{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.24539877300613497,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00245398773006135,
      "grad_norm": 1.2479394674301147,
      "learning_rate": 1e-05,
      "loss": 0.377,
      "step": 1
    },
    {
      "epoch": 0.00245398773006135,
      "eval_loss": 0.3467381000518799,
      "eval_runtime": 72.8348,
      "eval_samples_per_second": 4.709,
      "eval_steps_per_second": 0.59,
      "step": 1
    },
    {
      "epoch": 0.0049079754601227,
      "grad_norm": 0.9836198687553406,
      "learning_rate": 2e-05,
      "loss": 0.2967,
      "step": 2
    },
    {
      "epoch": 0.007361963190184049,
      "grad_norm": 1.7124032974243164,
      "learning_rate": 3e-05,
      "loss": 0.435,
      "step": 3
    },
    {
      "epoch": 0.0098159509202454,
      "grad_norm": 1.0345035791397095,
      "learning_rate": 4e-05,
      "loss": 0.4481,
      "step": 4
    },
    {
      "epoch": 0.012269938650306749,
      "grad_norm": 0.5763458013534546,
      "learning_rate": 5e-05,
      "loss": 0.3339,
      "step": 5
    },
    {
      "epoch": 0.014723926380368098,
      "grad_norm": 0.5332188010215759,
      "learning_rate": 6e-05,
      "loss": 0.2942,
      "step": 6
    },
    {
      "epoch": 0.01717791411042945,
      "grad_norm": 0.6470565795898438,
      "learning_rate": 7e-05,
      "loss": 0.3236,
      "step": 7
    },
    {
      "epoch": 0.0196319018404908,
      "grad_norm": 0.5321027040481567,
      "learning_rate": 8e-05,
      "loss": 0.2108,
      "step": 8
    },
    {
      "epoch": 0.022085889570552148,
      "grad_norm": 0.5127705335617065,
      "learning_rate": 9e-05,
      "loss": 0.2737,
      "step": 9
    },
    {
      "epoch": 0.022085889570552148,
      "eval_loss": 0.19359341263771057,
      "eval_runtime": 72.1719,
      "eval_samples_per_second": 4.753,
      "eval_steps_per_second": 0.596,
      "step": 9
    },
    {
      "epoch": 0.024539877300613498,
      "grad_norm": 0.6836053729057312,
      "learning_rate": 0.0001,
      "loss": 0.2004,
      "step": 10
    },
    {
      "epoch": 0.026993865030674847,
      "grad_norm": 0.502044141292572,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.1869,
      "step": 11
    },
    {
      "epoch": 0.029447852760736196,
      "grad_norm": 0.3825146555900574,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.1578,
      "step": 12
    },
    {
      "epoch": 0.03190184049079755,
      "grad_norm": 0.4236636161804199,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.1363,
      "step": 13
    },
    {
      "epoch": 0.0343558282208589,
      "grad_norm": 0.26337090134620667,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.1019,
      "step": 14
    },
    {
      "epoch": 0.03680981595092025,
      "grad_norm": 0.2415098398923874,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.1145,
      "step": 15
    },
    {
      "epoch": 0.0392638036809816,
      "grad_norm": 0.3321601152420044,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.1443,
      "step": 16
    },
    {
      "epoch": 0.04171779141104295,
      "grad_norm": 0.24422433972358704,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.112,
      "step": 17
    },
    {
      "epoch": 0.044171779141104296,
      "grad_norm": 0.37303489446640015,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.1728,
      "step": 18
    },
    {
      "epoch": 0.044171779141104296,
      "eval_loss": 0.1137324869632721,
      "eval_runtime": 72.1628,
      "eval_samples_per_second": 4.753,
      "eval_steps_per_second": 0.596,
      "step": 18
    },
    {
      "epoch": 0.046625766871165646,
      "grad_norm": 0.21177805960178375,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0938,
      "step": 19
    },
    {
      "epoch": 0.049079754601226995,
      "grad_norm": 0.28778278827667236,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.1162,
      "step": 20
    },
    {
      "epoch": 0.051533742331288344,
      "grad_norm": 0.21777169406414032,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.0951,
      "step": 21
    },
    {
      "epoch": 0.053987730061349694,
      "grad_norm": 0.6546361446380615,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0945,
      "step": 22
    },
    {
      "epoch": 0.05644171779141104,
      "grad_norm": 0.17881807684898376,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.0842,
      "step": 23
    },
    {
      "epoch": 0.05889570552147239,
      "grad_norm": 0.2673649191856384,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0776,
      "step": 24
    },
    {
      "epoch": 0.06134969325153374,
      "grad_norm": 0.33741259574890137,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.151,
      "step": 25
