{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 178,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011235955056179775,
      "grad_norm": 10.042351722717285,
      "learning_rate": 4e-05,
      "loss": 9.033,
      "step": 1
    },
    {
      "epoch": 0.02247191011235955,
      "grad_norm": 10.187106132507324,
      "learning_rate": 8e-05,
      "loss": 9.1846,
      "step": 2
    },
    {
      "epoch": 0.033707865168539325,
      "grad_norm": 8.38694953918457,
      "learning_rate": 0.00012,
      "loss": 7.9832,
      "step": 3
    },
    {
      "epoch": 0.0449438202247191,
      "grad_norm": 5.938446521759033,
      "learning_rate": 0.00016,
      "loss": 5.6493,
      "step": 4
    },
    {
      "epoch": 0.056179775280898875,
      "grad_norm": 4.586862087249756,
      "learning_rate": 0.0002,
      "loss": 4.0131,
      "step": 5
    },
    {
      "epoch": 0.06741573033707865,
      "grad_norm": 4.84490442276001,
      "learning_rate": 0.00019954545454545455,
      "loss": 2.9931,
      "step": 6
    },
    {
      "epoch": 0.07865168539325842,
      "grad_norm": 4.460867881774902,
      "learning_rate": 0.0001990909090909091,
      "loss": 2.261,
      "step": 7
    },
    {
      "epoch": 0.0898876404494382,
      "grad_norm": 3.067777395248413,
      "learning_rate": 0.00019863636363636364,
      "loss": 1.8861,
      "step": 8
    },
    {
      "epoch": 0.10112359550561797,
      "grad_norm": 1.5425913333892822,
      "learning_rate": 0.00019818181818181821,
      "loss": 1.4675,
      "step": 9
    },
    {
      "epoch": 0.11235955056179775,
      "grad_norm": 1.346417784690857,
      "learning_rate": 0.00019772727272727273,
      "loss": 1.3642,
      "step": 10
    },
    {
      "epoch": 0.12359550561797752,
      "grad_norm": 1.1825133562088013,
      "learning_rate": 0.00019727272727272728,
      "loss": 1.0109,
      "step": 11
    },
    {
      "epoch": 0.1348314606741573,
      "grad_norm": 0.9976914525032043,
      "learning_rate": 0.00019681818181818185,
      "loss": 0.9873,
      "step": 12
    },
    {
      "epoch": 0.14606741573033707,
      "grad_norm": 0.6481193900108337,
      "learning_rate": 0.00019636363636363636,
      "loss": 0.6746,
      "step": 13
    },
    {
      "epoch": 0.15730337078651685,
      "grad_norm": 0.5585954189300537,
      "learning_rate": 0.0001959090909090909,
      "loss": 0.5289,
      "step": 14
    },
    {
      "epoch": 0.16853932584269662,
      "grad_norm": 0.9624674916267395,
      "learning_rate": 0.00019545454545454548,
      "loss": 0.5552,
      "step": 15
    },
    {
      "epoch": 0.1797752808988764,
      "grad_norm": 0.7732966542243958,
      "learning_rate": 0.000195,
      "loss": 0.5047,
      "step": 16
    },
    {
      "epoch": 0.19101123595505617,
      "grad_norm": 0.7540618777275085,
      "learning_rate": 0.00019454545454545457,
      "loss": 0.5803,
      "step": 17
    },
    {
      "epoch": 0.20224719101123595,
      "grad_norm": 0.9345465302467346,
      "learning_rate": 0.0001940909090909091,
      "loss": 0.611,
      "step": 18
    },
    {
      "epoch": 0.21348314606741572,
      "grad_norm": 0.5613678693771362,
      "learning_rate": 0.00019363636363636363,
      "loss": 0.4007,
      "step": 19
    },
    {
      "epoch": 0.2247191011235955,
      "grad_norm": 0.8053308725357056,
      "learning_rate": 0.0001931818181818182,
      "loss": 0.5202,
      "step": 20
    },
    {
      "epoch": 0.23595505617977527,
      "grad_norm": 0.6621015667915344,
      "learning_rate": 0.00019272727272727274,
      "loss": 0.4851,
      "step": 21
    },
    {
      "epoch": 0.24719101123595505,
      "grad_norm": 0.797894299030304,
      "learning_rate": 0.00019227272727272726,
      "loss": 0.5401,
      "step": 22
    },
    {
      "epoch": 0.25842696629213485,
