{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2127659574468085,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002127659574468085,
      "grad_norm": 0.10300079733133316,
      "learning_rate": 1e-05,
      "loss": 0.5286,
      "step": 1
    },
    {
      "epoch": 0.002127659574468085,
      "eval_loss": 0.28012359142303467,
      "eval_runtime": 136.1969,
      "eval_samples_per_second": 2.908,
      "eval_steps_per_second": 0.367,
      "step": 1
    },
    {
      "epoch": 0.00425531914893617,
      "grad_norm": 0.10144907981157303,
      "learning_rate": 2e-05,
      "loss": 0.4953,
      "step": 2
    },
    {
      "epoch": 0.006382978723404255,
      "grad_norm": 0.08996520936489105,
      "learning_rate": 3e-05,
      "loss": 0.4374,
      "step": 3
    },
    {
      "epoch": 0.00851063829787234,
      "grad_norm": 0.09395291656255722,
      "learning_rate": 4e-05,
      "loss": 0.5495,
      "step": 4
    },
    {
      "epoch": 0.010638297872340425,
      "grad_norm": 0.10324636846780777,
      "learning_rate": 5e-05,
      "loss": 0.6145,
      "step": 5
    },
    {
      "epoch": 0.01276595744680851,
      "grad_norm": 0.08707210421562195,
      "learning_rate": 6e-05,
      "loss": 0.3558,
      "step": 6
    },
    {
      "epoch": 0.014893617021276596,
      "grad_norm": 0.11621297895908356,
      "learning_rate": 7e-05,
      "loss": 0.5514,
      "step": 7
    },
    {
      "epoch": 0.01702127659574468,
      "grad_norm": 0.10932344943284988,
      "learning_rate": 8e-05,
      "loss": 0.5639,
      "step": 8
    },
    {
      "epoch": 0.019148936170212766,
      "grad_norm": 0.1405569314956665,
      "learning_rate": 9e-05,
      "loss": 0.4737,
      "step": 9
    },
    {
      "epoch": 0.019148936170212766,
      "eval_loss": 0.2623712122440338,
      "eval_runtime": 137.2425,
      "eval_samples_per_second": 2.885,
      "eval_steps_per_second": 0.364,
      "step": 9
    },
    {
      "epoch": 0.02127659574468085,
      "grad_norm": 0.14397543668746948,
      "learning_rate": 0.0001,
      "loss": 0.5168,
      "step": 10
    },
    {
      "epoch": 0.023404255319148935,
      "grad_norm": 0.1323714256286621,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.4371,
      "step": 11
    },
    {
      "epoch": 0.02553191489361702,
      "grad_norm": 0.13116616010665894,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.4262,
      "step": 12
    },
    {
      "epoch": 0.027659574468085105,
      "grad_norm": 0.13853837549686432,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.5099,
      "step": 13
    },
    {
      "epoch": 0.029787234042553193,
      "grad_norm": 0.1474577784538269,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.3021,
      "step": 14
    },
    {
      "epoch": 0.031914893617021274,
      "grad_norm": 0.1504347324371338,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.4131,
      "step": 15
    },
    {
      "epoch": 0.03404255319148936,
      "grad_norm": 0.1708698570728302,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.4761,
      "step": 16
    },
    {
      "epoch": 0.036170212765957444,
      "grad_norm": 0.17005902528762817,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.3081,
      "step": 17
    },
    {
      "epoch": 0.03829787234042553,
      "grad_norm": 0.21712253987789154,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.4314,
      "step": 18
    },
    {
      "epoch": 0.03829787234042553,
      "eval_loss": 0.18715143203735352,
      "eval_runtime": 137.3301,
      "eval_samples_per_second": 2.884,
      "eval_steps_per_second": 0.364,
      "step": 18
    },
    {
      "epoch": 0.04042553191489362,
      "grad_norm": 0.23651768267154694,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.3969,
      "step": 19
    },
    {
      "epoch": 0.0425531914893617,
      "grad_norm": 0.1859365850687027,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.435,
      "step": 20
    },
    {
      "epoch": 0.04468085106382979,
      "grad_norm": 0.20384368300437927,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.3033,
      "step": 21
    },
    {
      "epoch": 0.04680851063829787,
      "grad_norm": 0.2507339417934418,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.3752,
      "step": 22
    },
    {
      "epoch": 0.04893617021276596,
      "grad_norm": 0.23452381789684296,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.2799,
      "step": 23
    },
    {
      "epoch": 0.05106382978723404,
      "grad_norm": 0.22419746220111847,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.334,
      "step": 24
    },
    {
      "epoch": 0.05319148936170213,
      "grad_norm": 0.19811676442623138,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.2044,
