{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 249,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 5.000676195286779,
      "learning_rate": 2.5e-05,
      "loss": 1.4173,
      "step": 1
    },
    {
      "epoch": 0.01,
      "grad_norm": 5.533334563322662,
      "learning_rate": 5e-05,
      "loss": 1.4686,
      "step": 2
    },
    {
      "epoch": 0.01,
      "grad_norm": 2.1215141861819773,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.1569,
      "step": 3
    },
    {
      "epoch": 0.02,
      "grad_norm": 2.1829474332972323,
      "learning_rate": 0.0001,
      "loss": 1.1048,
      "step": 4
    },
    {
      "epoch": 0.02,
      "grad_norm": 2.0028696101556926,
      "learning_rate": 0.000125,
      "loss": 1.0818,
      "step": 5
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.5248690364202462,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.0337,
      "step": 6
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.1217144084706645,
      "learning_rate": 0.000175,
      "loss": 0.9547,
      "step": 7
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.4464744842578992,
      "learning_rate": 0.0002,
      "loss": 0.9475,
      "step": 8
    },
    {
      "epoch": 0.04,
      "grad_norm": 1695.2119602484477,
      "learning_rate": 0.00019999150370633988,
      "loss": 2.8217,
      "step": 9
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.2498837065378345,
      "learning_rate": 0.00019996601626909964,
      "loss": 0.9227,
      "step": 10
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.0785140860234272,
      "learning_rate": 0.00019992354201925428,
      "loss": 0.9174,
      "step": 11
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.8766759988692014,
      "learning_rate": 0.0001998640881742778,
      "loss": 0.9297,
      "step": 12
    },
    {
      "epoch": 0.05,
      "grad_norm": 7.243650858657556,
      "learning_rate": 0.00019978766483691676,
      "loss": 0.892,
      "step": 13
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.538431288719503,
      "learning_rate": 0.0001996942849934735,
      "loss": 0.8863,
      "step": 14
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.370383009713962,
      "learning_rate": 0.00019958396451159936,
      "loss": 0.8137,
      "step": 15
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.0117664660143928,
      "learning_rate": 0.0001994567221375987,
      "loss": 0.8547,
      "step": 16
    },
    {
      "epoch": 0.07,
      "grad_norm": 1.1793686627309208,
      "learning_rate": 0.00019931257949324288,
      "loss": 0.889,
      "step": 17
    },
    {
      "epoch": 0.07,
      "grad_norm": 6.742266804538591,
      "learning_rate": 0.00019915156107209675,
      "loss": 0.8061,
      "step": 18
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.0901022322430638,
      "learning_rate": 0.000198973694235356,
      "loss": 0.8228,
      "step": 19
    },
    {
      "epoch": 0.08,
      "grad_norm": 2.50478337872783,
      "learning_rate": 0.00019877900920719827,
      "loss": 0.8285,
      "step": 20
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.1163796098877177,
      "learning_rate": 0.00019856753906964686,
      "loss": 0.7634,
      "step": 21
    },
    {
      "epoch": 0.09,
      "grad_norm": 1.2717680968650331,
      "learning_rate": 0.0001983393197569497,
      "loss": 0.8451,
      "step": 22
    },
    {
      "epoch": 0.09,
      "grad_norm": 1.1035753559158878,
      "learning_rate": 0.00019809439004947268,
      "loss": 0.8134,
      "step": 23
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.0228605041664325,
      "learning_rate": 0.00019783279156711022,
      "loss": 0.7859,
      "step": 24
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.0963594515481832,
      "learning_rate": 0.0001975545687622129,
      "loss": 0.7781,
      "step": 25
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.2366762317778497,
      "learning_rate": 0.00019725976891203376,
      "loss": 0.8779,
      "step": 26
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.9640376193091488,
      "learning_rate": 0.00019694844211069477,
      "loss": 0.7786,
      "step": 27
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.9093723580811977,
      "learning_rate": 0.00019662064126067452,
      "loss": 0.7569,
      "step": 28
    },
    {
      "epoch": 0.12,
      "grad_norm": 1.0668396721156181,
      "learning_rate": 0.00019627642206381863,
      "loss": 0.7912,
      "step": 29
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.9305159138901695,
      "learning_rate": 0.00019591584301187478,
      "loss": 0.7333,
      "step": 30
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.8786594903907613,
      "learning_rate": 0.00019553896537655318,
      "loss": 0.7597,
      "step": 31
    },
    {
      "epoch": 0.13,
      "grad_norm": 1.003046456072257,
      "learning_rate": 0.0001951458531991151,
