{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.018001800180018002,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00018001800180018,
      "grad_norm": 5.87307071685791,
      "learning_rate": 1e-05,
      "loss": 11.6144,
      "step": 1
    },
    {
      "epoch": 0.00018001800180018,
      "eval_loss": 11.61415958404541,
      "eval_runtime": 41.4656,
      "eval_samples_per_second": 112.816,
      "eval_steps_per_second": 14.108,
      "step": 1
    },
    {
      "epoch": 0.00036003600360036,
      "grad_norm": 6.0188374519348145,
      "learning_rate": 2e-05,
      "loss": 11.4565,
      "step": 2
    },
    {
      "epoch": 0.00054005400540054,
      "grad_norm": 5.906339168548584,
      "learning_rate": 3e-05,
      "loss": 11.3091,
      "step": 3
    },
    {
      "epoch": 0.00072007200720072,
      "grad_norm": 5.721518516540527,
      "learning_rate": 4e-05,
      "loss": 11.9668,
      "step": 4
    },
    {
      "epoch": 0.0009000900090009,
      "grad_norm": 6.276498794555664,
      "learning_rate": 5e-05,
      "loss": 11.5562,
      "step": 5
    },
    {
      "epoch": 0.00108010801080108,
      "grad_norm": 4.8785576820373535,
      "learning_rate": 6e-05,
      "loss": 11.1344,
      "step": 6
    },
    {
      "epoch": 0.0012601260126012602,
      "grad_norm": 5.525317668914795,
      "learning_rate": 7e-05,
      "loss": 11.1017,
      "step": 7
    },
    {
      "epoch": 0.00144014401440144,
      "grad_norm": 7.0762529373168945,
      "learning_rate": 8e-05,
      "loss": 11.8841,
      "step": 8
    },
    {
      "epoch": 0.0016201620162016202,
      "grad_norm": 5.757331371307373,
      "learning_rate": 9e-05,
      "loss": 11.6058,
      "step": 9
    },
    {
      "epoch": 0.0016201620162016202,
      "eval_loss": 11.442190170288086,
      "eval_runtime": 41.4866,
      "eval_samples_per_second": 112.759,
      "eval_steps_per_second": 14.101,
      "step": 9
    },
    {
      "epoch": 0.0018001800180018,
      "grad_norm": 5.312053203582764,
      "learning_rate": 0.0001,
      "loss": 11.3765,
      "step": 10
    },
    {
      "epoch": 0.0019801980198019802,
      "grad_norm": 5.930967807769775,
      "learning_rate": 9.99695413509548e-05,
      "loss": 11.6333,
      "step": 11
    },
    {
      "epoch": 0.00216021602160216,
      "grad_norm": 6.4748945236206055,
      "learning_rate": 9.987820251299122e-05,
      "loss": 11.5855,
      "step": 12
    },
    {
      "epoch": 0.00234023402340234,
      "grad_norm": 6.37196683883667,
      "learning_rate": 9.972609476841367e-05,
      "loss": 11.5042,
      "step": 13
    },
    {
      "epoch": 0.0025202520252025204,
      "grad_norm": 5.835845947265625,
      "learning_rate": 9.951340343707852e-05,
      "loss": 11.6153,
      "step": 14
    },
    {
      "epoch": 0.0027002700270027003,
      "grad_norm": 5.734114170074463,
      "learning_rate": 9.924038765061042e-05,
      "loss": 11.1202,
      "step": 15
    },
    {
      "epoch": 0.00288028802880288,
      "grad_norm": 5.847100257873535,
      "learning_rate": 9.890738003669029e-05,
      "loss": 11.1372,
      "step": 16
    },
    {
      "epoch": 0.0030603060306030605,
      "grad_norm": 5.214365005493164,
      "learning_rate": 9.851478631379982e-05,
      "loss": 11.0652,
      "step": 17
    },
    {
      "epoch": 0.0032403240324032404,
      "grad_norm": 5.617738723754883,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.7516,
      "step": 18
    },
    {
      "epoch": 0.0032403240324032404,
      "eval_loss": 10.946746826171875,
      "eval_runtime": 41.4928,
      "eval_samples_per_second": 112.743,
      "eval_steps_per_second": 14.099,
      "step": 18
    },
    {
      "epoch": 0.0034203420342034203,
      "grad_norm": 6.485275745391846,
      "learning_rate": 9.755282581475769e-05,
      "loss": 11.0168,
      "step": 19
    },
    {
      "epoch": 0.0036003600360036,