      "step": 25
    },
    {
      "epoch": 0.05531914893617021,
      "grad_norm": 0.359153151512146,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.2482,
      "step": 26
    },
    {
      "epoch": 0.0574468085106383,
      "grad_norm": 0.18441106379032135,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.1794,
      "step": 27
    },
    {
      "epoch": 0.0574468085106383,
      "eval_loss": 0.12238021194934845,
      "eval_runtime": 137.2684,
      "eval_samples_per_second": 2.885,
      "eval_steps_per_second": 0.364,
      "step": 27
    },
    {
      "epoch": 0.059574468085106386,
      "grad_norm": 0.22044096887111664,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.2014,
      "step": 28
    },
    {
      "epoch": 0.06170212765957447,
      "grad_norm": 0.2687065601348877,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.2124,
      "step": 29
    },
    {
      "epoch": 0.06382978723404255,
      "grad_norm": 0.233614981174469,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.1827,
      "step": 30
    },
    {
      "epoch": 0.06595744680851064,
      "grad_norm": 0.24253681302070618,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.2346,
      "step": 31
    },
    {
      "epoch": 0.06808510638297872,
      "grad_norm": 0.3058152198791504,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.2525,
      "step": 32
    },
    {
      "epoch": 0.07021276595744681,
      "grad_norm": 0.26571205258369446,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.2364,
      "step": 33
    },
    {
      "epoch": 0.07234042553191489,
      "grad_norm": 0.3335438668727875,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.2018,
      "step": 34
    },
    {
      "epoch": 0.07446808510638298,
      "grad_norm": 0.19825226068496704,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0671,
      "step": 35
    },
    {
      "epoch": 0.07659574468085106,
      "grad_norm": 0.29797136783599854,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.1928,
      "step": 36
    },
    {
      "epoch": 0.07659574468085106,
      "eval_loss": 0.07695513218641281,
      "eval_runtime": 137.3251,
      "eval_samples_per_second": 2.884,
      "eval_steps_per_second": 0.364,
      "step": 36
    },
    {
      "epoch": 0.07872340425531915,
      "grad_norm": 0.25794219970703125,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.1857,
      "step": 37
    },
    {
      "epoch": 0.08085106382978724,
      "grad_norm": 0.307058185338974,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.1421,
      "step": 38
    },
    {
      "epoch": 0.08297872340425531,
      "grad_norm": 0.3750346601009369,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.1814,
      "step": 39
    },
    {
      "epoch": 0.0851063829787234,
      "grad_norm": 0.20193852484226227,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1059,
      "step": 40
    },
    {
      "epoch": 0.08723404255319149,
      "grad_norm": 0.25090059638023376,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.1099,
      "step": 41
    },
    {
      "epoch": 0.08936170212765958,
      "grad_norm": 0.2916666567325592,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.1083,
      "step": 42
    },
    {
      "epoch": 0.09148936170212765,
      "grad_norm": 0.36291268467903137,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.2022,
      "step": 43
    },
    {
      "epoch": 0.09361702127659574,
      "grad_norm": 0.21358266472816467,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.1125,
      "step": 44
    },
    {
      "epoch": 0.09574468085106383,
      "grad_norm": 0.3255113661289215,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0567,
      "step": 45
    },
    {
      "epoch": 0.09574468085106383,
      "eval_loss": 0.04827962815761566,
      "eval_runtime": 137.277,
      "eval_samples_per_second": 2.885,
      "eval_steps_per_second": 0.364,
      "step": 45
    },
    {
      "epoch": 0.09787234042553192,
      "grad_norm": 0.3126741051673889,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.1151,
      "step": 46
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.3010190725326538,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.1746,
      "step": 47
    },
    {
      "epoch": 0.10212765957446808,
      "grad_norm": 0.2182113230228424,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0787,
      "step": 48
    },
    {
      "epoch": 0.10425531914893617,
      "grad_norm": 0.23019395768642426,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0583,
      "step": 49
    },
    {
      "epoch": 0.10638297872340426,
      "grad_norm": 0.18560408055782318,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0537,
      "step": 50
    },
    {