      "grad_norm": 0.5635455250740051,
      "learning_rate": 0.00019181818181818183,
      "loss": 0.4295,
      "step": 23
    },
    {
      "epoch": 0.2696629213483146,
      "grad_norm": 0.5012619495391846,
      "learning_rate": 0.00019136363636363638,
      "loss": 0.3133,
      "step": 24
    },
    {
      "epoch": 0.2808988764044944,
      "grad_norm": 0.5143508911132812,
      "learning_rate": 0.00019090909090909092,
      "loss": 0.3207,
      "step": 25
    },
    {
      "epoch": 0.29213483146067415,
      "grad_norm": NaN,
      "learning_rate": 0.00019090909090909092,
      "loss": 0.622,
      "step": 26
    },
    {
      "epoch": 0.30337078651685395,
      "grad_norm": NaN,
      "learning_rate": 0.00019090909090909092,
      "loss": 0.5544,
      "step": 27
    },
    {
      "epoch": 0.3146067415730337,
      "grad_norm": NaN,
      "learning_rate": 0.00019090909090909092,
      "loss": 0.4251,
      "step": 28
    },
    {
      "epoch": 0.3258426966292135,
      "grad_norm": NaN,
      "learning_rate": 0.00019090909090909092,
      "loss": 0.626,
      "step": 29
    },
    {
      "epoch": 0.33707865168539325,
      "grad_norm": 551.2264404296875,
      "learning_rate": 0.00019045454545454547,
      "loss": 0.5757,
      "step": 30
    },
    {
      "epoch": 0.34831460674157305,
      "grad_norm": 0.5639562010765076,
      "learning_rate": 0.00019,
      "loss": 0.3197,
      "step": 31
    },
    {
      "epoch": 0.3595505617977528,
      "grad_norm": 0.5104588270187378,
      "learning_rate": 0.00018954545454545455,
      "loss": 0.2792,
      "step": 32
    },
    {
      "epoch": 0.3707865168539326,
      "grad_norm": 0.6046687960624695,
      "learning_rate": 0.0001890909090909091,
      "loss": 0.4017,
      "step": 33
    },
    {
      "epoch": 0.38202247191011235,
      "grad_norm": 0.5290363430976868,
      "learning_rate": 0.00018863636363636364,
      "loss": 0.2522,
      "step": 34
    },
    {
      "epoch": 0.39325842696629215,
      "grad_norm": 0.4888989329338074,
      "learning_rate": 0.0001881818181818182,
      "loss": 0.2513,
      "step": 35
    },
    {
      "epoch": 0.4044943820224719,
      "grad_norm": 0.4538341164588928,
      "learning_rate": 0.00018772727272727273,
      "loss": 0.2394,
      "step": 36
    },
    {
      "epoch": 0.4157303370786517,
      "grad_norm": 0.5249782800674438,
      "learning_rate": 0.00018727272727272728,
      "loss": 0.3383,
      "step": 37
    },
    {
      "epoch": 0.42696629213483145,
      "grad_norm": 0.544735312461853,
      "learning_rate": 0.00018681818181818182,
      "loss": 0.3345,
      "step": 38
    },
    {
      "epoch": 0.43820224719101125,
      "grad_norm": 0.3868374228477478,
      "learning_rate": 0.00018636363636363636,
      "loss": 0.2425,
      "step": 39
    },
    {
      "epoch": 0.449438202247191,
      "grad_norm": 0.41138726472854614,
      "learning_rate": 0.0001859090909090909,
      "loss": 0.2625,
      "step": 40
    },
    {
      "epoch": 0.4606741573033708,
      "grad_norm": 0.684403657913208,
      "learning_rate": 0.00018545454545454545,
      "loss": 0.3363,
      "step": 41
    },
    {
      "epoch": 0.47191011235955055,
      "grad_norm": 0.4800611138343811,
      "learning_rate": 0.00018500000000000002,
      "loss": 0.2339,
      "step": 42
    },
    {
      "epoch": 0.48314606741573035,
      "grad_norm": 0.47672778367996216,
      "learning_rate": 0.00018454545454545454,
      "loss": 0.2908,
      "step": 43
    },
    {
      "epoch": 0.4943820224719101,
      "grad_norm": 0.44971343874931335,
      "learning_rate": 0.00018409090909090909,
      "loss": 0.2553,
      "step": 44
    },
    {
      "epoch": 0.5056179775280899,
      "grad_norm": 0.45129504799842834,
      "learning_rate": 0.00018363636363636366,
      "loss": 0.325,
