{
  "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": 3.981182133898211,
      "learning_rate": 2.5e-05,
      "loss": 1.365,
      "step": 1
    },
    {
      "epoch": 0.01,
      "grad_norm": 4.223447168750389,
      "learning_rate": 5e-05,
      "loss": 1.3932,
      "step": 2
    },
    {
      "epoch": 0.01,
      "grad_norm": 2.141765750699434,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.1306,
      "step": 3
    },
    {
      "epoch": 0.02,
      "grad_norm": 2.2703951636474855,
      "learning_rate": 0.0001,
      "loss": 1.0787,
      "step": 4
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.9111760478873023,
      "learning_rate": 0.000125,
      "loss": 1.0686,
      "step": 5
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.3499712071563628,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.0114,
      "step": 6
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.0911667817060011,
      "learning_rate": 0.000175,
      "loss": 0.9416,
      "step": 7
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.2496043705531406,
      "learning_rate": 0.0002,
      "loss": 0.9286,
      "step": 8
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.7692075337111344,
      "learning_rate": 0.00019999150370633988,
      "loss": 0.9074,
      "step": 9
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.9122071484249495,
      "learning_rate": 0.00019996601626909964,
      "loss": 0.8867,
      "step": 10
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.9493702949853532,
      "learning_rate": 0.00019992354201925428,
      "loss": 0.8814,
      "step": 11
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.8549355244573901,
      "learning_rate": 0.0001998640881742778,
      "loss": 0.8887,
      "step": 12
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.8921668257689561,
      "learning_rate": 0.00019978766483691676,
      "loss": 0.8542,
      "step": 13
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.8244188073583076,
      "learning_rate": 0.0001996942849934735,
      "loss": 0.8412,
      "step": 14
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.7478409595239439,
      "learning_rate": 0.00019958396451159936,
      "loss": 0.7793,
      "step": 15
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.758307762850361,
      "learning_rate": 0.0001994567221375987,
      "loss": 0.819,
      "step": 16
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.770947644951731,
      "learning_rate": 0.00019931257949324288,
      "loss": 0.8447,
      "step": 17
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.8358253752348583,
      "learning_rate": 0.00019915156107209675,
      "loss": 0.772,
      "step": 18
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.7175509358752481,
      "learning_rate": 0.000198973694235356,
      "loss": 0.7914,
      "step": 19
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.7542707242255626,
      "learning_rate": 0.00019877900920719827,
      "loss": 0.7983,
      "step": 20
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.7645202304094161,
      "learning_rate": 0.00019856753906964686,
      "loss": 0.7214,
      "step": 21
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.7430521597063948,
      "learning_rate": 0.0001983393197569497,
      "loss": 0.8091,
      "step": 22
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.7324090515929388,
      "learning_rate": 0.00019809439004947268,
      "loss": 0.7704,
      "step": 23
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.6896844994612445,
      "learning_rate": 0.00019783279156711022,
      "loss": 0.7556,
      "step": 24
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.6749132637574569,
      "learning_rate": 0.0001975545687622129,
      "loss": 0.7571,
      "step": 25
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.7076244352514828,
      "learning_rate": 0.00019725976891203376,
      "loss": 0.8445,
      "step": 26
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.6358516553573809,
      "learning_rate": 0.00019694844211069477,
      "loss": 0.7477,
      "step": 27
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.6633797558960025,
      "learning_rate": 0.00019662064126067452,
      "loss": 0.7359,
      "step": 28
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.7619604289470452,
      "learning_rate": 0.00019627642206381863,
      "loss": 0.7752,
      "step": 29
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.6693105562777081,
      "learning_rate": 0.00019591584301187478,
      "loss": 0.7147,
      "step": 30
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.6441185271339039,
      "learning_rate": 0.00019553896537655318,
      "loss": 0.7425,
      "step": 31
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.6912959653338677,
      "learning_rate": 0.0001951458531991151,
      "loss": 0.7344,
      "step": 32