      "loss": 0.7586,
      "step": 32
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.8294893505023185,
      "learning_rate": 0.00019473657327949054,
      "loss": 0.7481,
      "step": 33
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.9425474789456502,
      "learning_rate": 0.00019431119516492726,
      "loss": 0.7381,
      "step": 34
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.7607927866058226,
      "learning_rate": 0.00019386979113817282,
      "loss": 0.7598,
      "step": 35
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.8983977527007998,
      "learning_rate": 0.0001934124362051919,
      "loss": 0.7781,
      "step": 36
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.7601960470127274,
      "learning_rate": 0.00019293920808242083,
      "loss": 0.7704,
      "step": 37
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.8568120633321497,
      "learning_rate": 0.0001924501871835616,
      "loss": 0.7885,
      "step": 38
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.8412758002249293,
      "learning_rate": 0.00019194545660591752,
      "loss": 0.6997,
      "step": 39
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.3840877739036568,
      "learning_rate": 0.00019142510211627264,
      "loss": 0.7475,
      "step": 40
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.8713962244801455,
      "learning_rate": 0.000190889212136318,
      "loss": 0.746,
      "step": 41
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.8405881719204712,
      "learning_rate": 0.00019033787772762645,
      "loss": 0.7537,
      "step": 42
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.8881177433012806,
      "learning_rate": 0.00018977119257617878,
      "loss": 0.772,
      "step": 43
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.8327207244772546,
      "learning_rate": 0.00018918925297644416,
      "loss": 0.7671,
      "step": 44
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.7172850301202007,
      "learning_rate": 0.00018859215781501725,
      "loss": 0.7013,
      "step": 45
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.8520019963524466,
      "learning_rate": 0.0001879800085538147,
      "loss": 0.6775,
      "step": 46
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.7905901994214263,
      "learning_rate": 0.0001873529092128343,
      "loss": 0.7543,
      "step": 47
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.885042022048047,
      "learning_rate": 0.00018671096635247914,
      "loss": 0.7772,
      "step": 48
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.7923851096939509,
      "learning_rate": 0.00018605428905545032,
      "loss": 0.7647,
      "step": 49
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.7639779196406391,
      "learning_rate": 0.0001853829889082109,
      "loss": 0.73,
      "step": 50
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.7201688215295416,
      "learning_rate": 0.00018469717998202462,
      "loss": 0.7534,
      "step": 51
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.7092609652695424,
      "learning_rate": 0.00018399697881357212,
      "loss": 0.7402,
      "step": 52
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.7862922090916423,
      "learning_rate": 0.00018328250438514836,
      "loss": 0.6988,
      "step": 53
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.75620823509439,
      "learning_rate": 0.00018255387810444448,
      "loss": 0.7592,
      "step": 54
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.7979316767550451,
      "learning_rate": 0.0001818112237839174,
      "loss": 0.7174,
      "step": 55
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.7690661744799511,
      "learning_rate": 0.00018105466761975109,
      "loss": 0.7082,
      "step": 56
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.7543971879671839,
      "learning_rate": 0.00018028433817041236,
      "loss": 0.7334,
      "step": 57
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.7274070523128118,
      "learning_rate": 0.00017950036633480556,
      "loss": 0.7217,
      "step": 58
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.7805160984212568,
      "learning_rate": 0.00017870288533002938,
      "loss": 0.6994,
      "step": 59
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.7642678319646234,
      "learning_rate": 0.00017789203066873998,
      "loss": 0.7349,
      "step": 60
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.7068890647609225,
      "learning_rate": 0.00017706794013612364,
      "loss": 0.7408,
      "step": 61
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.7821294112932925,
      "learning_rate": 0.00017623075376648376,
      "loss": 0.718,
      "step": 62
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.7229664348394781,
      "learning_rate": 0.00017538061381944524,
      "loss": 0.7418,
      "step": 63
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.6951044250779959,
