{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.704225352112676,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007042253521126761,
      "grad_norm": 0.2323959767818451,
      "learning_rate": 1e-05,
      "loss": 10.4025,
      "step": 1
    },
    {
      "epoch": 0.007042253521126761,
      "eval_loss": 10.4074068069458,
      "eval_runtime": 0.4092,
      "eval_samples_per_second": 293.259,
      "eval_steps_per_second": 36.657,
      "step": 1
    },
    {
      "epoch": 0.014084507042253521,
      "grad_norm": 0.22009187936782837,
      "learning_rate": 2e-05,
      "loss": 10.4117,
      "step": 2
    },
    {
      "epoch": 0.02112676056338028,
      "grad_norm": 0.28439924120903015,
      "learning_rate": 3e-05,
      "loss": 10.3996,
      "step": 3
    },
    {
      "epoch": 0.028169014084507043,
      "grad_norm": 0.22647292912006378,
      "learning_rate": 4e-05,
      "loss": 10.4045,
      "step": 4
    },
    {
      "epoch": 0.035211267605633804,
      "grad_norm": 0.24614427983760834,
      "learning_rate": 5e-05,
      "loss": 10.396,
      "step": 5
    },
    {
      "epoch": 0.04225352112676056,
      "grad_norm": 0.24559475481510162,
      "learning_rate": 6e-05,
      "loss": 10.4052,
      "step": 6
    },
    {
      "epoch": 0.04929577464788732,
      "grad_norm": 0.243381068110466,
      "learning_rate": 7e-05,
      "loss": 10.3998,
      "step": 7
    },
    {
      "epoch": 0.056338028169014086,
      "grad_norm": 0.20445404946804047,
      "learning_rate": 8e-05,
      "loss": 10.4258,
      "step": 8
    },
    {
      "epoch": 0.06338028169014084,
      "grad_norm": 0.21230469644069672,
      "learning_rate": 9e-05,
      "loss": 10.4042,
      "step": 9
    },
    {
      "epoch": 0.06338028169014084,
      "eval_loss": 10.404547691345215,
      "eval_runtime": 0.4057,
      "eval_samples_per_second": 295.779,
      "eval_steps_per_second": 36.972,
      "step": 9
    },
    {
      "epoch": 0.07042253521126761,
      "grad_norm": 0.21898922324180603,
      "learning_rate": 0.0001,
      "loss": 10.4059,
      "step": 10
    },
    {
      "epoch": 0.07746478873239436,
      "grad_norm": 0.28304916620254517,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.3976,
      "step": 11
    },
    {
      "epoch": 0.08450704225352113,
      "grad_norm": 0.251845121383667,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.3886,
      "step": 12
    },
    {
      "epoch": 0.09154929577464789,
      "grad_norm": 0.2951556444168091,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.4012,
      "step": 13
    },
    {
      "epoch": 0.09859154929577464,
      "grad_norm": 0.25943925976753235,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.3734,
      "step": 14
    },
    {
      "epoch": 0.1056338028169014,
      "grad_norm": 0.2504953145980835,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.3932,
      "step": 15
    },
    {
      "epoch": 0.11267605633802817,
      "grad_norm": 0.2876141369342804,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.3677,
      "step": 16
    },
    {
      "epoch": 0.11971830985915492,
      "grad_norm": 0.2639096975326538,
      "learning_rate": 9.851478631379982e-05,
      "loss": 10.4076,
      "step": 17
    },
    {
      "epoch": 0.1267605633802817,
      "grad_norm": 0.2762654423713684,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.38,
      "step": 18
    },
    {
      "epoch": 0.1267605633802817,
      "eval_loss": 10.396947860717773,
      "eval_runtime": 0.4054,
      "eval_samples_per_second": 295.99,
      "eval_steps_per_second": 36.999,
      "step": 18
    },
    {
      "epoch": 0.13380281690140844,
      "grad_norm": 0.27750322222709656,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3711,
      "step": 19
    },
    {
      "epoch": 0.14084507042253522,
      "grad_norm": 0.2428402602672577,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.4018,
      "step": 20
    },
    {
      "epoch": 0.14788732394366197,
      "grad_norm": 0.2354544997215271,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.3841,
      "step": 21
    },
    {
      "epoch": 0.15492957746478872,
      "grad_norm": 0.22789806127548218,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.3909,
      "step": 22
    },
    {
      "epoch": 0.1619718309859155,
      "grad_norm": 0.28308409452438354,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.3719,
      "step": 23
    },
    {
      "epoch": 0.16901408450704225,
      "grad_norm": 0.27414482831954956,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.4069,
      "step": 24
    },
    {
      "epoch": 0.176056338028169,
      "grad_norm": 0.2813173234462738,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.4178,
      "step": 25
    },
    {