      "grad_norm": 5.778016090393066,
      "learning_rate": 9.698463103929542e-05,
      "loss": 11.0644,
      "step": 20
    },
    {
      "epoch": 0.0037803780378037805,
      "grad_norm": 4.897763252258301,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.8183,
      "step": 21
    },
    {
      "epoch": 0.0039603960396039604,
      "grad_norm": 4.856274127960205,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.8357,
      "step": 22
    },
    {
      "epoch": 0.004140414041404141,
      "grad_norm": 6.177309989929199,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.8354,
      "step": 23
    },
    {
      "epoch": 0.00432043204320432,
      "grad_norm": 5.736455917358398,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.4543,
      "step": 24
    },
    {
      "epoch": 0.004500450045004501,
      "grad_norm": 5.722464084625244,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.7997,
      "step": 25
    },
    {
      "epoch": 0.00468046804680468,
      "grad_norm": 5.896301746368408,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.8154,
      "step": 26
    },
    {
      "epoch": 0.00486048604860486,
      "grad_norm": 6.108735084533691,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.477,
      "step": 27
    },
    {
      "epoch": 0.00486048604860486,
      "eval_loss": 10.479217529296875,
      "eval_runtime": 41.5514,
      "eval_samples_per_second": 112.583,
      "eval_steps_per_second": 14.079,
      "step": 27
    },
    {
      "epoch": 0.005040504050405041,
      "grad_norm": 6.187192916870117,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.7532,
      "step": 28
    },
    {
      "epoch": 0.00522052205220522,
      "grad_norm": 6.162825107574463,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.0425,
      "step": 29
    },
    {
      "epoch": 0.0054005400540054005,
      "grad_norm": 5.06771993637085,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.6456,
      "step": 30
    },
    {
      "epoch": 0.005580558055805581,
      "grad_norm": 6.633289813995361,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.5557,
      "step": 31
    },
    {
      "epoch": 0.00576057605760576,
      "grad_norm": 7.135171413421631,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.4076,
      "step": 32
    },
    {
      "epoch": 0.005940594059405941,
      "grad_norm": 6.247159481048584,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.2683,
      "step": 33
    },
    {
      "epoch": 0.006120612061206121,
      "grad_norm": 5.888491153717041,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.3905,
      "step": 34
    },
    {
      "epoch": 0.0063006300630063005,
      "grad_norm": 6.2340407371521,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.0002,
      "step": 35
    },
    {
      "epoch": 0.006480648064806481,
      "grad_norm": 5.402869701385498,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.0471,
      "step": 36
    },
    {
      "epoch": 0.006480648064806481,
      "eval_loss": 10.007487297058105,
      "eval_runtime": 41.5019,
      "eval_samples_per_second": 112.718,
      "eval_steps_per_second": 14.096,
      "step": 36
    },
    {
      "epoch": 0.00666066606660666,
      "grad_norm": 6.251911163330078,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.0034,
      "step": 37
    },
    {
      "epoch": 0.006840684068406841,
      "grad_norm": 7.18772554397583,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.0799,
      "step": 38
    },
    {
      "epoch": 0.007020702070207021,
      "grad_norm": 6.769697666168213,
      "learning_rate": 7.649596321166024e-05,
      "loss": 9.8849,
      "step": 39
    },
    {
      "epoch": 0.0072007200720072,
      "grad_norm": 6.6725568771362305,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.18,
      "step": 40
    },
    {
      "epoch": 0.007380738073807381,