      "learning_rate": 0.0001745176647557809,
      "loss": 0.6934,
      "step": 64
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.73099474521294,
      "learning_rate": 0.00017364205321286394,
      "loss": 0.7135,
      "step": 65
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.6940403521727994,
      "learning_rate": 0.00017275392797975032,
      "loss": 0.7765,
      "step": 66
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.7211852964311306,
      "learning_rate": 0.00017185343997189588,
      "loss": 0.7427,
      "step": 67
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.6503797788991111,
      "learning_rate": 0.00017094074220551158,
      "loss": 0.7161,
      "step": 68
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.7010217970027596,
      "learning_rate": 0.0001700159897715624,
      "loss": 0.747,
      "step": 69
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.6787203912897876,
      "learning_rate": 0.00016907933980941312,
      "loss": 0.6659,
      "step": 70
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.6654181924251962,
      "learning_rate": 0.0001681309514801265,
      "loss": 0.6811,
      "step": 71
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.6670712031136201,
      "learning_rate": 0.00016717098593941752,
      "loss": 0.7116,
      "step": 72
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.6505402907966938,
      "learning_rate": 0.00016619960631026888,
      "loss": 0.7259,
      "step": 73
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.6860899500587603,
      "learning_rate": 0.0001652169776552123,
      "loss": 0.7082,
      "step": 74
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.6590732633850581,
      "learning_rate": 0.00016422326694828007,
      "loss": 0.6806,
      "step": 75
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.6360343519947935,
      "learning_rate": 0.00016321864304663173,
      "loss": 0.6951,
      "step": 76
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.6698752473367972,
      "learning_rate": 0.000162203276661861,
      "loss": 0.7284,
      "step": 77
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.686029660179383,
      "learning_rate": 0.00016117734033098744,
      "loss": 0.7253,
      "step": 78
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.6709613558030975,
      "learning_rate": 0.00016014100838713797,
      "loss": 0.7116,
      "step": 79
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.7224879379478429,
      "learning_rate": 0.000159094456929923,
      "loss": 0.7016,
      "step": 80
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.6428021529957839,
      "learning_rate": 0.0001580378637955128,
      "loss": 0.666,
      "step": 81
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.6960916861503723,
      "learning_rate": 0.00015697140852641834,
      "loss": 0.6997,
      "step": 82
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.7255100351288608,
      "learning_rate": 0.00015589527234098247,
      "loss": 0.746,
      "step": 83
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.6986598054325619,
      "learning_rate": 0.00015480963810258613,
      "loss": 0.6955,
      "step": 84
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.6942988324021939,
      "learning_rate": 0.00015371469028857532,
      "loss": 0.73,
      "step": 85
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.6464360901011618,
      "learning_rate": 0.00015261061495891345,
      "loss": 0.7066,
      "step": 86
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.6817451321331462,
      "learning_rate": 0.0001514975997245649,
      "loss": 0.6862,
      "step": 87
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.6836150931516597,
      "learning_rate": 0.00015037583371561535,
      "loss": 0.701,
      "step": 88
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.6521598742458213,
      "learning_rate": 0.0001492455075491334,
      "loss": 0.6951,
      "step": 89
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.6840291643645185,
      "learning_rate": 0.00014810681329677987,
      "loss": 0.6891,
      "step": 90
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.7119537505083154,
      "learning_rate": 0.00014695994445216985,
      "loss": 0.7055,
      "step": 91
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.6809155849632806,
      "learning_rate": 0.00014580509589799329,
      "loss": 0.7158,
      "step": 92
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.6582134532528549,
      "learning_rate": 0.00014464246387289913,
      "loss": 0.6816,
      "step": 93
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.6858460794714393,
      "learning_rate": 0.00014347224593814944,
      "loss": 0.7331,
      "step": 94
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.6279879762170197,
      "learning_rate": 0.00014229464094404865,
