "epoch": 1.2565597667638484,
      "grad_norm": 0.3458677417744315,
      "learning_rate": 1.3506010615906333e-05,
      "loss": 0.9027,
      "step": 431
    },
    {
      "epoch": 1.259475218658892,
      "grad_norm": 0.34251500677540714,
      "learning_rate": 1.341409481381827e-05,
      "loss": 0.8474,
      "step": 432
    },
    {
      "epoch": 1.2623906705539358,
      "grad_norm": 0.3190350803534079,
      "learning_rate": 1.332233476935921e-05,
      "loss": 0.8459,
      "step": 433
    },
    {
      "epoch": 1.2653061224489797,
      "grad_norm": 0.3265461354474515,
      "learning_rate": 1.3230732652667735e-05,
      "loss": 0.8689,
      "step": 434
    },
    {
      "epoch": 1.2682215743440233,
      "grad_norm": 0.3267958005137338,
      "learning_rate": 1.3139290630147426e-05,
      "loss": 0.8875,
      "step": 435
    },
    {
      "epoch": 1.271137026239067,
      "grad_norm": 0.38778316009874764,
      "learning_rate": 1.304801086441559e-05,
      "loss": 0.8932,
      "step": 436
    },
    {
      "epoch": 1.2740524781341107,
      "grad_norm": 0.3410085655324801,
      "learning_rate": 1.2956895514252155e-05,
      "loss": 0.9059,
      "step": 437
    },
    {
      "epoch": 1.2769679300291545,
      "grad_norm": 0.41937944828658263,
      "learning_rate": 1.2865946734548584e-05,
      "loss": 0.9002,
      "step": 438
    },
    {
      "epoch": 1.2798833819241984,
      "grad_norm": 0.38182491793130874,
      "learning_rate": 1.2775166676256942e-05,
      "loss": 0.9464,
      "step": 439
    },
    {
      "epoch": 1.282798833819242,
      "grad_norm": 0.36240327212282164,
      "learning_rate": 1.2684557486338991e-05,
      "loss": 0.9037,
      "step": 440
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.38163895310199947,
      "learning_rate": 1.2594121307715441e-05,
      "loss": 0.8961,
      "step": 441
    },
    {
      "epoch": 1.2886297376093294,
      "grad_norm": 0.4177515236060373,
      "learning_rate": 1.2503860279215242e-05,
      "loss": 0.8718,
      "step": 442
    },
    {
      "epoch": 1.2915451895043732,
      "grad_norm": 0.3414559830348138,
      "learning_rate": 1.2413776535525043e-05,
      "loss": 0.8944,
      "step": 443
    },
    {
      "epoch": 1.2944606413994169,
      "grad_norm": 0.3444285556032968,
      "learning_rate": 1.2323872207138666e-05,
      "loss": 0.8882,
      "step": 444
    },
    {
      "epoch": 1.2973760932944607,
      "grad_norm": 0.3481275643120278,
      "learning_rate": 1.2234149420306731e-05,
      "loss": 0.8574,
      "step": 445
    },
    {
      "epoch": 1.3002915451895043,
      "grad_norm": 0.39334877331174234,
      "learning_rate": 1.214461029698639e-05,
      "loss": 0.9041,
      "step": 446
    },
    {
      "epoch": 1.3032069970845481,
      "grad_norm": 0.45396505769468926,
      "learning_rate": 1.2055256954791114e-05,
      "loss": 0.8161,
      "step": 447
    },
    {
      "epoch": 1.306122448979592,
      "grad_norm": 0.33669105009228384,
      "learning_rate": 1.1966091506940616e-05,
      "loss": 0.8329,
      "step": 448
    },
    {
      "epoch": 1.3090379008746356,
      "grad_norm": 0.404159242739437,
      "learning_rate": 1.1877116062210891e-05,
      "loss": 0.8878,
      "step": 449
    },
    {
      "epoch": 1.3119533527696792,
      "grad_norm": 0.36088083861016024,
      "learning_rate": 1.1788332724884335e-05,
      "loss": 0.8706,
      "step": 450
    },
    {
      "epoch": 1.314868804664723,
      "grad_norm": 0.36792996117202054,
      "learning_rate": 1.1699743594699969e-05,
      "loss": 0.8936,
      "step": 451
    },
    {
      "epoch": 1.3177842565597668,
      "grad_norm": 0.349538085141998,
      "learning_rate": 1.1611350766803779e-05,
      "loss": 0.9015,