    },
    {
      "epoch": 0.0638036809815951,
      "grad_norm": 0.17411549389362335,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.0686,
      "step": 26
    },
    {
      "epoch": 0.06625766871165645,
      "grad_norm": 0.2852098345756531,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.137,
      "step": 27
    },
    {
      "epoch": 0.06625766871165645,
      "eval_loss": 0.09789270907640457,
      "eval_runtime": 72.1702,
      "eval_samples_per_second": 4.753,
      "eval_steps_per_second": 0.596,
      "step": 27
    },
    {
      "epoch": 0.0687116564417178,
      "grad_norm": 0.31971484422683716,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0784,
      "step": 28
    },
    {
      "epoch": 0.07116564417177915,
      "grad_norm": 0.18859021365642548,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.1233,
      "step": 29
    },
    {
      "epoch": 0.0736196319018405,
      "grad_norm": 0.18991915881633759,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.1155,
      "step": 30
    },
    {
      "epoch": 0.07607361963190185,
      "grad_norm": 0.14949046075344086,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.0898,
      "step": 31
    },
    {
      "epoch": 0.0785276073619632,
      "grad_norm": 0.1853727400302887,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.0984,
      "step": 32
    },
    {
      "epoch": 0.08098159509202454,
      "grad_norm": 0.15843620896339417,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.1025,
      "step": 33
    },
    {
      "epoch": 0.0834355828220859,
      "grad_norm": 0.28451696038246155,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.1152,
      "step": 34
    },
    {
      "epoch": 0.08588957055214724,
      "grad_norm": 0.14049944281578064,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0741,
      "step": 35
    },
    {
      "epoch": 0.08834355828220859,
      "grad_norm": 0.17335937917232513,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.1101,
      "step": 36
    },
    {
      "epoch": 0.08834355828220859,
      "eval_loss": 0.09257706999778748,
      "eval_runtime": 72.1778,
      "eval_samples_per_second": 4.752,
      "eval_steps_per_second": 0.596,
      "step": 36
    },
    {
      "epoch": 0.09079754601226994,
      "grad_norm": 0.17011794447898865,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.1023,
      "step": 37
    },
    {
      "epoch": 0.09325153374233129,
      "grad_norm": 0.12239332497119904,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.0675,
      "step": 38
    },
    {
      "epoch": 0.09570552147239264,
      "grad_norm": 0.19732674956321716,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.1292,
      "step": 39
    },
    {
      "epoch": 0.09815950920245399,
      "grad_norm": 0.21604038774967194,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1022,
      "step": 40
    },
    {
      "epoch": 0.10061349693251534,
      "grad_norm": 0.13140861690044403,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.0832,
      "step": 41
    },
    {
      "epoch": 0.10306748466257669,
      "grad_norm": 0.16922864317893982,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0905,
      "step": 42
    },
    {
      "epoch": 0.10552147239263804,
      "grad_norm": 0.13901649415493011,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0917,
      "step": 43
    },
    {
      "epoch": 0.10797546012269939,
      "grad_norm": 0.15898378193378448,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.0964,
      "step": 44
    },
    {
      "epoch": 0.11042944785276074,
      "grad_norm": 0.22242912650108337,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0929,
      "step": 45
    },
    {
      "epoch": 0.11042944785276074,
      "eval_loss": 0.08875416219234467,
      "eval_runtime": 72.1891,
      "eval_samples_per_second": 4.751,
      "eval_steps_per_second": 0.596,
      "step": 45
    },
    {
      "epoch": 0.11288343558282209,
      "grad_norm": 0.17921759188175201,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0968,
      "step": 46
    },
    {
      "epoch": 0.11533742331288344,
      "grad_norm": 0.3090013265609741,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.1161,
      "step": 47
    },
    {
      "epoch": 0.11779141104294479,
      "grad_norm": 0.1580764204263687,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0859,
      "step": 48
    },
    {
      "epoch": 0.12024539877300613,
      "grad_norm": 0.16299057006835938,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0931,
      "step": 49
    },
    {
      "epoch": 0.12269938650306748,
      "grad_norm": 0.18056711554527283,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0934,
      "step": 50
    },
    {