      "step": 45
    },
    {
      "epoch": 0.5168539325842697,
      "grad_norm": 0.48597297072410583,
      "learning_rate": 0.00018318181818181817,
      "loss": 0.2843,
      "step": 46
    },
    {
      "epoch": 0.5280898876404494,
      "grad_norm": 0.3514116704463959,
      "learning_rate": 0.00018272727272727275,
      "loss": 0.2128,
      "step": 47
    },
    {
      "epoch": 0.5393258426966292,
      "grad_norm": 0.46826595067977905,
      "learning_rate": 0.0001822727272727273,
      "loss": 0.2601,
      "step": 48
    },
    {
      "epoch": 0.550561797752809,
      "grad_norm": 0.3118669390678406,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.2192,
      "step": 49
    },
    {
      "epoch": 0.5617977528089888,
      "grad_norm": 0.37151020765304565,
      "learning_rate": 0.00018136363636363638,
      "loss": 0.2255,
      "step": 50
    },
    {
      "epoch": 0.5730337078651685,
      "grad_norm": 0.4220457971096039,
      "learning_rate": 0.00018090909090909092,
      "loss": 0.2463,
      "step": 51
    },
    {
      "epoch": 0.5842696629213483,
      "grad_norm": 0.298927366733551,
      "learning_rate": 0.00018045454545454547,
      "loss": 0.1939,
      "step": 52
    },
    {
      "epoch": 0.5955056179775281,
      "grad_norm": 0.3494245707988739,
      "learning_rate": 0.00018,
      "loss": 0.2276,
      "step": 53
    },
    {
      "epoch": 0.6067415730337079,
      "grad_norm": 0.7135240435600281,
      "learning_rate": 0.00017954545454545456,
      "loss": 0.316,
      "step": 54
    },
    {
      "epoch": 0.6179775280898876,
      "grad_norm": 0.47558313608169556,
      "learning_rate": 0.0001790909090909091,
      "loss": 0.1915,
      "step": 55
    },
    {
      "epoch": 0.6292134831460674,
      "grad_norm": 0.47424033284187317,
      "learning_rate": 0.00017863636363636364,
      "loss": 0.268,
      "step": 56
    },
    {
      "epoch": 0.6404494382022472,
      "grad_norm": 0.3898255228996277,
      "learning_rate": 0.0001781818181818182,
      "loss": 0.2346,
      "step": 57
    },
    {
      "epoch": 0.651685393258427,
      "grad_norm": 0.3044908940792084,
      "learning_rate": 0.00017772727272727273,
      "loss": 0.2244,
      "step": 58
    },
    {
      "epoch": 0.6629213483146067,
      "grad_norm": 0.4012211561203003,
      "learning_rate": 0.00017727272727272728,
      "loss": 0.2548,
      "step": 59
    },
    {
      "epoch": 0.6741573033707865,
      "grad_norm": 0.36978745460510254,
      "learning_rate": 0.00017681818181818182,
      "loss": 0.1945,
      "step": 60
    },
    {
      "epoch": 0.6853932584269663,
      "grad_norm": 0.3404884338378906,
      "learning_rate": 0.00017636363636363637,
      "loss": 0.2486,
      "step": 61
    },
    {
      "epoch": 0.6966292134831461,
      "grad_norm": 0.3647669851779938,
      "learning_rate": 0.0001759090909090909,
      "loss": 0.2267,
      "step": 62
    },
    {
      "epoch": 0.7078651685393258,
      "grad_norm": 0.2504497170448303,
      "learning_rate": 0.00017545454545454548,
      "loss": 0.1854,
      "step": 63
    },
    {
      "epoch": 0.7191011235955056,
      "grad_norm": 0.3424750566482544,
      "learning_rate": 0.000175,
      "loss": 0.2586,
      "step": 64
    },
    {
      "epoch": 0.7303370786516854,
      "grad_norm": 0.3164011836051941,
      "learning_rate": 0.00017454545454545454,
      "loss": 0.217,
      "step": 65
    },
    {
      "epoch": 0.7415730337078652,
      "grad_norm": 0.32831573486328125,
      "learning_rate": 0.00017409090909090911,
      "loss": 0.2326,
      "step": 66
    },
    {
      "epoch": 0.7528089887640449,
      "grad_norm": 0.3514035940170288,
      "learning_rate": 0.00017363636363636363,
      "loss": 0.2591,
      "step": 67
    },
    {
      "epoch": 0.7640449438202247,
      "grad_norm": 0.30864688754081726,