      "step": 452
    },
    {
      "epoch": 1.3206997084548104,
      "grad_norm": 0.334875040431663,
      "learning_rate": 1.1523156331699193e-05,
      "loss": 0.8756,
      "step": 453
    },
    {
      "epoch": 1.3236151603498543,
      "grad_norm": 0.3531907780008996,
      "learning_rate": 1.143516237519762e-05,
      "loss": 0.8658,
      "step": 454
    },
    {
      "epoch": 1.3265306122448979,
      "grad_norm": 0.362184223903246,
      "learning_rate": 1.1347370978369079e-05,
      "loss": 0.9037,
      "step": 455
    },
    {
      "epoch": 1.3294460641399417,
      "grad_norm": 0.3587468921176296,
      "learning_rate": 1.1259784217493066e-05,
      "loss": 0.8701,
      "step": 456
    },
    {
      "epoch": 1.3323615160349855,
      "grad_norm": 0.3298772264662029,
      "learning_rate": 1.1172404164009407e-05,
      "loss": 0.8736,
      "step": 457
    },
    {
      "epoch": 1.3352769679300291,
      "grad_norm": 0.3815272524154801,
      "learning_rate": 1.1085232884469236e-05,
      "loss": 0.879,
      "step": 458
    },
    {
      "epoch": 1.3381924198250728,
      "grad_norm": 0.36822484912081677,
      "learning_rate": 1.099827244048618e-05,
      "loss": 0.9244,
      "step": 459
    },
    {
      "epoch": 1.3411078717201166,
      "grad_norm": 0.36072841946566814,
      "learning_rate": 1.091152488868757e-05,
      "loss": 0.8999,
      "step": 460
    },
    {
      "epoch": 1.3440233236151604,
      "grad_norm": 0.33888396618261474,
      "learning_rate": 1.0824992280665795e-05,
      "loss": 0.8572,
      "step": 461
    },
    {
      "epoch": 1.346938775510204,
      "grad_norm": 0.3901819048276413,
      "learning_rate": 1.073867666292979e-05,
      "loss": 0.9347,
      "step": 462
    },
    {
      "epoch": 1.3498542274052479,
      "grad_norm": 0.40223314649198144,
      "learning_rate": 1.0652580076856651e-05,
      "loss": 0.9083,
      "step": 463
    },
    {
      "epoch": 1.3527696793002915,
      "grad_norm": 0.3491884382940672,
      "learning_rate": 1.0566704558643346e-05,
      "loss": 0.8786,
      "step": 464
    },
    {
      "epoch": 1.3556851311953353,
      "grad_norm": 0.4415544695353861,
      "learning_rate": 1.048105213925853e-05,
      "loss": 0.8776,
      "step": 465
    },
    {
      "epoch": 1.3586005830903791,
      "grad_norm": 0.3453075343303145,
      "learning_rate": 1.0395624844394572e-05,
      "loss": 0.9093,
      "step": 466
    },
    {
      "epoch": 1.3615160349854227,
      "grad_norm": 0.340399019623445,
      "learning_rate": 1.0310424694419577e-05,
      "loss": 0.8847,
      "step": 467
    },
    {
      "epoch": 1.3644314868804663,
      "grad_norm": 0.35072478611605545,
      "learning_rate": 1.0225453704329672e-05,
      "loss": 0.8676,
      "step": 468
    },
    {
      "epoch": 1.3673469387755102,
      "grad_norm": 0.366685868167488,
      "learning_rate": 1.0140713883701291e-05,
      "loss": 0.9,
      "step": 469
    },
    {
      "epoch": 1.370262390670554,
      "grad_norm": 0.3970701863890074,
      "learning_rate": 1.0056207236643702e-05,
      "loss": 0.9122,
      "step": 470
    },
    {
      "epoch": 1.3731778425655976,
      "grad_norm": 0.37213823009472397,
      "learning_rate": 9.971935761751574e-06,
      "loss": 0.8945,
      "step": 471
    },
    {
      "epoch": 1.3760932944606414,
      "grad_norm": 0.3454352920544214,
      "learning_rate": 9.887901452057713e-06,
      "loss": 0.8981,
      "step": 472
    },
    {
      "epoch": 1.379008746355685,
      "grad_norm": 0.360228295000985,
      "learning_rate": 9.804106294985929e-06,
      "loss": 0.8879,
      "step": 473
    },
    {
      "epoch": 1.3819241982507289,
      "grad_norm": 0.42020731308194914,
      "learning_rate": 9.720552272304052e-06,