      "grad_norm": 7.166985511779785,
      "learning_rate": 7.347357813929454e-05,
      "loss": 9.7688,
      "step": 41
    },
    {
      "epoch": 0.007560756075607561,
      "grad_norm": 5.779541015625,
      "learning_rate": 7.191855733945387e-05,
      "loss": 9.6471,
      "step": 42
    },
    {
      "epoch": 0.0077407740774077406,
      "grad_norm": 7.53178596496582,
      "learning_rate": 7.033683215379002e-05,
      "loss": 9.5978,
      "step": 43
    },
    {
      "epoch": 0.007920792079207921,
      "grad_norm": 5.810229301452637,
      "learning_rate": 6.873032967079561e-05,
      "loss": 9.6907,
      "step": 44
    },
    {
      "epoch": 0.008100810081008101,
      "grad_norm": 5.271368980407715,
      "learning_rate": 6.710100716628344e-05,
      "loss": 9.7006,
      "step": 45
    },
    {
      "epoch": 0.008100810081008101,
      "eval_loss": 9.594242095947266,
      "eval_runtime": 41.4612,
      "eval_samples_per_second": 112.828,
      "eval_steps_per_second": 14.11,
      "step": 45
    },
    {
      "epoch": 0.008280828082808282,
      "grad_norm": 6.034334182739258,
      "learning_rate": 6.545084971874738e-05,
      "loss": 9.9457,
      "step": 46
    },
    {
      "epoch": 0.00846084608460846,
      "grad_norm": 6.873132228851318,
      "learning_rate": 6.378186779084995e-05,
      "loss": 9.3553,
      "step": 47
    },
    {
      "epoch": 0.00864086408640864,
      "grad_norm": 5.189530849456787,
      "learning_rate": 6.209609477998338e-05,
      "loss": 9.7457,
      "step": 48
    },
    {
      "epoch": 0.00882088208820882,
      "grad_norm": 4.753223896026611,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 9.5327,
      "step": 49
    },
    {
      "epoch": 0.009000900090009001,
      "grad_norm": 5.407626628875732,
      "learning_rate": 5.868240888334653e-05,
      "loss": 9.4796,
      "step": 50
    },
    {
      "epoch": 0.009180918091809182,
      "grad_norm": 5.1421217918396,
      "learning_rate": 5.695865504800327e-05,
      "loss": 9.5437,
      "step": 51
    },
    {
      "epoch": 0.00936093609360936,
      "grad_norm": 4.592971324920654,
      "learning_rate": 5.522642316338268e-05,
      "loss": 9.1944,
      "step": 52
    },
    {
      "epoch": 0.00954095409540954,
      "grad_norm": 5.622161865234375,
      "learning_rate": 5.348782368720626e-05,
      "loss": 9.6394,
      "step": 53
    },
    {
      "epoch": 0.00972097209720972,
      "grad_norm": 5.27858829498291,
      "learning_rate": 5.174497483512506e-05,
      "loss": 9.5195,
      "step": 54
    },
    {
      "epoch": 0.00972097209720972,
      "eval_loss": 9.32948112487793,
      "eval_runtime": 41.5183,
      "eval_samples_per_second": 112.673,
      "eval_steps_per_second": 14.09,
      "step": 54
    },
    {
      "epoch": 0.009900990099009901,
      "grad_norm": 4.497775077819824,
      "learning_rate": 5e-05,
      "loss": 9.308,
      "step": 55
    },
    {
      "epoch": 0.010081008100810081,
      "grad_norm": 4.790937900543213,
      "learning_rate": 4.825502516487497e-05,
      "loss": 9.3374,
      "step": 56
    },
    {
      "epoch": 0.010261026102610262,
      "grad_norm": 4.156779766082764,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 9.0797,
      "step": 57
    },
    {
      "epoch": 0.01044104410441044,
      "grad_norm": 5.075934410095215,
      "learning_rate": 4.477357683661734e-05,
      "loss": 9.1865,
      "step": 58
    },
    {
      "epoch": 0.01062106210621062,
      "grad_norm": 5.212141513824463,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 9.2446,
      "step": 59
    },
    {
      "epoch": 0.010801080108010801,
      "grad_norm": 4.7454705238342285,
      "learning_rate": 4.131759111665349e-05,
      "loss": 9.1307,
      "step": 60
    },
    {
      "epoch": 0.010981098109810981,
      "grad_norm": 4.656852722167969,
      "learning_rate": 3.960441545911204e-05,