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.6265627524452637,
      "learning_rate": 0.00019473657327949054,
      "loss": 0.7292,
      "step": 33
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.8319948068621666,
      "learning_rate": 0.00019431119516492726,
      "loss": 0.7196,
      "step": 34
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.6374074802429165,
      "learning_rate": 0.00019386979113817282,
      "loss": 0.7549,
      "step": 35
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.6813527739244364,
      "learning_rate": 0.0001934124362051919,
      "loss": 0.7656,
      "step": 36
    },
    {
      "epoch": 0.15,
      "grad_norm": 1.6806360809140246,
      "learning_rate": 0.00019293920808242083,
      "loss": 0.7582,
      "step": 37
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.66415983259972,
      "learning_rate": 0.0001924501871835616,
      "loss": 0.7754,
      "step": 38
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.736768809075717,
      "learning_rate": 0.00019194545660591752,
      "loss": 0.6906,
      "step": 39
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.013197406350164,
      "learning_rate": 0.00019142510211627264,
      "loss": 0.7464,
      "step": 40
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.8455834245687115,
      "learning_rate": 0.000190889212136318,
      "loss": 0.7476,
      "step": 41
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.8000760159918991,
      "learning_rate": 0.00019033787772762645,
      "loss": 0.7612,
      "step": 42
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.7721776264489126,
      "learning_rate": 0.00018977119257617878,
      "loss": 0.7661,
      "step": 43
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.7411505347014887,
      "learning_rate": 0.00018918925297644416,
      "loss": 0.7582,
      "step": 44
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.6574055283176412,
      "learning_rate": 0.00018859215781501725,
      "loss": 0.693,
      "step": 45
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.6252820250088373,
      "learning_rate": 0.0001879800085538147,
      "loss": 0.6709,
      "step": 46
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.6283973563255442,
      "learning_rate": 0.0001873529092128343,
      "loss": 0.7499,
      "step": 47
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.691088723538482,
      "learning_rate": 0.00018671096635247914,
      "loss": 0.7595,
      "step": 48
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.6657667325476994,
      "learning_rate": 0.00018605428905545032,
      "loss": 0.7608,
      "step": 49
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.6483390927552524,
      "learning_rate": 0.0001853829889082109,
      "loss": 0.7267,
      "step": 50
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.5768376505606613,
      "learning_rate": 0.00018469717998202462,
      "loss": 0.7361,
      "step": 51
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.5962362264080698,
      "learning_rate": 0.00018399697881357212,
      "loss": 0.7373,
      "step": 52
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.6392264631697471,
      "learning_rate": 0.00018328250438514836,
      "loss": 0.7005,
      "step": 53
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.6242411219574141,
      "learning_rate": 0.00018255387810444448,
      "loss": 0.7522,
      "step": 54
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.5870527031664319,
      "learning_rate": 0.0001818112237839174,
      "loss": 0.7118,
      "step": 55
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.6066047817906325,
      "learning_rate": 0.00018105466761975109,
      "loss": 0.7058,
      "step": 56
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.6038141699713118,
      "learning_rate": 0.00018028433817041236,
      "loss": 0.7219,
      "step": 57
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.5847345831142737,
      "learning_rate": 0.00017950036633480556,
      "loss": 0.7147,
      "step": 58
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.6312111783082757,
      "learning_rate": 0.00017870288533002938,
      "loss": 0.6963,
      "step": 59
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.5966959070900965,
      "learning_rate": 0.00017789203066873998,
      "loss": 0.7307,
      "step": 60
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.5798593347176144,
      "learning_rate": 0.00017706794013612364,
      "loss": 0.7303,
      "step": 61
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.6100699019983455,
      "learning_rate": 0.00017623075376648376,
      "loss": 0.7122,
      "step": 62
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.6150446745513377,
      "learning_rate": 0.00017538061381944524,
      "loss": 0.7282,
      "step": 63
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.5839828703861961,
      "learning_rate": 0.0001745176647557809,
