{
  "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": 0.24358688294887543,
      "learning_rate": 1e-05,
      "loss": 10.4025,
      "step": 1
    },
    {
      "epoch": 0.007042253521126761,
      "eval_loss": 10.4074068069458,
      "eval_runtime": 0.4854,
      "eval_samples_per_second": 247.211,
      "eval_steps_per_second": 30.901,
      "step": 1
    },
    {
      "epoch": 0.014084507042253521,
      "grad_norm": 0.2351454645395279,
      "learning_rate": 2e-05,
      "loss": 10.4117,
      "step": 2
    },
    {
      "epoch": 0.02112676056338028,
      "grad_norm": 0.30535173416137695,
      "learning_rate": 3e-05,
      "loss": 10.3996,
      "step": 3
    },
    {
      "epoch": 0.028169014084507043,
      "grad_norm": 0.23860140144824982,
      "learning_rate": 4e-05,
      "loss": 10.4045,
      "step": 4
    },
    {
      "epoch": 0.035211267605633804,
      "grad_norm": 0.2526613175868988,
      "learning_rate": 5e-05,
      "loss": 10.3959,
      "step": 5
    },
    {
      "epoch": 0.04225352112676056,
      "grad_norm": 0.2759585678577423,
      "learning_rate": 6e-05,
      "loss": 10.4051,
      "step": 6
    },
    {
      "epoch": 0.04929577464788732,
      "grad_norm": 0.2518301010131836,
      "learning_rate": 7e-05,
      "loss": 10.3997,
      "step": 7
    },
    {
      "epoch": 0.056338028169014086,
      "grad_norm": 0.22514945268630981,
      "learning_rate": 8e-05,
      "loss": 10.4257,
      "step": 8
    },
    {
      "epoch": 0.06338028169014084,
      "grad_norm": 0.21962642669677734,
      "learning_rate": 9e-05,
      "loss": 10.4042,
      "step": 9
    },
    {
      "epoch": 0.06338028169014084,
      "eval_loss": 10.404335975646973,
      "eval_runtime": 0.4998,
      "eval_samples_per_second": 240.074,
      "eval_steps_per_second": 30.009,
      "step": 9
    },
    {
      "epoch": 0.07042253521126761,
      "grad_norm": 0.22805790603160858,
      "learning_rate": 0.0001,
      "loss": 10.4058,
      "step": 10
    },
    {
      "epoch": 0.07746478873239436,
      "grad_norm": 0.29901015758514404,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.3973,
      "step": 11
    },
    {
      "epoch": 0.08450704225352113,
      "grad_norm": 0.27135956287384033,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.3883,
      "step": 12
    },
    {
      "epoch": 0.09154929577464789,
      "grad_norm": 0.3067750036716461,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.401,
      "step": 13
    },
    {
      "epoch": 0.09859154929577464,
      "grad_norm": 0.2866221070289612,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.373,
      "step": 14
    },
    {
      "epoch": 0.1056338028169014,
      "grad_norm": 0.2563552260398865,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.3929,
      "step": 15
    },
    {
      "epoch": 0.11267605633802817,
      "grad_norm": 0.30029112100601196,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.3674,
      "step": 16
    },
    {
      "epoch": 0.11971830985915492,
      "grad_norm": 0.26711589097976685,
      "learning_rate": 9.851478631379982e-05,
      "loss": 10.4072,
      "step": 17
    },
    {
      "epoch": 0.1267605633802817,
      "grad_norm": 0.29278457164764404,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.3794,
      "step": 18
    },
    {
      "epoch": 0.1267605633802817,
      "eval_loss": 10.396374702453613,
      "eval_runtime": 0.4922,
      "eval_samples_per_second": 243.781,
      "eval_steps_per_second": 30.473,
      "step": 18
    },
    {
      "epoch": 0.13380281690140844,
      "grad_norm": 0.28824037313461304,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3705,
      "step": 19
    },
    {
      "epoch": 0.14084507042253522,
      "grad_norm": 0.247877836227417,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.4013,
      "step": 20
    },
    {
      "epoch": 0.14788732394366197,
      "grad_norm": 0.26219257712364197,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.3832,
      "step": 21
    },
    {
      "epoch": 0.15492957746478872,
      "grad_norm": 0.2339620590209961,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.3903,
      "step": 22
    },
    {
      "epoch": 0.1619718309859155,
      "grad_norm": 0.2921362817287445,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.3713,
      "step": 23
    },
    {
      "epoch": 0.16901408450704225,
      "grad_norm": 0.27569955587387085,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.4063,
      "step": 24
    },
    {
      "epoch": 0.176056338028169,
      "grad_norm": 0.2810605764389038,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.4172,
      "step": 25
    },
    {
      "epoch": 0.18309859154929578,