      "learning_rate": 0.0001731818181818182,
      "loss": 0.2073,
      "step": 68
    },
    {
      "epoch": 0.7752808988764045,
      "grad_norm": 0.32905542850494385,
      "learning_rate": 0.00017272727272727275,
      "loss": 0.2224,
      "step": 69
    },
    {
      "epoch": 0.7865168539325843,
      "grad_norm": 0.27842977643013,
      "learning_rate": 0.00017227272727272726,
      "loss": 0.1893,
      "step": 70
    },
    {
      "epoch": 0.797752808988764,
      "grad_norm": 0.3048170804977417,
      "learning_rate": 0.00017181818181818184,
      "loss": 0.2206,
      "step": 71
    },
    {
      "epoch": 0.8089887640449438,
      "grad_norm": 0.25344306230545044,
      "learning_rate": 0.00017136363636363638,
      "loss": 0.1876,
      "step": 72
    },
    {
      "epoch": 0.8202247191011236,
      "grad_norm": 0.3092687427997589,
      "learning_rate": 0.0001709090909090909,
      "loss": 0.1791,
      "step": 73
    },
    {
      "epoch": 0.8314606741573034,
      "grad_norm": 0.30857375264167786,
      "learning_rate": 0.00017045454545454547,
      "loss": 0.2099,
      "step": 74
    },
    {
      "epoch": 0.8426966292134831,
      "grad_norm": 0.20455722510814667,
      "learning_rate": 0.00017,
      "loss": 0.1705,
      "step": 75
    },
    {
      "epoch": 0.8539325842696629,
      "grad_norm": 0.273429274559021,
      "learning_rate": 0.00016954545454545456,
      "loss": 0.162,
      "step": 76
    },
    {
      "epoch": 0.8651685393258427,
      "grad_norm": 0.25422728061676025,
      "learning_rate": 0.0001690909090909091,
      "loss": 0.1804,
      "step": 77
    },
    {
      "epoch": 0.8764044943820225,
      "grad_norm": 0.2745291292667389,
      "learning_rate": 0.00016863636363636364,
      "loss": 0.2184,
      "step": 78
    },
    {
      "epoch": 0.8876404494382022,
      "grad_norm": 0.30162861943244934,
      "learning_rate": 0.0001681818181818182,
      "loss": 0.2371,
      "step": 79
    },
    {
      "epoch": 0.898876404494382,
      "grad_norm": 0.29733604192733765,
      "learning_rate": 0.00016772727272727273,
      "loss": 0.2018,
      "step": 80
    },
    {
      "epoch": 0.9101123595505618,
      "grad_norm": 0.22824084758758545,
      "learning_rate": 0.00016727272727272728,
      "loss": 0.1819,
      "step": 81
    },
    {
      "epoch": 0.9213483146067416,
      "grad_norm": 0.2034444659948349,
      "learning_rate": 0.00016681818181818182,
      "loss": 0.1715,
      "step": 82
    },
    {
      "epoch": 0.9325842696629213,
      "grad_norm": 0.2859365940093994,
      "learning_rate": 0.00016636363636363637,
      "loss": 0.2157,
      "step": 83
    },
    {
      "epoch": 0.9438202247191011,
      "grad_norm": 0.2006848305463791,
      "learning_rate": 0.00016590909090909094,
      "loss": 0.1595,
      "step": 84
    },
    {
      "epoch": 0.9550561797752809,
      "grad_norm": 0.3615463972091675,
      "learning_rate": 0.00016545454545454545,
      "loss": 0.2056,
      "step": 85
    },
    {
      "epoch": 0.9662921348314607,
      "grad_norm": 0.24181589484214783,
      "learning_rate": 0.000165,
      "loss": 0.2051,
      "step": 86
    },
    {
      "epoch": 0.9775280898876404,
      "grad_norm": 0.1747487634420395,
      "learning_rate": 0.00016454545454545457,
      "loss": 0.155,
      "step": 87
    },
    {
      "epoch": 0.9887640449438202,
      "grad_norm": 0.240757554769516,
      "learning_rate": 0.0001640909090909091,
      "loss": 0.1786,
      "step": 88
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.27025192975997925,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.1894,
      "step": 89
    },
    {
      "epoch": 1.0112359550561798,
      "grad_norm": 0.2341006100177765,
      "learning_rate": 0.0001631818181818182,
      "loss": 0.2067,
      "step": 90