      "epoch": 0.18309859154929578,
      "grad_norm": 0.2852443754673004,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.382,
      "step": 26
    },
    {
      "epoch": 0.19014084507042253,
      "grad_norm": 0.2790205180644989,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.3718,
      "step": 27
    },
    {
      "epoch": 0.19014084507042253,
      "eval_loss": 10.388708114624023,
      "eval_runtime": 0.4204,
      "eval_samples_per_second": 285.456,
      "eval_steps_per_second": 35.682,
      "step": 27
    },
    {
      "epoch": 0.19718309859154928,
      "grad_norm": 0.27786052227020264,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3631,
      "step": 28
    },
    {
      "epoch": 0.20422535211267606,
      "grad_norm": 0.2572324573993683,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.3705,
      "step": 29
    },
    {
      "epoch": 0.2112676056338028,
      "grad_norm": 0.29625269770622253,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.3695,
      "step": 30
    },
    {
      "epoch": 0.21830985915492956,
      "grad_norm": 0.31954002380371094,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.3925,
      "step": 31
    },
    {
      "epoch": 0.22535211267605634,
      "grad_norm": 0.2882094383239746,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.3968,
      "step": 32
    },
    {
      "epoch": 0.2323943661971831,
      "grad_norm": 0.2751225233078003,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.3999,
      "step": 33
    },
    {
      "epoch": 0.23943661971830985,
      "grad_norm": 0.340969443321228,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.396,
      "step": 34
    },
    {
      "epoch": 0.24647887323943662,
      "grad_norm": 0.31005537509918213,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.3853,
      "step": 35
    },
    {
      "epoch": 0.2535211267605634,
      "grad_norm": 0.3454052805900574,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.3648,
      "step": 36
    },
    {
      "epoch": 0.2535211267605634,
      "eval_loss": 10.379645347595215,
      "eval_runtime": 0.4068,
      "eval_samples_per_second": 295.012,
      "eval_steps_per_second": 36.877,
      "step": 36
    },
    {
      "epoch": 0.2605633802816901,
      "grad_norm": 0.3282582461833954,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3728,
      "step": 37
    },
    {
      "epoch": 0.2676056338028169,
      "grad_norm": 0.2983498275279999,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.3918,
      "step": 38
    },
    {
      "epoch": 0.2746478873239437,
      "grad_norm": 0.2939716577529907,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.3832,
      "step": 39
    },
    {
      "epoch": 0.28169014084507044,
      "grad_norm": 0.29452258348464966,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.405,
      "step": 40
    },
    {
      "epoch": 0.2887323943661972,
      "grad_norm": 0.33873146772384644,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.3717,
      "step": 41
    },
    {
      "epoch": 0.29577464788732394,
      "grad_norm": 0.35908937454223633,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.377,
      "step": 42
    },
    {
      "epoch": 0.3028169014084507,
      "grad_norm": 0.39580103754997253,
      "learning_rate": 7.033683215379002e-05,
      "loss": 10.351,
      "step": 43
    },
    {
      "epoch": 0.30985915492957744,
      "grad_norm": 0.401178777217865,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.3459,
      "step": 44
    },
    {
      "epoch": 0.31690140845070425,
      "grad_norm": 0.4038810133934021,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.3481,
      "step": 45
    },
    {
      "epoch": 0.31690140845070425,
      "eval_loss": 10.369983673095703,
      "eval_runtime": 0.414,
      "eval_samples_per_second": 289.854,
      "eval_steps_per_second": 36.232,
      "step": 45
    },
    {
      "epoch": 0.323943661971831,
      "grad_norm": 0.37503623962402344,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3812,
      "step": 46
    },
    {
      "epoch": 0.33098591549295775,
      "grad_norm": 0.426323264837265,
      "learning_rate": 6.378186779084995e-05,
      "loss": 10.3761,
      "step": 47
    },
    {
      "epoch": 0.3380281690140845,
      "grad_norm": 0.37719449400901794,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.3515,
      "step": 48
    },
    {
      "epoch": 0.34507042253521125,
      "grad_norm": 0.3680926561355591,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 10.343,
      "step": 49
    },
    {
      "epoch": 0.352112676056338,
      "grad_norm": 0.3452039957046509,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.3559,
      "step": 50
    },
    {
      "epoch": 0.3591549295774648,