      "loss": 0.6841,
      "step": 64
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.5832617502478282,
      "learning_rate": 0.00017364205321286394,
      "loss": 0.7088,
      "step": 65
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.6117567542213321,
      "learning_rate": 0.00017275392797975032,
      "loss": 0.781,
      "step": 66
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.6332126002995662,
      "learning_rate": 0.00017185343997189588,
      "loss": 0.7346,
      "step": 67
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.5617477585453899,
      "learning_rate": 0.00017094074220551158,
      "loss": 0.7114,
      "step": 68
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.5820274703305921,
      "learning_rate": 0.0001700159897715624,
      "loss": 0.742,
      "step": 69
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.580367538119296,
      "learning_rate": 0.00016907933980941312,
      "loss": 0.6663,
      "step": 70
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.5652333172835816,
      "learning_rate": 0.0001681309514801265,
      "loss": 0.678,
      "step": 71
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.5604822769679129,
      "learning_rate": 0.00016717098593941752,
      "loss": 0.7027,
      "step": 72
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.5443005590527936,
      "learning_rate": 0.00016619960631026888,
      "loss": 0.7235,
      "step": 73
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.5648289749630883,
      "learning_rate": 0.0001652169776552123,
      "loss": 0.6966,
      "step": 74
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.5511612101503145,
      "learning_rate": 0.00016422326694828007,
      "loss": 0.6716,
      "step": 75
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.5652818087038983,
      "learning_rate": 0.00016321864304663173,
      "loss": 0.6964,
      "step": 76
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.5873059772542137,
      "learning_rate": 0.000162203276661861,
      "loss": 0.7268,
      "step": 77
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.584440156512384,
      "learning_rate": 0.00016117734033098744,
      "loss": 0.7183,
      "step": 78
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.5476205992100533,
      "learning_rate": 0.00016014100838713797,
      "loss": 0.7063,
      "step": 79
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.6013346658704335,
      "learning_rate": 0.000159094456929923,
      "loss": 0.6893,
      "step": 80
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.5525643324311199,
      "learning_rate": 0.0001580378637955128,
      "loss": 0.6691,
      "step": 81
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.5889885232500072,
      "learning_rate": 0.00015697140852641834,
      "loss": 0.6944,
      "step": 82
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.6105160593879608,
      "learning_rate": 0.00015589527234098247,
      "loss": 0.7328,
      "step": 83
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.580479859109292,
      "learning_rate": 0.00015480963810258613,
      "loss": 0.6913,
      "step": 84
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.5618974771825274,
      "learning_rate": 0.00015371469028857532,
      "loss": 0.724,
      "step": 85
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.560525959205613,
      "learning_rate": 0.00015261061495891345,
      "loss": 0.7048,
      "step": 86
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.6212802766603819,
      "learning_rate": 0.0001514975997245649,
      "loss": 0.6858,
      "step": 87
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.570889967163218,
      "learning_rate": 0.00015037583371561535,
      "loss": 0.696,
      "step": 88
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.5568747400044114,
      "learning_rate": 0.0001492455075491334,
      "loss": 0.693,
      "step": 89
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.5563715707732911,
      "learning_rate": 0.00014810681329677987,
      "loss": 0.6806,
      "step": 90
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.568992451570255,
      "learning_rate": 0.00014695994445216985,
      "loss": 0.7074,
      "step": 91
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.5767587218056255,
      "learning_rate": 0.00014580509589799329,
      "loss": 0.7094,
      "step": 92
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.5425009774160251,
      "learning_rate": 0.00014464246387289913,
      "loss": 0.6781,
      "step": 93
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.5513859545077572,
      "learning_rate": 0.00014347224593814944,
      "loss": 0.7234,
      "step": 94
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.5339051729787517,
      "learning_rate": 0.00014229464094404865,
      "loss": 0.6931,
      "step": 95