    },
    {
      "epoch": 1.0224719101123596,
      "grad_norm": 0.2805992364883423,
      "learning_rate": 0.00016272727272727272,
      "loss": 0.223,
      "step": 91
    },
    {
      "epoch": 1.0337078651685394,
      "grad_norm": 0.21516099572181702,
      "learning_rate": 0.0001622727272727273,
      "loss": 0.1891,
      "step": 92
    },
    {
      "epoch": 1.0449438202247192,
      "grad_norm": 0.2255050241947174,
      "learning_rate": 0.00016181818181818184,
      "loss": 0.195,
      "step": 93
    },
    {
      "epoch": 1.0561797752808988,
      "grad_norm": 0.278639554977417,
      "learning_rate": 0.00016136363636363635,
      "loss": 0.2074,
      "step": 94
    },
    {
      "epoch": 1.0674157303370786,
      "grad_norm": 0.2584143877029419,
      "learning_rate": 0.00016090909090909092,
      "loss": 0.2121,
      "step": 95
    },
    {
      "epoch": 1.0786516853932584,
      "grad_norm": 0.2629978358745575,
      "learning_rate": 0.00016045454545454547,
      "loss": 0.2038,
      "step": 96
    },
    {
      "epoch": 1.0898876404494382,
      "grad_norm": 0.2283640205860138,
      "learning_rate": 0.00016,
      "loss": 0.1768,
      "step": 97
    },
    {
      "epoch": 1.101123595505618,
      "grad_norm": 0.2216864973306656,
      "learning_rate": 0.00015954545454545456,
      "loss": 0.1989,
      "step": 98
    },
    {
      "epoch": 1.1123595505617978,
      "grad_norm": 0.18183070421218872,
      "learning_rate": 0.0001590909090909091,
      "loss": 0.1631,
      "step": 99
    },
    {
      "epoch": 1.1235955056179776,
      "grad_norm": 0.19485391676425934,
      "learning_rate": 0.00015863636363636365,
      "loss": 0.1748,
      "step": 100
    },
    {
      "epoch": 1.1348314606741572,
      "grad_norm": 0.2579084038734436,
      "learning_rate": 0.0001581818181818182,
      "loss": 0.2012,
      "step": 101
    },
    {
      "epoch": 1.146067415730337,
      "grad_norm": 0.1952996402978897,
      "learning_rate": 0.00015772727272727273,
      "loss": 0.1634,
      "step": 102
    },
    {
      "epoch": 1.1573033707865168,
      "grad_norm": 0.20118536055088043,
      "learning_rate": 0.00015727272727272728,
      "loss": 0.1839,
      "step": 103
    },
    {
      "epoch": 1.1685393258426966,
      "grad_norm": 0.23753251135349274,
      "learning_rate": 0.00015681818181818182,
      "loss": 0.1861,
      "step": 104
    },
    {
      "epoch": 1.1797752808988764,
      "grad_norm": 0.26496222615242004,
      "learning_rate": 0.00015636363636363637,
      "loss": 0.226,
      "step": 105
    },
    {
      "epoch": 1.1910112359550562,
      "grad_norm": 0.17998002469539642,
      "learning_rate": 0.0001559090909090909,
      "loss": 0.1595,
      "step": 106
    },
    {
      "epoch": 1.202247191011236,
      "grad_norm": 0.25317177176475525,
      "learning_rate": 0.00015545454545454546,
      "loss": 0.1825,
      "step": 107
    },
    {
      "epoch": 1.2134831460674158,
      "grad_norm": 0.20935533940792084,
      "learning_rate": 0.000155,
      "loss": 0.1747,
      "step": 108
    },
    {
      "epoch": 1.2247191011235956,
      "grad_norm": 0.23691172897815704,
      "learning_rate": 0.00015454545454545454,
      "loss": 0.2247,
      "step": 109
    },
    {
      "epoch": 1.2359550561797752,
      "grad_norm": 0.22647719085216522,
      "learning_rate": 0.00015409090909090912,
      "loss": 0.1829,
      "step": 110
    },
    {
      "epoch": 1.247191011235955,
      "grad_norm": 0.23936079442501068,
      "learning_rate": 0.00015363636363636363,
      "loss": 0.1938,
      "step": 111
    },
    {
      "epoch": 1.2584269662921348,
      "grad_norm": 0.19330653548240662,
      "learning_rate": 0.00015318181818181818,
      "loss": 0.1603,
      "step": 112
    },
    {
      "epoch": 1.2696629213483146,