      "loss": 0.6948,
      "step": 95
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.6781606487340365,
      "learning_rate": 0.00014110984899615367,
      "loss": 0.7012,
      "step": 96
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.6235005575378192,
      "learning_rate": 0.0001399180714212708,
      "loss": 0.6856,
      "step": 97
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.6222064438389479,
      "learning_rate": 0.00013871951073324507,
      "loss": 0.7224,
      "step": 98
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.6509887436189455,
      "learning_rate": 0.0001375143705985481,
      "loss": 0.6928,
      "step": 99
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.656042231341122,
      "learning_rate": 0.00013630285580166945,
      "loss": 0.6762,
      "step": 100
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.7077822267736881,
      "learning_rate": 0.000135085172210319,
      "loss": 0.6925,
      "step": 101
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.6377433248181216,
      "learning_rate": 0.00013386152674044422,
      "loss": 0.6744,
      "step": 102
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.6794295874230116,
      "learning_rate": 0.00013263212732107012,
      "loss": 0.7011,
      "step": 103
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.643130008468374,
      "learning_rate": 0.00013139718285896655,
      "loss": 0.6569,
      "step": 104
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.6362056274475615,
      "learning_rate": 0.00013015690320314954,
      "loss": 0.7033,
      "step": 105
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.635021955027263,
      "learning_rate": 0.00012891149910922267,
      "loss": 0.6963,
      "step": 106
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.6264643470826873,
      "learning_rate": 0.00012766118220356408,
      "loss": 0.6894,
      "step": 107
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.6342127038295544,
      "learning_rate": 0.0001264061649473657,
      "loss": 0.6738,
      "step": 108
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.6621446452478139,
      "learning_rate": 0.00012514666060053076,
      "loss": 0.6758,
      "step": 109
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.6226477303367899,
      "learning_rate": 0.00012388288318543512,
      "loss": 0.6503,
      "step": 110
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.6596957404307451,
      "learning_rate": 0.00012261504745055964,
      "loss": 0.651,
      "step": 111
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.6351342299233715,
      "learning_rate": 0.00012134336883399855,
      "loss": 0.6522,
      "step": 112
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.6285397550645089,
      "learning_rate": 0.00012006806342685126,
      "loss": 0.7196,
      "step": 113
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.6776322591334888,
      "learning_rate": 0.00011878934793650273,
      "loss": 0.5976,
      "step": 114
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.6928273118779775,
      "learning_rate": 0.00011750743964979918,
      "loss": 0.6546,
      "step": 115
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.639279635845659,
      "learning_rate": 0.00011622255639612554,
      "loss": 0.6946,
      "step": 116
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.6515482805820111,
      "learning_rate": 0.00011493491651039077,
      "loss": 0.698,
      "step": 117
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.660223620241514,
      "learning_rate": 0.00011364473879592674,
      "loss": 0.673,
      "step": 118
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.666404899679247,
      "learning_rate": 0.0001123522424873082,
      "loss": 0.6705,
      "step": 119
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.643302464795397,
      "learning_rate": 0.000111057647213099,
      "loss": 0.66,
      "step": 120
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.6221645734900332,
      "learning_rate": 0.00010976117295853154,
      "loss": 0.6306,
      "step": 121
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.6114539557810817,
      "learning_rate": 0.00010846304002812564,
      "loss": 0.6688,
      "step": 122
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.6441864804470223,
      "learning_rate": 0.00010716346900825299,
      "loss": 0.6914,
      "step": 123
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.6126099908354491,
      "learning_rate": 0.00010586268072965396,
      "loss": 0.6847,
      "step": 124
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.6226190206986176,
      "learning_rate": 0.00010456089622991263,
      "loss": 0.6405,
      "step": 125
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.5913341649918665,
      "learning_rate": 0.00010325833671589687,
      "loss": 0.7136,
      "step": 126