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.5549045365561713,
      "learning_rate": 0.00014110984899615367,
      "loss": 0.6962,
      "step": 96
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.5395797162975184,
      "learning_rate": 0.0001399180714212708,
      "loss": 0.6832,
      "step": 97
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.5393020282422275,
      "learning_rate": 0.00013871951073324507,
      "loss": 0.7212,
      "step": 98
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.5406971945004404,
      "learning_rate": 0.0001375143705985481,
      "loss": 0.6878,
      "step": 99
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.5741985470318297,
      "learning_rate": 0.00013630285580166945,
      "loss": 0.6725,
      "step": 100
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.6087387724460733,
      "learning_rate": 0.000135085172210319,
      "loss": 0.6876,
      "step": 101
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.5202304228310284,
      "learning_rate": 0.00013386152674044422,
      "loss": 0.6652,
      "step": 102
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.5660298147339341,
      "learning_rate": 0.00013263212732107012,
      "loss": 0.693,
      "step": 103
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.546774134041922,
      "learning_rate": 0.00013139718285896655,
      "loss": 0.6464,
      "step": 104
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.5338303600632187,
      "learning_rate": 0.00013015690320314954,
      "loss": 0.7009,
      "step": 105
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.5396484507008162,
      "learning_rate": 0.00012891149910922267,
      "loss": 0.696,
      "step": 106
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.5185373681304583,
      "learning_rate": 0.00012766118220356408,
      "loss": 0.687,
      "step": 107
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.5102091277266492,
      "learning_rate": 0.0001264061649473657,
      "loss": 0.6648,
      "step": 108
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.5727613881928513,
      "learning_rate": 0.00012514666060053076,
      "loss": 0.6777,
      "step": 109
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.5165707891231989,
      "learning_rate": 0.00012388288318543512,
      "loss": 0.6454,
      "step": 110
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.5463906044314786,
      "learning_rate": 0.00012261504745055964,
      "loss": 0.6463,
      "step": 111
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.5150747138759594,
      "learning_rate": 0.00012134336883399855,
      "loss": 0.6436,
      "step": 112
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.5268166681458911,
      "learning_rate": 0.00012006806342685126,
      "loss": 0.7139,
      "step": 113
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.5797636370362743,
      "learning_rate": 0.00011878934793650273,
      "loss": 0.5959,
      "step": 114
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.5168654595529651,
      "learning_rate": 0.00011750743964979918,
      "loss": 0.6465,
      "step": 115
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.5586505025432532,
      "learning_rate": 0.00011622255639612554,
      "loss": 0.6954,
      "step": 116
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.5733109224839272,
      "learning_rate": 0.00011493491651039077,
      "loss": 0.6951,
      "step": 117
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.5798484006098489,
      "learning_rate": 0.00011364473879592674,
      "loss": 0.6713,
      "step": 118
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.5558404867313713,
      "learning_rate": 0.0001123522424873082,
      "loss": 0.6627,
      "step": 119
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.564370632395679,
      "learning_rate": 0.000111057647213099,
      "loss": 0.6582,
      "step": 120
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.5247546019655245,
      "learning_rate": 0.00010976117295853154,
      "loss": 0.6274,
      "step": 121
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.5043366815729828,
      "learning_rate": 0.00010846304002812564,
      "loss": 0.663,
      "step": 122
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.5377570953262834,
      "learning_rate": 0.00010716346900825299,
      "loss": 0.6879,
      "step": 123
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.5316530391582156,
      "learning_rate": 0.00010586268072965396,
      "loss": 0.6812,
      "step": 124
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.5309847868667069,
      "learning_rate": 0.00010456089622991263,
      "loss": 0.6378,
      "step": 125
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.49952898047881455,
      "learning_rate": 0.00010325833671589687,
      "loss": 0.7031,
      "step": 126
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.513186855879022,