      "loss": 0.9226,
      "step": 474
    },
    {
      "epoch": 1.3848396501457727,
      "grad_norm": 0.3412811092807568,
      "learning_rate": 9.63724136007705e-06,
      "loss": 0.8304,
      "step": 475
    },
    {
      "epoch": 1.3877551020408163,
      "grad_norm": 0.3872889292215835,
      "learning_rate": 9.554175528620268e-06,
      "loss": 0.9462,
      "step": 476
    },
    {
      "epoch": 1.39067055393586,
      "grad_norm": 0.34781062699895504,
      "learning_rate": 9.471356742452881e-06,
      "loss": 0.8765,
      "step": 477
    },
    {
      "epoch": 1.3935860058309038,
      "grad_norm": 0.3483345892307839,
      "learning_rate": 9.388786960251405e-06,
      "loss": 0.8475,
      "step": 478
    },
    {
      "epoch": 1.3965014577259476,
      "grad_norm": 0.3790773367687499,
      "learning_rate": 9.30646813480336e-06,
      "loss": 0.9009,
      "step": 479
    },
    {
      "epoch": 1.3994169096209912,
      "grad_norm": 0.4205998029964938,
      "learning_rate": 9.224402212961096e-06,
      "loss": 0.8873,
      "step": 480
    },
    {
      "epoch": 1.402332361516035,
      "grad_norm": 0.36628713096418625,
      "learning_rate": 9.142591135595782e-06,
      "loss": 0.9311,
      "step": 481
    },
    {
      "epoch": 1.4052478134110786,
      "grad_norm": 0.3435864317922267,
      "learning_rate": 9.061036837551467e-06,
      "loss": 0.8952,
      "step": 482
    },
    {
      "epoch": 1.4081632653061225,
      "grad_norm": 0.377356721465227,
      "learning_rate": 8.979741247599316e-06,
      "loss": 0.9334,
      "step": 483
    },
    {
      "epoch": 1.4110787172011663,
      "grad_norm": 0.36256826670709436,
      "learning_rate": 8.89870628839203e-06,
      "loss": 0.9042,
      "step": 484
    },
    {
      "epoch": 1.41399416909621,
      "grad_norm": 0.3531404440716723,
      "learning_rate": 8.817933876418349e-06,
      "loss": 0.8659,
      "step": 485
    },
    {
      "epoch": 1.4169096209912537,
      "grad_norm": 0.4187534028031517,
      "learning_rate": 8.737425921957726e-06,
      "loss": 0.8303,
      "step": 486
    },
    {
      "epoch": 1.4198250728862973,
      "grad_norm": 0.3691883637551743,
      "learning_rate": 8.657184329035151e-06,
      "loss": 0.9052,
      "step": 487
    },
    {
      "epoch": 1.4227405247813412,
      "grad_norm": 0.38858873680533296,
      "learning_rate": 8.577210995376135e-06,
      "loss": 0.8786,
      "step": 488
    },
    {
      "epoch": 1.4256559766763848,
      "grad_norm": 0.36643937908368496,
      "learning_rate": 8.497507812361826e-06,
      "loss": 0.9161,
      "step": 489
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.3823114752504239,
      "learning_rate": 8.418076664984236e-06,
      "loss": 0.8946,
      "step": 490
    },
    {
      "epoch": 1.4314868804664722,
      "grad_norm": 0.35170467761018115,
      "learning_rate": 8.338919431801738e-06,
      "loss": 0.8571,
      "step": 491
    },
    {
      "epoch": 1.434402332361516,
      "grad_norm": 0.3701359423395854,
      "learning_rate": 8.260037984894553e-06,
      "loss": 0.8641,
      "step": 492
    },
    {
      "epoch": 1.4373177842565599,
      "grad_norm": 0.3665017275322417,
      "learning_rate": 8.181434189820552e-06,
      "loss": 0.8873,
      "step": 493
    },
    {
      "epoch": 1.4402332361516035,
      "grad_norm": 0.3582809415312125,
      "learning_rate": 8.103109905571062e-06,
      "loss": 0.9288,
      "step": 494
    },
    {
      "epoch": 1.4431486880466473,
      "grad_norm": 0.31631298202014885,
      "learning_rate": 8.02506698452697e-06,
      "loss": 0.825,
      "step": 495
    },
    {
      "epoch": 1.446064139941691,
      "grad_norm": 0.3534409758588844,