      "grad_norm": 0.19124047458171844,
      "learning_rate": 0.00015272727272727275,
      "loss": 0.184,
      "step": 113
    },
    {
      "epoch": 1.2808988764044944,
      "grad_norm": 0.1912234127521515,
      "learning_rate": 0.00015227272727272727,
      "loss": 0.1659,
      "step": 114
    },
    {
      "epoch": 1.2921348314606742,
      "grad_norm": 0.1903829127550125,
      "learning_rate": 0.0001518181818181818,
      "loss": 0.1755,
      "step": 115
    },
    {
      "epoch": 1.303370786516854,
      "grad_norm": 0.1836494654417038,
      "learning_rate": 0.00015136363636363638,
      "loss": 0.1575,
      "step": 116
    },
    {
      "epoch": 1.3146067415730336,
      "grad_norm": 0.21919198334217072,
      "learning_rate": 0.0001509090909090909,
      "loss": 0.1978,
      "step": 117
    },
    {
      "epoch": 1.3258426966292136,
      "grad_norm": 0.22532597184181213,
      "learning_rate": 0.00015045454545454547,
      "loss": 0.1604,
      "step": 118
    },
    {
      "epoch": 1.3370786516853932,
      "grad_norm": 0.22674380242824554,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.183,
      "step": 119
    },
    {
      "epoch": 1.348314606741573,
      "grad_norm": 0.23995709419250488,
      "learning_rate": 0.00014954545454545453,
      "loss": 0.1777,
      "step": 120
    },
    {
      "epoch": 1.3595505617977528,
      "grad_norm": 0.15110474824905396,
      "learning_rate": 0.0001490909090909091,
      "loss": 0.154,
      "step": 121
    },
    {
      "epoch": 1.3707865168539326,
      "grad_norm": 0.1769479662179947,
      "learning_rate": 0.00014863636363636365,
      "loss": 0.1824,
      "step": 122
    },
    {
      "epoch": 1.3820224719101124,
      "grad_norm": 0.2355855405330658,
      "learning_rate": 0.0001481818181818182,
      "loss": 0.187,
      "step": 123
    },
    {
      "epoch": 1.3932584269662922,
      "grad_norm": 0.21928639709949493,
      "learning_rate": 0.00014772727272727274,
      "loss": 0.2154,
      "step": 124
    },
    {
      "epoch": 1.404494382022472,
      "grad_norm": 0.23884353041648865,
      "learning_rate": 0.00014727272727272728,
      "loss": 0.2144,
      "step": 125
    },
    {
      "epoch": 1.4157303370786516,
      "grad_norm": 0.19905094802379608,
      "learning_rate": 0.00014681818181818182,
      "loss": 0.1758,
      "step": 126
    },
    {
      "epoch": 1.4269662921348314,
      "grad_norm": 0.20008406043052673,
      "learning_rate": 0.00014636363636363637,
      "loss": 0.1988,
      "step": 127
    },
    {
      "epoch": 1.4382022471910112,
      "grad_norm": 0.14788155257701874,
      "learning_rate": 0.0001459090909090909,
      "loss": 0.1591,
      "step": 128
    },
    {
      "epoch": 1.449438202247191,
      "grad_norm": 0.17816966772079468,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.1607,
      "step": 129
    },
    {
      "epoch": 1.4606741573033708,
      "grad_norm": 0.2414962351322174,
      "learning_rate": 0.000145,
      "loss": 0.1988,
      "step": 130
    },
    {
      "epoch": 1.4719101123595506,
      "grad_norm": 0.21710173785686493,
      "learning_rate": 0.00014454545454545457,
      "loss": 0.1749,
      "step": 131
    },
    {
      "epoch": 1.4831460674157304,
      "grad_norm": 0.30704858899116516,
      "learning_rate": 0.0001440909090909091,
      "loss": 0.2106,
      "step": 132
    },
    {
      "epoch": 1.49438202247191,
      "grad_norm": 0.22256992757320404,
      "learning_rate": 0.00014363636363636363,
      "loss": 0.1828,
      "step": 133
    },
    {
      "epoch": 1.50561797752809,
      "grad_norm": 0.2698194980621338,
      "learning_rate": 0.0001431818181818182,
      "loss": 0.2418,
      "step": 134
    },
    {
      "epoch": 1.5168539325842696,
      "grad_norm": 0.22738061845302582,