      "loss": 8.9722,
      "step": 61
    },
    {
      "epoch": 0.011161116111611162,
      "grad_norm": 4.986353397369385,
      "learning_rate": 3.790390522001662e-05,
      "loss": 9.6201,
      "step": 62
    },
    {
      "epoch": 0.01134113411341134,
      "grad_norm": 4.1770830154418945,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 9.1031,
      "step": 63
    },
    {
      "epoch": 0.01134113411341134,
      "eval_loss": 9.168355941772461,
      "eval_runtime": 41.4788,
      "eval_samples_per_second": 112.781,
      "eval_steps_per_second": 14.104,
      "step": 63
    },
    {
      "epoch": 0.01152115211521152,
      "grad_norm": 5.309531211853027,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 9.3599,
      "step": 64
    },
    {
      "epoch": 0.011701170117011701,
      "grad_norm": 4.383259296417236,
      "learning_rate": 3.289899283371657e-05,
      "loss": 9.15,
      "step": 65
    },
    {
      "epoch": 0.011881188118811881,
      "grad_norm": 4.308704853057861,
      "learning_rate": 3.12696703292044e-05,
      "loss": 9.0913,
      "step": 66
    },
    {
      "epoch": 0.012061206120612062,
      "grad_norm": 4.408690929412842,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 9.3145,
      "step": 67
    },
    {
      "epoch": 0.012241224122412242,
      "grad_norm": 4.576683521270752,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 8.8956,
      "step": 68
    },
    {
      "epoch": 0.01242124212421242,
      "grad_norm": 4.590541839599609,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 9.1312,
      "step": 69
    },
    {
      "epoch": 0.012601260126012601,
      "grad_norm": 4.922686576843262,
      "learning_rate": 2.500000000000001e-05,
      "loss": 9.0805,
      "step": 70
    },
    {
      "epoch": 0.012781278127812781,
      "grad_norm": 4.215728759765625,
      "learning_rate": 2.350403678833976e-05,
      "loss": 9.2433,
      "step": 71
    },
    {
      "epoch": 0.012961296129612962,
      "grad_norm": 4.534681797027588,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 8.948,
      "step": 72
    },
    {
      "epoch": 0.012961296129612962,
      "eval_loss": 9.072084426879883,
      "eval_runtime": 41.5005,
      "eval_samples_per_second": 112.721,
      "eval_steps_per_second": 14.096,
      "step": 72
    },
    {
      "epoch": 0.013141314131413142,
      "grad_norm": 4.945130348205566,
      "learning_rate": 2.061073738537635e-05,
      "loss": 9.4625,
      "step": 73
    },
    {
      "epoch": 0.01332133213321332,
      "grad_norm": 4.447700500488281,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 8.8096,
      "step": 74
    },
    {
      "epoch": 0.013501350135013501,
      "grad_norm": 4.476735591888428,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 8.8277,
      "step": 75
    },
    {
      "epoch": 0.013681368136813681,
      "grad_norm": 4.766935348510742,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 9.1841,
      "step": 76
    },
    {
      "epoch": 0.013861386138613862,
      "grad_norm": 3.851850986480713,
      "learning_rate": 1.526708147705013e-05,
      "loss": 9.1235,
      "step": 77
    },
    {
      "epoch": 0.014041404140414042,
      "grad_norm": 4.168645858764648,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 8.9935,
      "step": 78
    },
    {
      "epoch": 0.014221422142214222,
      "grad_norm": 4.831826210021973,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 8.9272,
      "step": 79
    },
    {
      "epoch": 0.0144014401440144,
      "grad_norm": 4.024872779846191,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 9.0397,
      "step": 80
    },
    {
      "epoch": 0.014581458145814581,
      "grad_norm": 4.845215797424316,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 9.3672,
      "step": 81
    },
    {
      "epoch": 0.014581458145814581,