      "learning_rate": 7.947307272414874e-06,
      "loss": 0.9054,
      "step": 496
    },
    {
      "epoch": 1.4489795918367347,
      "grad_norm": 0.3598528867752392,
      "learning_rate": 7.869832608263427e-06,
      "loss": 0.8922,
      "step": 497
    },
    {
      "epoch": 1.4518950437317784,
      "grad_norm": 0.3684455264389801,
      "learning_rate": 7.792644824359858e-06,
      "loss": 0.8585,
      "step": 498
    },
    {
      "epoch": 1.4548104956268222,
      "grad_norm": 0.38121906726183624,
      "learning_rate": 7.715745746206644e-06,
      "loss": 0.8459,
      "step": 499
    },
    {
      "epoch": 1.4577259475218658,
      "grad_norm": 0.3638442962640907,
      "learning_rate": 7.639137192478334e-06,
      "loss": 0.8539,
      "step": 500
    },
    {
      "epoch": 1.4606413994169096,
      "grad_norm": 0.40163215440287875,
      "learning_rate": 7.5628209749785084e-06,
      "loss": 0.8732,
      "step": 501
    },
    {
      "epoch": 1.4635568513119535,
      "grad_norm": 0.34533156621538597,
      "learning_rate": 7.486798898596976e-06,
      "loss": 0.8811,
      "step": 502
    },
    {
      "epoch": 1.466472303206997,
      "grad_norm": 0.43990397905816536,
      "learning_rate": 7.4110727612670575e-06,
      "loss": 0.8852,
      "step": 503
    },
    {
      "epoch": 1.469387755102041,
      "grad_norm": 0.5289781287921499,
      "learning_rate": 7.3356443539230685e-06,
      "loss": 0.8236,
      "step": 504
    },
    {
      "epoch": 1.4723032069970845,
      "grad_norm": 0.3328540341889078,
      "learning_rate": 7.260515460457958e-06,
      "loss": 0.8851,
      "step": 505
    },
    {
      "epoch": 1.4752186588921283,
      "grad_norm": 0.4870383351032914,
      "learning_rate": 7.185687857681141e-06,
      "loss": 0.9001,
      "step": 506
    },
    {
      "epoch": 1.478134110787172,
      "grad_norm": 0.37408255528035744,
      "learning_rate": 7.1111633152764705e-06,
      "loss": 0.918,
      "step": 507
    },
    {
      "epoch": 1.4810495626822158,
      "grad_norm": 0.3833103179567533,
      "learning_rate": 7.036943595760353e-06,
      "loss": 0.8998,
      "step": 508
    },
    {
      "epoch": 1.4839650145772594,
      "grad_norm": 0.4014548252016667,
      "learning_rate": 6.963030454440111e-06,
      "loss": 0.8555,
      "step": 509
    },
    {
      "epoch": 1.4868804664723032,
      "grad_norm": 0.390416467602609,
      "learning_rate": 6.889425639372427e-06,
      "loss": 0.915,
      "step": 510
    },
    {
      "epoch": 1.489795918367347,
      "grad_norm": 0.36354946444392827,
      "learning_rate": 6.816130891322048e-06,
      "loss": 0.8467,
      "step": 511
    },
    {
      "epoch": 1.4927113702623906,
      "grad_norm": 0.34245284338451154,
      "learning_rate": 6.743147943720561e-06,
      "loss": 0.8704,
      "step": 512
    },
    {
      "epoch": 1.4956268221574345,
      "grad_norm": 0.3577510719440281,
      "learning_rate": 6.6704785226254455e-06,
      "loss": 0.8741,
      "step": 513
    },
    {
      "epoch": 1.498542274052478,
      "grad_norm": 0.4257938974909593,
      "learning_rate": 6.598124346679238e-06,
      "loss": 0.9088,
      "step": 514
    },
    {
      "epoch": 1.501457725947522,
      "grad_norm": 0.40239598681570304,
      "learning_rate": 6.526087127068857e-06,
      "loss": 0.8626,
      "step": 515
    },
    {
      "epoch": 1.5043731778425657,
      "grad_norm": 0.33201278139400314,
      "learning_rate": 6.4543685674851834e-06,
      "loss": 0.8985,
      "step": 516
    }
  ],
  "logging_steps": 1,
  "max_steps": 686,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 172,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2140852218494976.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}