      "learning_rate": 0.00014272727272727272,
      "loss": 0.2023,
      "step": 135
    },
    {
      "epoch": 1.5280898876404494,
      "grad_norm": 0.2749398946762085,
      "learning_rate": 0.00014227272727272727,
      "loss": 0.2201,
      "step": 136
    },
    {
      "epoch": 1.5393258426966292,
      "grad_norm": 0.20003195106983185,
      "learning_rate": 0.00014181818181818184,
      "loss": 0.1658,
      "step": 137
    },
    {
      "epoch": 1.550561797752809,
      "grad_norm": 0.1827768236398697,
      "learning_rate": 0.00014136363636363635,
      "loss": 0.1787,
      "step": 138
    },
    {
      "epoch": 1.5617977528089888,
      "grad_norm": 0.20226892828941345,
      "learning_rate": 0.00014090909090909093,
      "loss": 0.1812,
      "step": 139
    },
    {
      "epoch": 1.5730337078651684,
      "grad_norm": 0.18449921905994415,
      "learning_rate": 0.00014045454545454547,
      "loss": 0.183,
      "step": 140
    },
    {
      "epoch": 1.5842696629213484,
      "grad_norm": 0.22666248679161072,
      "learning_rate": 0.00014,
      "loss": 0.2163,
      "step": 141
    },
    {
      "epoch": 1.595505617977528,
      "grad_norm": 0.2258187234401703,
      "learning_rate": 0.00013954545454545456,
      "loss": 0.2024,
      "step": 142
    },
    {
      "epoch": 1.606741573033708,
      "grad_norm": 0.17761889100074768,
      "learning_rate": 0.0001390909090909091,
      "loss": 0.1822,
      "step": 143
    },
    {
      "epoch": 1.6179775280898876,
      "grad_norm": 0.1967982053756714,
      "learning_rate": 0.00013863636363636365,
      "loss": 0.1768,
      "step": 144
    },
    {
      "epoch": 1.6292134831460674,
      "grad_norm": 0.21614395081996918,
      "learning_rate": 0.0001381818181818182,
      "loss": 0.1941,
      "step": 145
    },
    {
      "epoch": 1.6404494382022472,
      "grad_norm": 0.21362508833408356,
      "learning_rate": 0.00013772727272727274,
      "loss": 0.2053,
      "step": 146
    },
    {
      "epoch": 1.651685393258427,
      "grad_norm": 0.1829160451889038,
      "learning_rate": 0.00013727272727272728,
      "loss": 0.1601,
      "step": 147
    },
    {
      "epoch": 1.6629213483146068,
      "grad_norm": 0.19813786447048187,
      "learning_rate": 0.00013681818181818182,
      "loss": 0.2027,
      "step": 148
    },
    {
      "epoch": 1.6741573033707864,
      "grad_norm": 0.19203445315361023,
      "learning_rate": 0.00013636363636363637,
      "loss": 0.1638,
      "step": 149
    },
    {
      "epoch": 1.6853932584269664,
      "grad_norm": 0.1693754941225052,
      "learning_rate": 0.0001359090909090909,
      "loss": 0.1695,
      "step": 150
    },
    {
      "epoch": 1.696629213483146,
      "grad_norm": 0.19884233176708221,
      "learning_rate": 0.00013545454545454546,
      "loss": 0.2037,
      "step": 151
    },
    {
      "epoch": 1.7078651685393258,
      "grad_norm": 0.20025449991226196,
      "learning_rate": 0.00013500000000000003,
      "loss": 0.1927,
      "step": 152
    },
    {
      "epoch": 1.7191011235955056,
      "grad_norm": 0.1659104973077774,
      "learning_rate": 0.00013454545454545455,
      "loss": 0.164,
      "step": 153
    },
    {
      "epoch": 1.7303370786516854,
      "grad_norm": 0.16635450720787048,
      "learning_rate": 0.0001340909090909091,
      "loss": 0.1729,
      "step": 154
    },
    {
      "epoch": 1.7415730337078652,
      "grad_norm": 0.2119787037372589,
      "learning_rate": 0.00013363636363636366,
      "loss": 0.1761,
      "step": 155
    },
    {
      "epoch": 1.7528089887640448,
      "grad_norm": 0.1592678278684616,
      "learning_rate": 0.00013318181818181818,
      "loss": 0.1582,
      "step": 156
    },
    {
      "epoch": 1.7640449438202248,
      "grad_norm": 0.20228628814220428,
      "learning_rate": 0.00013272727272727275,