      "epoch": 0.12515337423312883,
      "grad_norm": 0.12899591028690338,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.0896,
      "step": 51
    },
    {
      "epoch": 0.1276073619631902,
      "grad_norm": 0.13761845231056213,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0926,
      "step": 52
    },
    {
      "epoch": 0.13006134969325153,
      "grad_norm": 0.1670072227716446,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.0979,
      "step": 53
    },
    {
      "epoch": 0.1325153374233129,
      "grad_norm": 0.14916564524173737,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0799,
      "step": 54
    },
    {
      "epoch": 0.1325153374233129,
      "eval_loss": 0.0861867144703865,
      "eval_runtime": 72.1722,
      "eval_samples_per_second": 4.753,
      "eval_steps_per_second": 0.596,
      "step": 54
    },
    {
      "epoch": 0.13496932515337423,
      "grad_norm": 0.1766030490398407,
      "learning_rate": 5e-05,
      "loss": 0.0606,
      "step": 55
    },
    {
      "epoch": 0.1374233128834356,
      "grad_norm": 0.133830726146698,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.0845,
      "step": 56
    },
    {
      "epoch": 0.13987730061349693,
      "grad_norm": 0.17518991231918335,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.073,
      "step": 57
    },
    {
      "epoch": 0.1423312883435583,
      "grad_norm": 0.1533428430557251,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0843,
      "step": 58
    },
    {
      "epoch": 0.14478527607361963,
      "grad_norm": 0.13991299271583557,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.0718,
      "step": 59
    },
    {
      "epoch": 0.147239263803681,
      "grad_norm": 0.1512841433286667,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.085,
      "step": 60
    },
    {
      "epoch": 0.14969325153374233,
      "grad_norm": 0.1344129890203476,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.0761,
      "step": 61
    },
    {
      "epoch": 0.1521472392638037,
      "grad_norm": 0.1694488674402237,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0939,
      "step": 62
    },
    {
      "epoch": 0.15460122699386503,
      "grad_norm": 0.14527535438537598,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.0855,
      "step": 63
    },
    {
      "epoch": 0.15460122699386503,
      "eval_loss": 0.0837635025382042,
      "eval_runtime": 72.198,
      "eval_samples_per_second": 4.751,
      "eval_steps_per_second": 0.596,
      "step": 63
    },
    {
      "epoch": 0.1570552147239264,
      "grad_norm": 0.11152983456850052,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0755,
      "step": 64
    },
    {
      "epoch": 0.15950920245398773,
      "grad_norm": 0.14772440493106842,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.08,
      "step": 65
    },
    {
      "epoch": 0.1619631901840491,
      "grad_norm": 0.14314669370651245,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0783,
      "step": 66
    },
    {
      "epoch": 0.16441717791411042,
      "grad_norm": 0.23815108835697174,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.1082,
      "step": 67
    },
    {
      "epoch": 0.1668711656441718,
      "grad_norm": 0.19166451692581177,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0888,
      "step": 68
    },
    {
      "epoch": 0.16932515337423312,
      "grad_norm": 0.19325505197048187,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.1017,
      "step": 69
    },
    {
      "epoch": 0.17177914110429449,
      "grad_norm": 0.16106754541397095,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0922,
      "step": 70
    },
    {
      "epoch": 0.17423312883435582,
      "grad_norm": 0.0972488522529602,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0567,
      "step": 71
    },
    {
      "epoch": 0.17668711656441718,
      "grad_norm": 0.1254057139158249,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0602,
      "step": 72
    },
    {
      "epoch": 0.17668711656441718,
      "eval_loss": 0.0817757397890091,
      "eval_runtime": 72.2756,
      "eval_samples_per_second": 4.746,
      "eval_steps_per_second": 0.595,
      "step": 72
    },
    {
      "epoch": 0.17914110429447852,
      "grad_norm": 0.1219269409775734,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0836,
      "step": 73
    },
    {
      "epoch": 0.18159509202453988,
      "grad_norm": 0.10528916865587234,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0572,
      "step": 74
    },
    {
      "epoch": 0.18404907975460122,
      "grad_norm": 0.1957486867904663,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0593,
      "step": 75
    },
    {
      "epoch": 0.18650306748466258,