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.6063136858538771,
      "learning_rate": 0.00010195522352616943,
      "loss": 0.643,
      "step": 127
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.6474255343280048,
      "learning_rate": 0.00010065177809337702,
      "loss": 0.7012,
      "step": 128
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.611817998176696,
      "learning_rate": 9.934822190662299e-05,
      "loss": 0.7232,
      "step": 129
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.6315544767518864,
      "learning_rate": 9.80447764738306e-05,
      "loss": 0.6531,
      "step": 130
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.5824211156475344,
      "learning_rate": 9.674166328410318e-05,
      "loss": 0.6308,
      "step": 131
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.6172010731454831,
      "learning_rate": 9.543910377008742e-05,
      "loss": 0.66,
      "step": 132
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.6025679891477139,
      "learning_rate": 9.413731927034605e-05,
      "loss": 0.6332,
      "step": 133
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.6396295661454142,
      "learning_rate": 9.283653099174704e-05,
      "loss": 0.6352,
      "step": 134
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.6490127330699687,
      "learning_rate": 9.15369599718744e-05,
      "loss": 0.667,
      "step": 135
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.6428918190195956,
      "learning_rate": 9.023882704146848e-05,
      "loss": 0.6278,
      "step": 136
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.6195852999012177,
      "learning_rate": 8.894235278690104e-05,
      "loss": 0.6919,
      "step": 137
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.5890514234117395,
      "learning_rate": 8.764775751269182e-05,
      "loss": 0.6282,
      "step": 138
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.6383232450338161,
      "learning_rate": 8.635526120407329e-05,
      "loss": 0.6335,
      "step": 139
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.6298327584602661,
      "learning_rate": 8.506508348960924e-05,
      "loss": 0.6757,
      "step": 140
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.5951533121419991,
      "learning_rate": 8.377744360387447e-05,
      "loss": 0.6378,
      "step": 141
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.5990230767413158,
      "learning_rate": 8.249256035020086e-05,
      "loss": 0.6398,
      "step": 142
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.594734539715176,
      "learning_rate": 8.121065206349729e-05,
      "loss": 0.6688,
      "step": 143
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.624787885220957,
      "learning_rate": 7.993193657314875e-05,
      "loss": 0.6287,
      "step": 144
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.6482697342730748,
      "learning_rate": 7.865663116600148e-05,
      "loss": 0.6586,
      "step": 145
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.713715611061142,
      "learning_rate": 7.738495254944042e-05,
      "loss": 0.6697,
      "step": 146
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.6234960883575744,
      "learning_rate": 7.611711681456493e-05,
      "loss": 0.6368,
      "step": 147
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.630287976111448,
      "learning_rate": 7.485333939946926e-05,
      "loss": 0.6508,
      "step": 148
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.6378675582501994,
      "learning_rate": 7.359383505263431e-05,
      "loss": 0.6841,
      "step": 149
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.6156108176431241,
      "learning_rate": 7.233881779643594e-05,
      "loss": 0.6444,
      "step": 150
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.5897421977125701,
      "learning_rate": 7.108850089077735e-05,
      "loss": 0.6719,
      "step": 151
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.5849183219702926,
      "learning_rate": 6.98430967968505e-05,
      "loss": 0.6733,
      "step": 152
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.6260421998777234,
      "learning_rate": 6.86028171410335e-05,
      "loss": 0.6383,
      "step": 153
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.6304596579295512,
      "learning_rate": 6.736787267892991e-05,
      "loss": 0.6717,
      "step": 154
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.6048424796187638,
      "learning_rate": 6.613847325955578e-05,
      "loss": 0.659,
      "step": 155
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.6343949665489499,
      "learning_rate": 6.491482778968104e-05,
      "loss": 0.6651,
      "step": 156
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.6032899750286133,
      "learning_rate": 6.369714419833056e-05,
      "loss": 0.6337,
      "step": 157
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.7108946242576734,