      "grad_norm": 0.33691930770874023,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.3518,
      "step": 51
    },
    {
      "epoch": 0.36619718309859156,
      "grad_norm": 0.4393768608570099,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.3666,
      "step": 52
    },
    {
      "epoch": 0.3732394366197183,
      "grad_norm": 0.42232954502105713,
      "learning_rate": 5.348782368720626e-05,
      "loss": 10.3746,
      "step": 53
    },
    {
      "epoch": 0.38028169014084506,
      "grad_norm": 0.43516579270362854,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.3505,
      "step": 54
    },
    {
      "epoch": 0.38028169014084506,
      "eval_loss": 10.360475540161133,
      "eval_runtime": 0.4151,
      "eval_samples_per_second": 289.056,
      "eval_steps_per_second": 36.132,
      "step": 54
    },
    {
      "epoch": 0.3873239436619718,
      "grad_norm": 0.3640041947364807,
      "learning_rate": 5e-05,
      "loss": 10.3532,
      "step": 55
    },
    {
      "epoch": 0.39436619718309857,
      "grad_norm": 0.4502539336681366,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.3388,
      "step": 56
    },
    {
      "epoch": 0.4014084507042254,
      "grad_norm": 0.40651506185531616,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.3417,
      "step": 57
    },
    {
      "epoch": 0.4084507042253521,
      "grad_norm": 0.3992672860622406,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.3183,
      "step": 58
    },
    {
      "epoch": 0.4154929577464789,
      "grad_norm": 0.4093829095363617,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 10.3617,
      "step": 59
    },
    {
      "epoch": 0.4225352112676056,
      "grad_norm": 0.4767419397830963,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.3806,
      "step": 60
    },
    {
      "epoch": 0.4295774647887324,
      "grad_norm": 0.463030606508255,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.3756,
      "step": 61
    },
    {
      "epoch": 0.43661971830985913,
      "grad_norm": 0.49670639634132385,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.3488,
      "step": 62
    },
    {
      "epoch": 0.44366197183098594,
      "grad_norm": 0.4131371080875397,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.3594,
      "step": 63
    },
    {
      "epoch": 0.44366197183098594,
      "eval_loss": 10.352477073669434,
      "eval_runtime": 0.4055,
      "eval_samples_per_second": 295.956,
      "eval_steps_per_second": 36.994,
      "step": 63
    },
    {
      "epoch": 0.4507042253521127,
      "grad_norm": 0.37016379833221436,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.3651,
      "step": 64
    },
    {
      "epoch": 0.45774647887323944,
      "grad_norm": 0.4693770408630371,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.3473,
      "step": 65
    },
    {
      "epoch": 0.4647887323943662,
      "grad_norm": 0.34537220001220703,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.3488,
      "step": 66
    },
    {
      "epoch": 0.47183098591549294,
      "grad_norm": 0.48998722434043884,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 10.3422,
      "step": 67
    },
    {
      "epoch": 0.4788732394366197,
      "grad_norm": 0.3674013912677765,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.34,
      "step": 68
    },
    {
      "epoch": 0.4859154929577465,
      "grad_norm": 0.38952964544296265,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.3635,
      "step": 69
    },
    {
      "epoch": 0.49295774647887325,
      "grad_norm": 0.4728361666202545,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.3293,
      "step": 70
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.4525172710418701,
      "learning_rate": 2.350403678833976e-05,
      "loss": 10.3354,
      "step": 71
    },
    {
      "epoch": 0.5070422535211268,
      "grad_norm": 0.4703201353549957,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.3275,
      "step": 72
    },
    {
      "epoch": 0.5070422535211268,
      "eval_loss": 10.34687328338623,
      "eval_runtime": 0.4256,
      "eval_samples_per_second": 281.966,
      "eval_steps_per_second": 35.246,
      "step": 72
    },
    {
      "epoch": 0.5140845070422535,
      "grad_norm": 0.4370110332965851,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3539,
      "step": 73
    },
    {
      "epoch": 0.5211267605633803,
      "grad_norm": 0.4113081693649292,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.3532,
      "step": 74
    },
    {
      "epoch": 0.528169014084507,
      "grad_norm": 0.4943798780441284,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.3506,
      "step": 75
    },
    {
      "epoch": 0.5352112676056338,
      "grad_norm": 0.4924846887588501,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 10.3339,