      "learning_rate": 0.00010195522352616943,
      "loss": 0.6346,
      "step": 127
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.5624215177016363,
      "learning_rate": 0.00010065177809337702,
      "loss": 0.7014,
      "step": 128
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.5339748834208153,
      "learning_rate": 9.934822190662299e-05,
      "loss": 0.7169,
      "step": 129
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.5298864830864823,
      "learning_rate": 9.80447764738306e-05,
      "loss": 0.6419,
      "step": 130
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.49790603329053645,
      "learning_rate": 9.674166328410318e-05,
      "loss": 0.6277,
      "step": 131
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.5222038396293899,
      "learning_rate": 9.543910377008742e-05,
      "loss": 0.6617,
      "step": 132
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.5076737199539593,
      "learning_rate": 9.413731927034605e-05,
      "loss": 0.6315,
      "step": 133
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.540367448084855,
      "learning_rate": 9.283653099174704e-05,
      "loss": 0.637,
      "step": 134
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.5259754962695676,
      "learning_rate": 9.15369599718744e-05,
      "loss": 0.6564,
      "step": 135
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.5297038847994276,
      "learning_rate": 9.023882704146848e-05,
      "loss": 0.6174,
      "step": 136
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.5175810600475641,
      "learning_rate": 8.894235278690104e-05,
      "loss": 0.6885,
      "step": 137
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.49466775844805594,
      "learning_rate": 8.764775751269182e-05,
      "loss": 0.6264,
      "step": 138
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.5468376014397491,
      "learning_rate": 8.635526120407329e-05,
      "loss": 0.6293,
      "step": 139
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.5266499924056278,
      "learning_rate": 8.506508348960924e-05,
      "loss": 0.6672,
      "step": 140
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.5125354022430374,
      "learning_rate": 8.377744360387447e-05,
      "loss": 0.6289,
      "step": 141
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.508760796232234,
      "learning_rate": 8.249256035020086e-05,
      "loss": 0.6311,
      "step": 142
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.5021864887346997,
      "learning_rate": 8.121065206349729e-05,
      "loss": 0.6594,
      "step": 143
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.5355896437675315,
      "learning_rate": 7.993193657314875e-05,
      "loss": 0.6224,
      "step": 144
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.5488326374985829,
      "learning_rate": 7.865663116600148e-05,
      "loss": 0.6465,
      "step": 145
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.6071274038365753,
      "learning_rate": 7.738495254944042e-05,
      "loss": 0.6576,
      "step": 146
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.5212237290379841,
      "learning_rate": 7.611711681456493e-05,
      "loss": 0.6286,
      "step": 147
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.5361821341032351,
      "learning_rate": 7.485333939946926e-05,
      "loss": 0.6436,
      "step": 148
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.5328445664549779,
      "learning_rate": 7.359383505263431e-05,
      "loss": 0.6805,
      "step": 149
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.5169478911375548,
      "learning_rate": 7.233881779643594e-05,
      "loss": 0.6351,
      "step": 150
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.4942190213678014,
      "learning_rate": 7.108850089077735e-05,
      "loss": 0.6645,
      "step": 151
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.4777490402143269,
      "learning_rate": 6.98430967968505e-05,
      "loss": 0.6646,
      "step": 152
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.5203792217543509,
      "learning_rate": 6.86028171410335e-05,
      "loss": 0.6264,
      "step": 153
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.5295673373178881,
      "learning_rate": 6.736787267892991e-05,
      "loss": 0.6574,
      "step": 154
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.5054007800089361,
      "learning_rate": 6.613847325955578e-05,
      "loss": 0.6463,
      "step": 155
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.5328764157075438,
      "learning_rate": 6.491482778968104e-05,
      "loss": 0.6542,
      "step": 156
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.518388232442327,
      "learning_rate": 6.369714419833056e-05,
      "loss": 0.6266,
      "step": 157
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.6119309470927382,
      "learning_rate": 6.248562940145195e-05,