      "eval_loss": 9.021185874938965,
      "eval_runtime": 41.5093,
      "eval_samples_per_second": 112.698,
      "eval_steps_per_second": 14.093,
      "step": 81
    },
    {
      "epoch": 0.014761476147614761,
      "grad_norm": 4.619018077850342,
      "learning_rate": 9.549150281252633e-06,
      "loss": 8.9587,
      "step": 82
    },
    {
      "epoch": 0.014941494149414942,
      "grad_norm": 4.925379276275635,
      "learning_rate": 8.548121372247918e-06,
      "loss": 9.0123,
      "step": 83
    },
    {
      "epoch": 0.015121512151215122,
      "grad_norm": 4.891155242919922,
      "learning_rate": 7.597595192178702e-06,
      "loss": 9.1269,
      "step": 84
    },
    {
      "epoch": 0.0153015301530153,
      "grad_norm": 5.3043365478515625,
      "learning_rate": 6.698729810778065e-06,
      "loss": 9.0393,
      "step": 85
    },
    {
      "epoch": 0.015481548154815481,
      "grad_norm": 4.2021026611328125,
      "learning_rate": 5.852620357053651e-06,
      "loss": 9.1264,
      "step": 86
    },
    {
      "epoch": 0.015661566156615663,
      "grad_norm": 4.361050605773926,
      "learning_rate": 5.060297685041659e-06,
      "loss": 8.5332,
      "step": 87
    },
    {
      "epoch": 0.015841584158415842,
      "grad_norm": 4.473583221435547,
      "learning_rate": 4.322727117869951e-06,
      "loss": 9.0751,
      "step": 88
    },
    {
      "epoch": 0.01602160216021602,
      "grad_norm": 4.596582412719727,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 8.8596,
      "step": 89
    },
    {
      "epoch": 0.016201620162016202,
      "grad_norm": 4.931702613830566,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 9.0441,
      "step": 90
    },
    {
      "epoch": 0.016201620162016202,
      "eval_loss": 9.001091003417969,
      "eval_runtime": 41.4597,
      "eval_samples_per_second": 112.832,
      "eval_steps_per_second": 14.11,
      "step": 90
    },
    {
      "epoch": 0.01638163816381638,
      "grad_norm": 5.500175952911377,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 9.2136,
      "step": 91
    },
    {
      "epoch": 0.016561656165616563,
      "grad_norm": 5.783007621765137,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 9.234,
      "step": 92
    },
    {
      "epoch": 0.01674167416741674,
      "grad_norm": 4.667166233062744,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 9.107,
      "step": 93
    },
    {
      "epoch": 0.01692169216921692,
      "grad_norm": 4.6480712890625,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 8.7428,
      "step": 94
    },
    {
      "epoch": 0.017101710171017102,
      "grad_norm": 4.516505241394043,
      "learning_rate": 7.596123493895991e-07,
      "loss": 8.8254,
      "step": 95
    },
    {
      "epoch": 0.01728172817281728,
      "grad_norm": 4.1551103591918945,
      "learning_rate": 4.865965629214819e-07,
      "loss": 8.9528,
      "step": 96
    },
    {
      "epoch": 0.017461746174617463,
      "grad_norm": 4.877590656280518,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 9.1006,
      "step": 97
    },
    {
      "epoch": 0.01764176417641764,
      "grad_norm": 5.414852619171143,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 9.0552,
      "step": 98
    },
    {
      "epoch": 0.01782178217821782,
      "grad_norm": 5.404477596282959,
      "learning_rate": 3.04586490452119e-08,
      "loss": 9.08,
      "step": 99
    },
    {
      "epoch": 0.01782178217821782,
      "eval_loss": 8.99763298034668,
      "eval_runtime": 41.4635,
      "eval_samples_per_second": 112.822,
      "eval_steps_per_second": 14.109,
      "step": 99
    },
    {
      "epoch": 0.018001800180018002,
      "grad_norm": 5.185412406921387,
      "learning_rate": 0.0,
      "loss": 9.0785,
      "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": 27149520076800.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}