      "epoch": 0.10851063829787234,
      "grad_norm": 0.24473926424980164,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.1363,
      "step": 51
    },
    {
      "epoch": 0.11063829787234042,
      "grad_norm": 0.23498021066188812,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0853,
      "step": 52
    },
    {
      "epoch": 0.1127659574468085,
      "grad_norm": 0.2749404013156891,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.0979,
      "step": 53
    },
    {
      "epoch": 0.1148936170212766,
      "grad_norm": 0.18543550372123718,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0393,
      "step": 54
    },
    {
      "epoch": 0.1148936170212766,
      "eval_loss": 0.0312594510614872,
      "eval_runtime": 137.3683,
      "eval_samples_per_second": 2.883,
      "eval_steps_per_second": 0.364,
      "step": 54
    },
    {
      "epoch": 0.11702127659574468,
      "grad_norm": 0.2447483092546463,
      "learning_rate": 5e-05,
      "loss": 0.0567,
      "step": 55
    },
    {
      "epoch": 0.11914893617021277,
      "grad_norm": 0.32978394627571106,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.018,
      "step": 56
    },
    {
      "epoch": 0.12127659574468085,
      "grad_norm": 0.19853627681732178,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.0312,
      "step": 57
    },
    {
      "epoch": 0.12340425531914893,
      "grad_norm": 0.17412202060222626,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0432,
      "step": 58
    },
    {
      "epoch": 0.125531914893617,
      "grad_norm": 0.12538942694664001,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.02,
      "step": 59
    },
    {
      "epoch": 0.1276595744680851,
      "grad_norm": 0.184116929769516,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0261,
      "step": 60
    },
    {
      "epoch": 0.12978723404255318,
      "grad_norm": 0.20825651288032532,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.0487,
      "step": 61
    },
    {
      "epoch": 0.13191489361702127,
      "grad_norm": 0.23447850346565247,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0424,
      "step": 62
    },
    {
      "epoch": 0.13404255319148936,
      "grad_norm": 0.3336513340473175,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.0973,
      "step": 63
    },
    {
      "epoch": 0.13404255319148936,
      "eval_loss": 0.02362966351211071,
      "eval_runtime": 137.1904,
      "eval_samples_per_second": 2.886,
      "eval_steps_per_second": 0.364,
      "step": 63
    },
    {
      "epoch": 0.13617021276595745,
      "grad_norm": 0.18834097683429718,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0442,
      "step": 64
    },
    {
      "epoch": 0.13829787234042554,
      "grad_norm": 0.11435489356517792,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0251,
      "step": 65
    },
    {
      "epoch": 0.14042553191489363,
      "grad_norm": 0.16500040888786316,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0479,
      "step": 66
    },
    {
      "epoch": 0.1425531914893617,
      "grad_norm": 0.18839475512504578,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.05,
      "step": 67
    },
    {
      "epoch": 0.14468085106382977,
      "grad_norm": 0.18193626403808594,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.027,
      "step": 68
    },
    {
      "epoch": 0.14680851063829786,
      "grad_norm": 0.2267770916223526,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.0946,
      "step": 69
    },
    {
      "epoch": 0.14893617021276595,
      "grad_norm": 0.1924557089805603,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0699,
      "step": 70
    },
    {
      "epoch": 0.15106382978723404,
      "grad_norm": 0.14939941465854645,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0233,
      "step": 71
    },
    {
      "epoch": 0.15319148936170213,
      "grad_norm": 0.1674216091632843,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0439,
      "step": 72
    },
    {
      "epoch": 0.15319148936170213,
      "eval_loss": 0.018976736813783646,
      "eval_runtime": 137.2066,
      "eval_samples_per_second": 2.886,
      "eval_steps_per_second": 0.364,
      "step": 72
    },
    {
      "epoch": 0.15531914893617021,
      "grad_norm": 0.16422490775585175,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0626,
      "step": 73
    },
    {
      "epoch": 0.1574468085106383,
      "grad_norm": 0.16370365023612976,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0269,
      "step": 74
    },
    {
      "epoch": 0.1595744680851064,
      "grad_norm": 0.18531498312950134,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0403,
      "step": 75
    },
    {
      "epoch": 0.16170212765957448,