      "loss": 0.6336,
      "step": 158
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.4963434899391007,
      "learning_rate": 6.128048926675494e-05,
      "loss": 0.6718,
      "step": 159
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.5095621401572632,
      "learning_rate": 6.008192857872923e-05,
      "loss": 0.637,
      "step": 160
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.5093440110600602,
      "learning_rate": 5.889015100384636e-05,
      "loss": 0.6307,
      "step": 161
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.5082532966773227,
      "learning_rate": 5.770535905595138e-05,
      "loss": 0.6382,
      "step": 162
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.5305244284181049,
      "learning_rate": 5.6527754061850554e-05,
      "loss": 0.6424,
      "step": 163
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.5234971513196092,
      "learning_rate": 5.5357536127100904e-05,
      "loss": 0.6485,
      "step": 164
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.5035050904882836,
      "learning_rate": 5.419490410200675e-05,
      "loss": 0.6037,
      "step": 165
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.4979993303718048,
      "learning_rate": 5.304005554783015e-05,
      "loss": 0.6394,
      "step": 166
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.4822032608918998,
      "learning_rate": 5.1893186703220165e-05,
      "loss": 0.6107,
      "step": 167
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.47831076024478025,
      "learning_rate": 5.0754492450866607e-05,
      "loss": 0.6171,
      "step": 168
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.5217479864900989,
      "learning_rate": 4.9624166284384656e-05,
      "loss": 0.6039,
      "step": 169
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.4966800853562241,
      "learning_rate": 4.850240027543509e-05,
      "loss": 0.6399,
      "step": 170
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.48803795748690887,
      "learning_rate": 4.738938504108659e-05,
      "loss": 0.6182,
      "step": 171
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.5080270857045189,
      "learning_rate": 4.628530971142471e-05,
      "loss": 0.6141,
      "step": 172
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.47913685117930593,
      "learning_rate": 4.519036189741386e-05,
      "loss": 0.6386,
      "step": 173
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.5026651678612354,
      "learning_rate": 4.410472765901755e-05,
      "loss": 0.6185,
      "step": 174
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.5224312932610757,
      "learning_rate": 4.302859147358168e-05,
      "loss": 0.5824,
      "step": 175
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.5178862834267116,
      "learning_rate": 4.196213620448723e-05,
      "loss": 0.6329,
      "step": 176
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.5323664753651522,
      "learning_rate": 4.0905543070077036e-05,
      "loss": 0.6317,
      "step": 177
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.5216091278689122,
      "learning_rate": 3.985899161286205e-05,
      "loss": 0.6487,
      "step": 178
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.4968974338551305,
      "learning_rate": 3.882265966901257e-05,
      "loss": 0.6692,
      "step": 179
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.4904223105734582,
      "learning_rate": 3.7796723338138995e-05,
      "loss": 0.5781,
      "step": 180
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.47447489519607455,
      "learning_rate": 3.6781356953368284e-05,
      "loss": 0.6254,
      "step": 181
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.5197591426247571,
      "learning_rate": 3.5776733051719936e-05,
      "loss": 0.6023,
      "step": 182
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.49832288681418657,
      "learning_rate": 3.47830223447877e-05,
      "loss": 0.6551,
      "step": 183
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.5129531748899837,
      "learning_rate": 3.3800393689731146e-05,
      "loss": 0.6196,
      "step": 184
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.5036518056972021,
      "learning_rate": 3.28290140605825e-05,
      "loss": 0.6175,
      "step": 185
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.480187816135646,
      "learning_rate": 3.186904851987351e-05,
      "loss": 0.5996,
      "step": 186
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.5242700195547425,
      "learning_rate": 3.092066019058689e-05,
      "loss": 0.61,
      "step": 187
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.5152846503044708,
      "learning_rate": 2.998401022843761e-05,
      "loss": 0.6404,
      "step": 188
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.513298219609548,
      "learning_rate": 2.9059257794488424e-05,
      "loss": 0.557,
      "step": 189