      "step": 76
    },
    {
      "epoch": 0.5422535211267606,
      "grad_norm": 0.433089017868042,
      "learning_rate": 1.526708147705013e-05,
      "loss": 10.326,
      "step": 77
    },
    {
      "epoch": 0.5492957746478874,
      "grad_norm": 0.47787341475486755,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.3411,
      "step": 78
    },
    {
      "epoch": 0.5563380281690141,
      "grad_norm": 0.4763740599155426,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 10.3519,
      "step": 79
    },
    {
      "epoch": 0.5633802816901409,
      "grad_norm": 0.4627920985221863,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.3142,
      "step": 80
    },
    {
      "epoch": 0.5704225352112676,
      "grad_norm": 0.45368728041648865,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 10.329,
      "step": 81
    },
    {
      "epoch": 0.5704225352112676,
      "eval_loss": 10.343488693237305,
      "eval_runtime": 0.4128,
      "eval_samples_per_second": 290.723,
      "eval_steps_per_second": 36.34,
      "step": 81
    },
    {
      "epoch": 0.5774647887323944,
      "grad_norm": 0.5440958142280579,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.3666,
      "step": 82
    },
    {
      "epoch": 0.5845070422535211,
      "grad_norm": 0.5889712572097778,
      "learning_rate": 8.548121372247918e-06,
      "loss": 10.33,
      "step": 83
    },
    {
      "epoch": 0.5915492957746479,
      "grad_norm": 0.44246238470077515,
      "learning_rate": 7.597595192178702e-06,
      "loss": 10.3423,
      "step": 84
    },
    {
      "epoch": 0.5985915492957746,
      "grad_norm": 0.4974898099899292,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.2996,
      "step": 85
    },
    {
      "epoch": 0.6056338028169014,
      "grad_norm": 0.44511786103248596,
      "learning_rate": 5.852620357053651e-06,
      "loss": 10.3347,
      "step": 86
    },
    {
      "epoch": 0.6126760563380281,
      "grad_norm": 0.49932533502578735,
      "learning_rate": 5.060297685041659e-06,
      "loss": 10.3229,
      "step": 87
    },
    {
      "epoch": 0.6197183098591549,
      "grad_norm": 0.5125223398208618,
      "learning_rate": 4.322727117869951e-06,
      "loss": 10.3135,
      "step": 88
    },
    {
      "epoch": 0.6267605633802817,
      "grad_norm": 0.5311346054077148,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 10.3467,
      "step": 89
    },
    {
      "epoch": 0.6338028169014085,
      "grad_norm": 0.47513583302497864,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.3413,
      "step": 90
    },
    {
      "epoch": 0.6338028169014085,
      "eval_loss": 10.342093467712402,
      "eval_runtime": 0.4072,
      "eval_samples_per_second": 294.689,
      "eval_steps_per_second": 36.836,
      "step": 90
    },
    {
      "epoch": 0.6408450704225352,
      "grad_norm": 0.4879860281944275,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.3247,
      "step": 91
    },
    {
      "epoch": 0.647887323943662,
      "grad_norm": 0.4435056746006012,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 10.3496,
      "step": 92
    },
    {
      "epoch": 0.6549295774647887,
      "grad_norm": 0.4078325629234314,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 10.3403,
      "step": 93
    },
    {
      "epoch": 0.6619718309859155,
      "grad_norm": 0.4901764988899231,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.3486,
      "step": 94
    },
    {
      "epoch": 0.6690140845070423,
      "grad_norm": 0.5062358975410461,
      "learning_rate": 7.596123493895991e-07,
      "loss": 10.3274,
      "step": 95
    },
    {
      "epoch": 0.676056338028169,
      "grad_norm": 0.4807267189025879,
      "learning_rate": 4.865965629214819e-07,
      "loss": 10.3403,
      "step": 96
    },
    {
      "epoch": 0.6830985915492958,
      "grad_norm": 0.4300658106803894,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 10.3333,
      "step": 97
    },
    {
      "epoch": 0.6901408450704225,
      "grad_norm": 0.49888625741004944,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 10.3342,
      "step": 98
    },
    {
      "epoch": 0.6971830985915493,
      "grad_norm": 0.42185673117637634,
      "learning_rate": 3.04586490452119e-08,
      "loss": 10.3364,
      "step": 99
    },
    {
      "epoch": 0.6971830985915493,
      "eval_loss": 10.341872215270996,
      "eval_runtime": 0.4363,
      "eval_samples_per_second": 275.027,
      "eval_steps_per_second": 34.378,
      "step": 99
    },
    {
      "epoch": 0.704225352112676,
      "grad_norm": 0.4972395896911621,
      "learning_rate": 0.0,
      "loss": 10.3264,
      "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": 5230244659200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}