      "learning_rate": 6.248562940145195e-05,
      "loss": 0.6459,
      "step": 158
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.5901296881624672,
      "learning_rate": 6.128048926675494e-05,
      "loss": 0.6764,
      "step": 159
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.5918343934659875,
      "learning_rate": 6.008192857872923e-05,
      "loss": 0.6428,
      "step": 160
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.5970600618333325,
      "learning_rate": 5.889015100384636e-05,
      "loss": 0.6324,
      "step": 161
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.6038442007114545,
      "learning_rate": 5.770535905595138e-05,
      "loss": 0.6496,
      "step": 162
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.6204490128832106,
      "learning_rate": 5.6527754061850554e-05,
      "loss": 0.6485,
      "step": 163
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.6179929201872987,
      "learning_rate": 5.5357536127100904e-05,
      "loss": 0.6545,
      "step": 164
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.619221490890743,
      "learning_rate": 5.419490410200675e-05,
      "loss": 0.612,
      "step": 165
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.5966676205978181,
      "learning_rate": 5.304005554783015e-05,
      "loss": 0.6498,
      "step": 166
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.5822755936769207,
      "learning_rate": 5.1893186703220165e-05,
      "loss": 0.6171,
      "step": 167
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.5842041127752368,
      "learning_rate": 5.0754492450866607e-05,
      "loss": 0.6243,
      "step": 168
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.6337182771676403,
      "learning_rate": 4.9624166284384656e-05,
      "loss": 0.6147,
      "step": 169
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.6017489055813804,
      "learning_rate": 4.850240027543509e-05,
      "loss": 0.653,
      "step": 170
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.5809709526862709,
      "learning_rate": 4.738938504108659e-05,
      "loss": 0.6267,
      "step": 171
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.5826938185721535,
      "learning_rate": 4.628530971142471e-05,
      "loss": 0.6213,
      "step": 172
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.5737019305587774,
      "learning_rate": 4.519036189741386e-05,
      "loss": 0.6502,
      "step": 173
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.5945680765374372,
      "learning_rate": 4.410472765901755e-05,
      "loss": 0.6286,
      "step": 174
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.6094073434165231,
      "learning_rate": 4.302859147358168e-05,
      "loss": 0.5848,
      "step": 175
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.6187888066340587,
      "learning_rate": 4.196213620448723e-05,
      "loss": 0.6439,
      "step": 176
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.6419980315369229,
      "learning_rate": 4.0905543070077036e-05,
      "loss": 0.6471,
      "step": 177
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.6337264596412628,
      "learning_rate": 3.985899161286205e-05,
      "loss": 0.6616,
      "step": 178
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.5832375614778771,
      "learning_rate": 3.882265966901257e-05,
      "loss": 0.6767,
      "step": 179
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.574891135054901,
      "learning_rate": 3.7796723338138995e-05,
      "loss": 0.5807,
      "step": 180
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.5699073164192423,
      "learning_rate": 3.6781356953368284e-05,
      "loss": 0.6371,
      "step": 181
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.616654702040988,
      "learning_rate": 3.5776733051719936e-05,
      "loss": 0.6086,
      "step": 182
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.5867706666852922,
      "learning_rate": 3.47830223447877e-05,
      "loss": 0.6639,
      "step": 183
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.623145463941295,
      "learning_rate": 3.3800393689731146e-05,
      "loss": 0.6345,
      "step": 184
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.5981407629418406,
      "learning_rate": 3.28290140605825e-05,
      "loss": 0.6273,
      "step": 185
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.5674343545696854,
      "learning_rate": 3.186904851987351e-05,
      "loss": 0.6058,
      "step": 186
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.6399842879941413,
      "learning_rate": 3.092066019058689e-05,
      "loss": 0.6231,
      "step": 187
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.6313162630484164,
      "learning_rate": 2.998401022843761e-05,
      "loss": 0.6486,
      "step": 188
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.6028986124900413,
      "learning_rate": 2.9059257794488424e-05,
      "loss": 0.567,
      "step": 189