      "grad_norm": 0.2948496639728546,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.3812,
      "step": 26
    },
    {
      "epoch": 0.19014084507042253,
      "grad_norm": 0.29332059621810913,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.3708,
      "step": 27
    },
    {
      "epoch": 0.19014084507042253,
      "eval_loss": 10.388020515441895,
      "eval_runtime": 0.5108,
      "eval_samples_per_second": 234.929,
      "eval_steps_per_second": 29.366,
      "step": 27
    },
    {
      "epoch": 0.19718309859154928,
      "grad_norm": 0.28901439905166626,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3622,
      "step": 28
    },
    {
      "epoch": 0.20422535211267606,
      "grad_norm": 0.2676180303096771,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.3697,
      "step": 29
    },
    {
      "epoch": 0.2112676056338028,
      "grad_norm": 0.3027353584766388,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.3689,
      "step": 30
    },
    {
      "epoch": 0.21830985915492956,
      "grad_norm": 0.3184084892272949,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.3918,
      "step": 31
    },
    {
      "epoch": 0.22535211267605634,
      "grad_norm": 0.28535696864128113,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.3964,
      "step": 32
    },
    {
      "epoch": 0.2323943661971831,
      "grad_norm": 0.278022825717926,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.399,
      "step": 33
    },
    {
      "epoch": 0.23943661971830985,
      "grad_norm": 0.35305413603782654,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.3943,
      "step": 34
    },
    {
      "epoch": 0.24647887323943662,
      "grad_norm": 0.3135928213596344,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.3847,
      "step": 35
    },
    {
      "epoch": 0.2535211267605634,
      "grad_norm": 0.36001405119895935,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.3633,
      "step": 36
    },
    {
      "epoch": 0.2535211267605634,
      "eval_loss": 10.378849029541016,
      "eval_runtime": 0.5378,
      "eval_samples_per_second": 223.129,
      "eval_steps_per_second": 27.891,
      "step": 36
    },
    {
      "epoch": 0.2605633802816901,
      "grad_norm": 0.3195047676563263,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3732,
      "step": 37
    },
    {
      "epoch": 0.2676056338028169,
      "grad_norm": 0.293624609708786,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.3915,
      "step": 38
    },
    {
      "epoch": 0.2746478873239437,
      "grad_norm": 0.3025934100151062,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.3822,
      "step": 39
    },
    {
      "epoch": 0.28169014084507044,
      "grad_norm": 0.2917957901954651,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.4043,
      "step": 40
    },
    {
      "epoch": 0.2887323943661972,
      "grad_norm": 0.33415523171424866,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.3714,
      "step": 41
    },
    {
      "epoch": 0.29577464788732394,
      "grad_norm": 0.35728704929351807,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.3771,
      "step": 42
    },
    {
      "epoch": 0.3028169014084507,
      "grad_norm": 0.3928280472755432,
      "learning_rate": 7.033683215379002e-05,
      "loss": 10.3508,
      "step": 43
    },
    {
      "epoch": 0.30985915492957744,
      "grad_norm": 0.41211655735969543,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.3447,
      "step": 44
    },
    {
      "epoch": 0.31690140845070425,
      "grad_norm": 0.415772408246994,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.3459,
      "step": 45
    },
    {
      "epoch": 0.31690140845070425,
      "eval_loss": 10.36909294128418,
      "eval_runtime": 0.4934,
      "eval_samples_per_second": 243.209,
      "eval_steps_per_second": 30.401,
      "step": 45
    },
    {
      "epoch": 0.323943661971831,
      "grad_norm": 0.3777596056461334,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3796,
      "step": 46
    },
    {
      "epoch": 0.33098591549295775,
      "grad_norm": 0.43159905076026917,
      "learning_rate": 6.378186779084995e-05,
      "loss": 10.3739,
      "step": 47
    },
    {
      "epoch": 0.3380281690140845,
      "grad_norm": 0.38116705417633057,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.3504,
      "step": 48
    },
    {
      "epoch": 0.34507042253521125,
      "grad_norm": 0.379307359457016,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 10.3412,
      "step": 49
    },
    {
      "epoch": 0.352112676056338,
      "grad_norm": 0.34717878699302673,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.3554,
      "step": 50
    },
    {
      "epoch": 0.3591549295774648,