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.5021252812027022,
      "learning_rate": 2.8146560028104153e-05,
      "loss": 0.6634,
      "step": 190
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.519800671516665,
      "learning_rate": 2.724607202024969e-05,
      "loss": 0.6121,
      "step": 191
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.5385204988477328,
      "learning_rate": 2.6357946787136113e-05,
      "loss": 0.6334,
      "step": 192
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.4878184839311098,
      "learning_rate": 2.548233524421911e-05,
      "loss": 0.6267,
      "step": 193
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.5220934509633983,
      "learning_rate": 2.461938618055478e-05,
      "loss": 0.6391,
      "step": 194
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.49114273229478017,
      "learning_rate": 2.3769246233516242e-05,
      "loss": 0.5895,
      "step": 195
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.4886291762205353,
      "learning_rate": 2.2932059863876365e-05,
      "loss": 0.6325,
      "step": 196
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.4939232885896318,
      "learning_rate": 2.2107969331260048e-05,
      "loss": 0.6165,
      "step": 197
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.5320372697561206,
      "learning_rate": 2.1297114669970618e-05,
      "loss": 0.585,
      "step": 198
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.4897381232694001,
      "learning_rate": 2.049963366519446e-05,
      "loss": 0.6132,
      "step": 199
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.5063086712780054,
      "learning_rate": 1.971566182958765e-05,
      "loss": 0.5857,
      "step": 200
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.49709180074211373,
      "learning_rate": 1.8945332380248913e-05,
      "loss": 0.5934,
      "step": 201
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.5013514907900145,
      "learning_rate": 1.8188776216082603e-05,
      "loss": 0.6079,
      "step": 202
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.4846234378658167,
      "learning_rate": 1.7446121895555555e-05,
      "loss": 0.6238,
      "step": 203
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.5159176854303504,
      "learning_rate": 1.6717495614851652e-05,
      "loss": 0.618,
      "step": 204
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.48388369881041865,
      "learning_rate": 1.6003021186427893e-05,
      "loss": 0.6115,
      "step": 205
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.4972352579200309,
      "learning_rate": 1.5302820017975394e-05,
      "loss": 0.6129,
      "step": 206
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.48184028854019717,
      "learning_rate": 1.4617011091789135e-05,
      "loss": 0.6016,
      "step": 207
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.4693368878966723,
      "learning_rate": 1.3945710944549706e-05,
      "loss": 0.6055,
      "step": 208
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.49328037858750934,
      "learning_rate": 1.3289033647520877e-05,
      "loss": 0.5841,
      "step": 209
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.4887185175626592,
      "learning_rate": 1.2647090787165694e-05,
      "loss": 0.6118,
      "step": 210
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.5275529498494832,
      "learning_rate": 1.2019991446185309e-05,
      "loss": 0.6056,
      "step": 211
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.5139820604569797,
      "learning_rate": 1.1407842184982786e-05,
      "loss": 0.6033,
      "step": 212
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.5018443059475605,
      "learning_rate": 1.0810747023555878e-05,
      "loss": 0.5949,
      "step": 213
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.48214911033187263,
      "learning_rate": 1.0228807423821263e-05,
      "loss": 0.5889,
      "step": 214
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.48428681987465205,
      "learning_rate": 9.662122272373575e-06,
      "loss": 0.5819,
      "step": 215
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.528477861467508,
      "learning_rate": 9.110787863682002e-06,
      "loss": 0.5819,
      "step": 216
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.542081152492008,
      "learning_rate": 8.574897883727384e-06,
      "loss": 0.6237,
      "step": 217
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.5087137996746921,
      "learning_rate": 8.054543394082504e-06,
      "loss": 0.6057,
      "step": 218
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.504565281502016,
      "learning_rate": 7.5498128164383955e-06,
      "loss": 0.5934,
      "step": 219
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.4973612377357542,
      "learning_rate": 7.0607919175791796e-06,
      "loss": 0.6008,
      "step": 220
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.4569327819305099,