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.5960517928587284,
      "learning_rate": 2.8146560028104153e-05,
      "loss": 0.6716,
      "step": 190
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.6286103402740058,
      "learning_rate": 2.724607202024969e-05,
      "loss": 0.6188,
      "step": 191
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.644610126637308,
      "learning_rate": 2.6357946787136113e-05,
      "loss": 0.6434,
      "step": 192
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.5729979241776278,
      "learning_rate": 2.548233524421911e-05,
      "loss": 0.6319,
      "step": 193
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.6328611584490075,
      "learning_rate": 2.461938618055478e-05,
      "loss": 0.6554,
      "step": 194
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.5975966512993659,
      "learning_rate": 2.3769246233516242e-05,
      "loss": 0.5977,
      "step": 195
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.59320648444735,
      "learning_rate": 2.2932059863876365e-05,
      "loss": 0.6456,
      "step": 196
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.590627235987933,
      "learning_rate": 2.2107969331260048e-05,
      "loss": 0.6259,
      "step": 197
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.6410336378215516,
      "learning_rate": 2.1297114669970618e-05,
      "loss": 0.5967,
      "step": 198
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.5839140783732536,
      "learning_rate": 2.049963366519446e-05,
      "loss": 0.6245,
      "step": 199
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.6055114057003023,
      "learning_rate": 1.971566182958765e-05,
      "loss": 0.5994,
      "step": 200
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.588555313698678,
      "learning_rate": 1.8945332380248913e-05,
      "loss": 0.604,
      "step": 201
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.6088478693980861,
      "learning_rate": 1.8188776216082603e-05,
      "loss": 0.6212,
      "step": 202
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.5893151236661324,
      "learning_rate": 1.7446121895555555e-05,
      "loss": 0.632,
      "step": 203
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.599854694440474,
      "learning_rate": 1.6717495614851652e-05,
      "loss": 0.6231,
      "step": 204
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.5802528574601737,
      "learning_rate": 1.6003021186427893e-05,
      "loss": 0.6234,
      "step": 205
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.585335132783131,
      "learning_rate": 1.5302820017975394e-05,
      "loss": 0.6269,
      "step": 206
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.5818204916703836,
      "learning_rate": 1.4617011091789135e-05,
      "loss": 0.6104,
      "step": 207
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.568918470562012,
      "learning_rate": 1.3945710944549706e-05,
      "loss": 0.6178,
      "step": 208
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.5925712778064853,
      "learning_rate": 1.3289033647520877e-05,
      "loss": 0.5969,
      "step": 209
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.5906570988072316,
      "learning_rate": 1.2647090787165694e-05,
      "loss": 0.6202,
      "step": 210
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.625879731780627,
      "learning_rate": 1.2019991446185309e-05,
      "loss": 0.6114,
      "step": 211
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.6143685840442832,
      "learning_rate": 1.1407842184982786e-05,
      "loss": 0.6186,
      "step": 212
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.6155175082291917,
      "learning_rate": 1.0810747023555878e-05,
      "loss": 0.6102,
      "step": 213
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.5795310616149347,
      "learning_rate": 1.0228807423821263e-05,
      "loss": 0.5998,
      "step": 214
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.5831880790523601,
      "learning_rate": 9.662122272373575e-06,
      "loss": 0.5945,
      "step": 215
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.6290115114493054,
      "learning_rate": 9.110787863682002e-06,
      "loss": 0.5857,
      "step": 216
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.6603504517272147,
      "learning_rate": 8.574897883727384e-06,
      "loss": 0.6373,
      "step": 217
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.6087100188068558,
      "learning_rate": 8.054543394082504e-06,
      "loss": 0.6134,
      "step": 218
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.6064067085429232,
      "learning_rate": 7.5498128164383955e-06,
      "loss": 0.5998,
      "step": 219
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.5920112342958288,
      "learning_rate": 7.0607919175791796e-06,
      "loss": 0.6134,
      "step": 220
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.5549713422524726,