      "grad_norm": 0.34007278084754944,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.35,
      "step": 51
    },
    {
      "epoch": 0.36619718309859156,
      "grad_norm": 0.4468972384929657,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.3637,
      "step": 52
    },
    {
      "epoch": 0.3732394366197183,
      "grad_norm": 0.3781704902648926,
      "learning_rate": 5.348782368720626e-05,
      "loss": 10.3758,
      "step": 53
    },
    {
      "epoch": 0.38028169014084506,
      "grad_norm": 0.44845354557037354,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.3479,
      "step": 54
    },
    {
      "epoch": 0.38028169014084506,
      "eval_loss": 10.359603881835938,
      "eval_runtime": 0.504,
      "eval_samples_per_second": 238.083,
      "eval_steps_per_second": 29.76,
      "step": 54
    },
    {
      "epoch": 0.3873239436619718,
      "grad_norm": 0.38202252984046936,
      "learning_rate": 5e-05,
      "loss": 10.3515,
      "step": 55
    },
    {
      "epoch": 0.39436619718309857,
      "grad_norm": 0.43705958127975464,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.3376,
      "step": 56
    },
    {
      "epoch": 0.4014084507042254,
      "grad_norm": 0.4019726812839508,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.3409,
      "step": 57
    },
    {
      "epoch": 0.4084507042253521,
      "grad_norm": 0.41095566749572754,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.3169,
      "step": 58
    },
    {
      "epoch": 0.4154929577464789,
      "grad_norm": 0.402935653924942,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 10.3601,
      "step": 59
    },
    {
      "epoch": 0.4225352112676056,
      "grad_norm": 0.45852792263031006,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.3804,
      "step": 60
    },
    {
      "epoch": 0.4295774647887324,
      "grad_norm": 0.4683137536048889,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.373,
      "step": 61
    },
    {
      "epoch": 0.43661971830985913,
      "grad_norm": 0.47680333256721497,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.3482,
      "step": 62
    },
    {
      "epoch": 0.44366197183098594,
      "grad_norm": 0.4151249825954437,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.3576,
      "step": 63
    },
    {
      "epoch": 0.44366197183098594,
      "eval_loss": 10.351668357849121,
      "eval_runtime": 0.4911,
      "eval_samples_per_second": 244.326,
      "eval_steps_per_second": 30.541,
      "step": 63
    },
    {
      "epoch": 0.4507042253521127,
      "grad_norm": 0.3624146580696106,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.3636,
      "step": 64
    },
    {
      "epoch": 0.45774647887323944,
      "grad_norm": 0.47819146513938904,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.3438,
      "step": 65
    },
    {
      "epoch": 0.4647887323943662,
      "grad_norm": 0.3400690257549286,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.3488,
      "step": 66
    },
    {
      "epoch": 0.47183098591549294,
      "grad_norm": 0.4769725799560547,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 10.3423,
      "step": 67
    },
    {
      "epoch": 0.4788732394366197,
      "grad_norm": 0.3802928030490875,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.3375,
      "step": 68
    },
    {
      "epoch": 0.4859154929577465,
      "grad_norm": 0.374841570854187,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.3634,
      "step": 69
    },
    {
      "epoch": 0.49295774647887325,
      "grad_norm": 0.4511743187904358,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.3315,
      "step": 70
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.42619290947914124,
      "learning_rate": 2.350403678833976e-05,
      "loss": 10.3358,
      "step": 71
    },
    {
      "epoch": 0.5070422535211268,
      "grad_norm": 0.44817185401916504,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.3273,
      "step": 72
    },
    {
      "epoch": 0.5070422535211268,
      "eval_loss": 10.346145629882812,
      "eval_runtime": 0.499,
      "eval_samples_per_second": 240.461,
      "eval_steps_per_second": 30.058,
      "step": 72
    },
    {
      "epoch": 0.5140845070422535,
      "grad_norm": 0.4042167365550995,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3548,
      "step": 73
    },
    {
      "epoch": 0.5211267605633803,
      "grad_norm": 0.40181946754455566,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.3526,
      "step": 74
    },
    {
      "epoch": 0.528169014084507,
      "grad_norm": 0.45714980363845825,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.3526,
      "step": 75
    },
    {
      "epoch": 0.5352112676056338,
      "grad_norm": 0.48135364055633545,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 10.3316,