      "learning_rate": 6.587563794808127e-06,
      "loss": 0.6257,
      "step": 221
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.5013818574659203,
      "learning_rate": 6.130208861827202e-06,
      "loss": 0.6111,
      "step": 222
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.5396029754257269,
      "learning_rate": 5.688804835072748e-06,
      "loss": 0.6049,
      "step": 223
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.4941288037270458,
      "learning_rate": 5.263426720509468e-06,
      "loss": 0.5498,
      "step": 224
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.5221213240498462,
      "learning_rate": 4.8541468008849285e-06,
      "loss": 0.5939,
      "step": 225
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.5148521707210466,
      "learning_rate": 4.461034623446847e-06,
      "loss": 0.5773,
      "step": 226
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.4933400691524689,
      "learning_rate": 4.084156988125231e-06,
      "loss": 0.6078,
      "step": 227
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.4882090112322451,
      "learning_rate": 3.723577936181366e-06,
      "loss": 0.6044,
      "step": 228
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.4899230526737377,
      "learning_rate": 3.3793587393255e-06,
      "loss": 0.5841,
      "step": 229
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.48341263558623804,
      "learning_rate": 3.0515578893052344e-06,
      "loss": 0.5636,
      "step": 230
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.45580749261782566,
      "learning_rate": 2.7402310879662497e-06,
      "loss": 0.6148,
      "step": 231
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.5090083434022111,
      "learning_rate": 2.44543123778711e-06,
      "loss": 0.6169,
      "step": 232
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.4909526042662716,
      "learning_rate": 2.167208432889789e-06,
      "loss": 0.61,
      "step": 233
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.4915614072461919,
      "learning_rate": 1.9056099505273427e-06,
      "loss": 0.5589,
      "step": 234
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.4967849394301577,
      "learning_rate": 1.6606802430503166e-06,
      "loss": 0.6148,
      "step": 235
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.49008026008002525,
      "learning_rate": 1.43246093035313e-06,
      "loss": 0.5432,
      "step": 236
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.47910645199801954,
      "learning_rate": 1.2209907928017795e-06,
      "loss": 0.6306,
      "step": 237
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.47354206064914267,
      "learning_rate": 1.0263057646440199e-06,
      "loss": 0.6149,
      "step": 238
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.48080154743346765,
      "learning_rate": 8.484389279032834e-07,
      "loss": 0.6118,
      "step": 239
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.5000613082596329,
      "learning_rate": 6.874205067571083e-07,
      "loss": 0.6344,
      "step": 240
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.5161518232153531,
      "learning_rate": 5.432778624013257e-07,
      "loss": 0.6341,
      "step": 241
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.5360018159046693,
      "learning_rate": 4.1603548840062345e-07,
      "loss": 0.6191,
      "step": 242
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.5403903928320288,
      "learning_rate": 3.0571500652651907e-07,
      "loss": 0.6069,
      "step": 243
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.480958206210995,
      "learning_rate": 2.1233516308323264e-07,
      "loss": 0.6041,
      "step": 244
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.46018947114009656,
      "learning_rate": 1.359118257221903e-07,
      "loss": 0.5822,
      "step": 245
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.5297015912922861,
      "learning_rate": 7.645798074572552e-08,
      "loss": 0.6451,
      "step": 246
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.4867081187971182,
      "learning_rate": 3.3983730900377655e-08,
      "loss": 0.5977,
      "step": 247
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5439247812896818,
      "learning_rate": 8.496293660120724e-09,
      "loss": 0.659,
      "step": 248
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5183819113313861,
      "learning_rate": 0.0,
      "loss": 0.5523,
      "step": 249
    },
    {
      "epoch": 1.0,
      "step": 249,
      "total_flos": 37334311403520.0,
      "train_loss": 0.6850855740677401,
      "train_runtime": 4182.855,
      "train_samples_per_second": 3.802,
      "train_steps_per_second": 0.06
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 249,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "total_flos": 37334311403520.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}