      "grad_norm": 0.1609889268875122,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.1074,
      "step": 76
    },
    {
      "epoch": 0.18895705521472392,
      "grad_norm": 0.14295519888401031,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.0724,
      "step": 77
    },
    {
      "epoch": 0.19141104294478528,
      "grad_norm": 0.2733156681060791,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.1378,
      "step": 78
    },
    {
      "epoch": 0.19386503067484662,
      "grad_norm": 0.19158926606178284,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.0873,
      "step": 79
    },
    {
      "epoch": 0.19631901840490798,
      "grad_norm": 0.15549211204051971,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0799,
      "step": 80
    },
    {
      "epoch": 0.19877300613496932,
      "grad_norm": 0.1473371535539627,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0927,
      "step": 81
    },
    {
      "epoch": 0.19877300613496932,
      "eval_loss": 0.08084429800510406,
      "eval_runtime": 72.2318,
      "eval_samples_per_second": 4.749,
      "eval_steps_per_second": 0.595,
      "step": 81
    },
    {
      "epoch": 0.20122699386503068,
      "grad_norm": 0.18977564573287964,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0813,
      "step": 82
    },
    {
      "epoch": 0.20368098159509201,
      "grad_norm": 0.19046197831630707,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.0985,
      "step": 83
    },
    {
      "epoch": 0.20613496932515338,
      "grad_norm": 0.2664346992969513,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.1368,
      "step": 84
    },
    {
      "epoch": 0.2085889570552147,
      "grad_norm": 0.15875068306922913,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0904,
      "step": 85
    },
    {
      "epoch": 0.21104294478527608,
      "grad_norm": 0.141635924577713,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0763,
      "step": 86
    },
    {
      "epoch": 0.2134969325153374,
      "grad_norm": 0.1432258039712906,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.0752,
      "step": 87
    },
    {
      "epoch": 0.21595092024539878,
      "grad_norm": 0.1705997735261917,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0682,
      "step": 88
    },
    {
      "epoch": 0.2184049079754601,
      "grad_norm": 0.172316774725914,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.0725,
      "step": 89
    },
    {
      "epoch": 0.22085889570552147,
      "grad_norm": 0.14289115369319916,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.087,
      "step": 90
    },
    {
      "epoch": 0.22085889570552147,
      "eval_loss": 0.07996805757284164,
      "eval_runtime": 72.1848,
      "eval_samples_per_second": 4.752,
      "eval_steps_per_second": 0.596,
      "step": 90
    },
    {
      "epoch": 0.2233128834355828,
      "grad_norm": 0.18413448333740234,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0918,
      "step": 91
    },
    {
      "epoch": 0.22576687116564417,
      "grad_norm": 0.21855594217777252,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.1008,
      "step": 92
    },
    {
      "epoch": 0.2282208588957055,
      "grad_norm": 0.1916782408952713,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.089,
      "step": 93
    },
    {
      "epoch": 0.23067484662576687,
      "grad_norm": 0.15419402718544006,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.1061,
      "step": 94
    },
    {
      "epoch": 0.2331288343558282,
      "grad_norm": 0.10309912264347076,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0595,
      "step": 95
    },
    {
      "epoch": 0.23558282208588957,
      "grad_norm": 0.1862940937280655,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0664,
      "step": 96
    },
    {
      "epoch": 0.23803680981595093,
      "grad_norm": 0.15097887814044952,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.0872,
      "step": 97
    },
    {
      "epoch": 0.24049079754601227,
      "grad_norm": 0.466399222612381,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0873,
      "step": 98
    },
    {
      "epoch": 0.24294478527607363,
      "grad_norm": 0.12407394498586655,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0674,
      "step": 99
    },
    {
      "epoch": 0.24294478527607363,
      "eval_loss": 0.07985200732946396,
      "eval_runtime": 72.2547,
      "eval_samples_per_second": 4.747,
      "eval_steps_per_second": 0.595,
      "step": 99
    },
    {
      "epoch": 0.24539877300613497,
      "grad_norm": 0.13656176626682281,
      "learning_rate": 0.0,
      "loss": 0.0659,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.283465000559575e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}