      "step": 76
    },
    {
      "epoch": 0.5422535211267606,
      "grad_norm": 0.44966384768486023,
      "learning_rate": 1.526708147705013e-05,
      "loss": 10.3226,
      "step": 77
    },
    {
      "epoch": 0.5492957746478874,
      "grad_norm": 0.4600827395915985,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.3408,
      "step": 78
    },
    {
      "epoch": 0.5563380281690141,
      "grad_norm": 0.4820798635482788,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 10.3488,
      "step": 79
    },
    {
      "epoch": 0.5633802816901409,
      "grad_norm": 0.45883482694625854,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.3127,
      "step": 80
    },
    {
      "epoch": 0.5704225352112676,
      "grad_norm": 0.4635918140411377,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 10.3243,
      "step": 81
    },
    {
      "epoch": 0.5704225352112676,
      "eval_loss": 10.342907905578613,
      "eval_runtime": 0.5248,
      "eval_samples_per_second": 228.655,
      "eval_steps_per_second": 28.582,
      "step": 81
    },
    {
      "epoch": 0.5774647887323944,
      "grad_norm": 0.5020090937614441,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.3671,
      "step": 82
    },
    {
      "epoch": 0.5845070422535211,
      "grad_norm": 0.571985125541687,
      "learning_rate": 8.548121372247918e-06,
      "loss": 10.3296,
      "step": 83
    },
    {
      "epoch": 0.5915492957746479,
      "grad_norm": 0.41995105147361755,
      "learning_rate": 7.597595192178702e-06,
      "loss": 10.3415,
      "step": 84
    },
    {
      "epoch": 0.5985915492957746,
      "grad_norm": 0.475591778755188,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.3001,
      "step": 85
    },
    {
      "epoch": 0.6056338028169014,
      "grad_norm": 0.4260372221469879,
      "learning_rate": 5.852620357053651e-06,
      "loss": 10.3346,
      "step": 86
    },
    {
      "epoch": 0.6126760563380281,
      "grad_norm": 0.48487669229507446,
      "learning_rate": 5.060297685041659e-06,
      "loss": 10.3202,
      "step": 87
    },
    {
      "epoch": 0.6197183098591549,
      "grad_norm": 0.5162070393562317,
      "learning_rate": 4.322727117869951e-06,
      "loss": 10.3107,
      "step": 88
    },
    {
      "epoch": 0.6267605633802817,
      "grad_norm": 0.5247275233268738,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 10.3445,
      "step": 89
    },
    {
      "epoch": 0.6338028169014085,
      "grad_norm": 0.4642081558704376,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.3393,
      "step": 90
    },
    {
      "epoch": 0.6338028169014085,
      "eval_loss": 10.34151554107666,
      "eval_runtime": 0.5021,
      "eval_samples_per_second": 239.0,
      "eval_steps_per_second": 29.875,
      "step": 90
    },
    {
      "epoch": 0.6408450704225352,
      "grad_norm": 0.452671080827713,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.3266,
      "step": 91
    },
    {
      "epoch": 0.647887323943662,
      "grad_norm": 0.41254308819770813,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 10.3512,
      "step": 92
    },
    {
      "epoch": 0.6549295774647887,
      "grad_norm": 0.3993806838989258,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 10.3397,
      "step": 93
    },
    {
      "epoch": 0.6619718309859155,
      "grad_norm": 0.46821779012680054,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.3482,
      "step": 94
    },
    {
      "epoch": 0.6690140845070423,
      "grad_norm": 0.5118176937103271,
      "learning_rate": 7.596123493895991e-07,
      "loss": 10.3231,
      "step": 95
    },
    {
      "epoch": 0.676056338028169,
      "grad_norm": 0.46694812178611755,
      "learning_rate": 4.865965629214819e-07,
      "loss": 10.3398,
      "step": 96
    },
    {
      "epoch": 0.6830985915492958,
      "grad_norm": 0.44762948155403137,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 10.3289,
      "step": 97
    },
    {
      "epoch": 0.6901408450704225,
      "grad_norm": 0.49409934878349304,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 10.3326,
      "step": 98
    },
    {
      "epoch": 0.6971830985915493,
      "grad_norm": 0.3911196291446686,
      "learning_rate": 3.04586490452119e-08,
      "loss": 10.3373,
      "step": 99
    },
    {
      "epoch": 0.6971830985915493,
      "eval_loss": 10.341242790222168,
      "eval_runtime": 0.4937,
      "eval_samples_per_second": 243.083,
      "eval_steps_per_second": 30.385,
      "step": 99
    },
    {
      "epoch": 0.704225352112676,
      "grad_norm": 0.4704214632511139,
      "learning_rate": 0.0,
      "loss": 10.3267,
      "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
}