      "learning_rate": 6.587563794808127e-06,
      "loss": 0.644,
      "step": 221
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.6110503712077385,
      "learning_rate": 6.130208861827202e-06,
      "loss": 0.6276,
      "step": 222
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.6526080947670703,
      "learning_rate": 5.688804835072748e-06,
      "loss": 0.6122,
      "step": 223
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.592228703593387,
      "learning_rate": 5.263426720509468e-06,
      "loss": 0.5666,
      "step": 224
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.6154318985980524,
      "learning_rate": 4.8541468008849285e-06,
      "loss": 0.6022,
      "step": 225
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.6245746165165417,
      "learning_rate": 4.461034623446847e-06,
      "loss": 0.5916,
      "step": 226
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.587908724284237,
      "learning_rate": 4.084156988125231e-06,
      "loss": 0.6164,
      "step": 227
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.5951699842997723,
      "learning_rate": 3.723577936181366e-06,
      "loss": 0.6195,
      "step": 228
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.5667459142096927,
      "learning_rate": 3.3793587393255e-06,
      "loss": 0.5908,
      "step": 229
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.5639108144148681,
      "learning_rate": 3.0515578893052344e-06,
      "loss": 0.5743,
      "step": 230
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.5459205466426152,
      "learning_rate": 2.7402310879662497e-06,
      "loss": 0.6269,
      "step": 231
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.6031704942783882,
      "learning_rate": 2.44543123778711e-06,
      "loss": 0.6269,
      "step": 232
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.5770810110581429,
      "learning_rate": 2.167208432889789e-06,
      "loss": 0.6151,
      "step": 233
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.5952891318172381,
      "learning_rate": 1.9056099505273427e-06,
      "loss": 0.5728,
      "step": 234
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.5904225313614513,
      "learning_rate": 1.6606802430503166e-06,
      "loss": 0.6235,
      "step": 235
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.5782760417216553,
      "learning_rate": 1.43246093035313e-06,
      "loss": 0.5593,
      "step": 236
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.580467530625868,
      "learning_rate": 1.2209907928017795e-06,
      "loss": 0.6423,
      "step": 237
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.5711598715443851,
      "learning_rate": 1.0263057646440199e-06,
      "loss": 0.6291,
      "step": 238
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.5686426031326551,
      "learning_rate": 8.484389279032834e-07,
      "loss": 0.6198,
      "step": 239
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.6046363181474087,
      "learning_rate": 6.874205067571083e-07,
      "loss": 0.6468,
      "step": 240
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.6072995257131998,
      "learning_rate": 5.432778624013257e-07,
      "loss": 0.6486,
      "step": 241
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.6201193729192779,
      "learning_rate": 4.1603548840062345e-07,
      "loss": 0.6272,
      "step": 242
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.6312528212744211,
      "learning_rate": 3.0571500652651907e-07,
      "loss": 0.6177,
      "step": 243
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.5687699288742071,
      "learning_rate": 2.1233516308323264e-07,
      "loss": 0.618,
      "step": 244
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.5523484801821387,
      "learning_rate": 1.359118257221903e-07,
      "loss": 0.5945,
      "step": 245
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.636843838687328,
      "learning_rate": 7.645798074572552e-08,
      "loss": 0.6551,
      "step": 246
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.5817618418266682,
      "learning_rate": 3.3983730900377655e-08,
      "loss": 0.6149,
      "step": 247
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6358174664632625,
      "learning_rate": 8.496293660120724e-09,
      "loss": 0.6777,
      "step": 248
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6195064507565601,
      "learning_rate": 0.0,
      "loss": 0.5658,
      "step": 249
    },
    {
      "epoch": 1.0,
      "step": 249,
      "total_flos": 37734407700480.0,
      "train_loss": 0.7035722335179647,
      "train_runtime": 3820.5554,
      "train_samples_per_second": 4.162,
      "train_steps_per_second": 0.065
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 249,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "total_flos": 37734407700480.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}