      "grad_norm": 0.2003021091222763,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0533,
      "step": 76
    },
    {
      "epoch": 0.16382978723404254,
      "grad_norm": 0.12371911853551865,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.0258,
      "step": 77
    },
    {
      "epoch": 0.16595744680851063,
      "grad_norm": 0.17193201184272766,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.03,
      "step": 78
    },
    {
      "epoch": 0.16808510638297872,
      "grad_norm": 0.2122802734375,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.0446,
      "step": 79
    },
    {
      "epoch": 0.1702127659574468,
      "grad_norm": 0.17824585735797882,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0516,
      "step": 80
    },
    {
      "epoch": 0.1723404255319149,
      "grad_norm": 0.10696157068014145,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0105,
      "step": 81
    },
    {
      "epoch": 0.1723404255319149,
      "eval_loss": 0.016418613493442535,
      "eval_runtime": 137.3662,
      "eval_samples_per_second": 2.883,
      "eval_steps_per_second": 0.364,
      "step": 81
    },
    {
      "epoch": 0.17446808510638298,
      "grad_norm": 0.19411924481391907,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0412,
      "step": 82
    },
    {
      "epoch": 0.17659574468085107,
      "grad_norm": 0.15288114547729492,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.0347,
      "step": 83
    },
    {
      "epoch": 0.17872340425531916,
      "grad_norm": 0.13765448331832886,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0298,
      "step": 84
    },
    {
      "epoch": 0.18085106382978725,
      "grad_norm": 0.2824060320854187,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0797,
      "step": 85
    },
    {
      "epoch": 0.1829787234042553,
      "grad_norm": 0.15786072611808777,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0406,
      "step": 86
    },
    {
      "epoch": 0.1851063829787234,
      "grad_norm": 0.12804144620895386,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.0286,
      "step": 87
    },
    {
      "epoch": 0.18723404255319148,
      "grad_norm": 0.16002494096755981,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0166,
      "step": 88
    },
    {
      "epoch": 0.18936170212765957,
      "grad_norm": 0.17278890311717987,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.0615,
      "step": 89
    },
    {
      "epoch": 0.19148936170212766,
      "grad_norm": 0.12740778923034668,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0259,
      "step": 90
    },
    {
      "epoch": 0.19148936170212766,
      "eval_loss": 0.015345096588134766,
      "eval_runtime": 137.224,
      "eval_samples_per_second": 2.886,
      "eval_steps_per_second": 0.364,
      "step": 90
    },
    {
      "epoch": 0.19361702127659575,
      "grad_norm": 0.10843079537153244,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0235,
      "step": 91
    },
    {
      "epoch": 0.19574468085106383,
      "grad_norm": 0.11718861013650894,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.0224,
      "step": 92
    },
    {
      "epoch": 0.19787234042553192,
      "grad_norm": 0.19033397734165192,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.0543,
      "step": 93
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.17855358123779297,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0734,
      "step": 94
    },
    {
      "epoch": 0.20212765957446807,
      "grad_norm": 0.16578811407089233,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0443,
      "step": 95
    },
    {
      "epoch": 0.20425531914893616,
      "grad_norm": 0.10047528892755508,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0116,
      "step": 96
    },
    {
      "epoch": 0.20638297872340425,
      "grad_norm": 0.1590314358472824,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.031,
      "step": 97
    },
    {
      "epoch": 0.20851063829787234,
      "grad_norm": 0.12019843608140945,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0363,
      "step": 98
    },
    {
      "epoch": 0.21063829787234042,
      "grad_norm": 0.19698375463485718,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0541,
      "step": 99
    },
    {
      "epoch": 0.21063829787234042,
      "eval_loss": 0.01515384390950203,
      "eval_runtime": 137.3473,
      "eval_samples_per_second": 2.883,
      "eval_steps_per_second": 0.364,
      "step": 99
    },
    {
      "epoch": 0.2127659574468085,
      "grad_norm": 0.09224493056535721,
      "learning_rate": 0.0,
      "loss": 0.007,
      "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": 1.306929288708096e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}