      "loss": 0.1833,
      "step": 157
    },
    {
      "epoch": 1.7752808988764044,
      "grad_norm": 0.19576573371887207,
      "learning_rate": 0.0001322727272727273,
      "loss": 0.1716,
      "step": 158
    },
    {
      "epoch": 1.7865168539325844,
      "grad_norm": 0.17609822750091553,
      "learning_rate": 0.0001318181818181818,
      "loss": 0.1566,
      "step": 159
    },
    {
      "epoch": 1.797752808988764,
      "grad_norm": 0.19382323324680328,
      "learning_rate": 0.00013136363636363638,
      "loss": 0.1637,
      "step": 160
    },
    {
      "epoch": 1.8089887640449438,
      "grad_norm": 0.26488256454467773,
      "learning_rate": 0.00013090909090909093,
      "loss": 0.2064,
      "step": 161
    },
    {
      "epoch": 1.8202247191011236,
      "grad_norm": 0.23723822832107544,
      "learning_rate": 0.00013045454545454544,
      "loss": 0.177,
      "step": 162
    },
    {
      "epoch": 1.8314606741573034,
      "grad_norm": 0.1890057623386383,
      "learning_rate": 0.00013000000000000002,
      "loss": 0.1784,
      "step": 163
    },
    {
      "epoch": 1.8426966292134832,
      "grad_norm": 0.1911257803440094,
      "learning_rate": 0.00012954545454545456,
      "loss": 0.1788,
      "step": 164
    },
    {
      "epoch": 1.8539325842696628,
      "grad_norm": 0.2343178540468216,
      "learning_rate": 0.0001290909090909091,
      "loss": 0.1833,
      "step": 165
    },
    {
      "epoch": 1.8651685393258428,
      "grad_norm": 0.1506495475769043,
      "learning_rate": 0.00012863636363636365,
      "loss": 0.1655,
      "step": 166
    },
    {
      "epoch": 1.8764044943820224,
      "grad_norm": 0.17160733044147491,
      "learning_rate": 0.0001281818181818182,
      "loss": 0.1586,
      "step": 167
    },
    {
      "epoch": 1.8876404494382022,
      "grad_norm": 0.13511358201503754,
      "learning_rate": 0.00012772727272727274,
      "loss": 0.1439,
      "step": 168
    },
    {
      "epoch": 1.898876404494382,
      "grad_norm": 0.1821577399969101,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.1973,
      "step": 169
    },
    {
      "epoch": 1.9101123595505618,
      "grad_norm": 0.18846295773983002,
      "learning_rate": 0.00012681818181818183,
      "loss": 0.1767,
      "step": 170
    },
    {
      "epoch": 1.9213483146067416,
      "grad_norm": 0.17300470173358917,
      "learning_rate": 0.00012636363636363637,
      "loss": 0.1726,
      "step": 171
    },
    {
      "epoch": 1.9325842696629212,
      "grad_norm": 0.20833244919776917,
      "learning_rate": 0.00012590909090909091,
      "loss": 0.2248,
      "step": 172
    },
    {
      "epoch": 1.9438202247191012,
      "grad_norm": 0.17537686228752136,
      "learning_rate": 0.00012545454545454546,
      "loss": 0.147,
      "step": 173
    },
    {
      "epoch": 1.9550561797752808,
      "grad_norm": 0.17684531211853027,
      "learning_rate": 0.000125,
      "loss": 0.1774,
      "step": 174
    },
    {
      "epoch": 1.9662921348314608,
      "grad_norm": 0.20325636863708496,
      "learning_rate": 0.00012454545454545455,
      "loss": 0.1921,
      "step": 175
    },
    {
      "epoch": 1.9775280898876404,
      "grad_norm": 0.2229178249835968,
      "learning_rate": 0.0001240909090909091,
      "loss": 0.2058,
      "step": 176
    },
    {
      "epoch": 1.9887640449438202,
      "grad_norm": 0.18187855184078217,
      "learning_rate": 0.00012363636363636364,
      "loss": 0.1883,
      "step": 177
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.18570281565189362,
      "learning_rate": 0.0001231818181818182,
      "loss": 0.1716,
      "step": 178
    }
  ],
  "logging_steps": 1,
  "max_steps": 445,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.933479100108186e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}