{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9345794392523364,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009345794392523364,
      "grad_norm": 0.050634294748306274,
      "learning_rate": 1e-05,
      "loss": 10.3752,
      "step": 1
    },
    {
      "epoch": 0.009345794392523364,
      "eval_loss": 10.376474380493164,
      "eval_runtime": 0.2593,
      "eval_samples_per_second": 347.077,
      "eval_steps_per_second": 46.277,
      "step": 1
    },
    {
      "epoch": 0.018691588785046728,
      "grad_norm": 0.03872130811214447,
      "learning_rate": 2e-05,
      "loss": 10.3748,
      "step": 2
    },
    {
      "epoch": 0.028037383177570093,
      "grad_norm": 0.045502543449401855,
      "learning_rate": 3e-05,
      "loss": 10.3763,
      "step": 3
    },
    {
      "epoch": 0.037383177570093455,
      "grad_norm": 0.052466411143541336,
      "learning_rate": 4e-05,
      "loss": 10.3786,
      "step": 4
    },
    {
      "epoch": 0.04672897196261682,
      "grad_norm": 0.04888991639018059,
      "learning_rate": 5e-05,
      "loss": 10.3764,
      "step": 5
    },
    {
      "epoch": 0.056074766355140186,
      "grad_norm": 0.04502081498503685,
      "learning_rate": 6e-05,
      "loss": 10.379,
      "step": 6
    },
    {
      "epoch": 0.06542056074766354,
      "grad_norm": 0.03738797828555107,
      "learning_rate": 7e-05,
      "loss": 10.3764,
      "step": 7
    },
    {
      "epoch": 0.07476635514018691,
      "grad_norm": 0.049519024789333344,
      "learning_rate": 8e-05,
      "loss": 10.3781,
      "step": 8
    },
    {
      "epoch": 0.08411214953271028,
      "grad_norm": 0.04312705248594284,
      "learning_rate": 9e-05,
      "loss": 10.3749,
      "step": 9
    },
    {
      "epoch": 0.08411214953271028,
      "eval_loss": 10.376031875610352,
      "eval_runtime": 0.2876,
      "eval_samples_per_second": 312.894,
      "eval_steps_per_second": 41.719,
      "step": 9
    },
    {
      "epoch": 0.09345794392523364,
      "grad_norm": 0.045628100633621216,
      "learning_rate": 0.0001,
      "loss": 10.3764,
      "step": 10
    },
    {
      "epoch": 0.102803738317757,
      "grad_norm": 0.05476449057459831,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.3745,
      "step": 11
    },
    {
      "epoch": 0.11214953271028037,
      "grad_norm": 0.055228810757398605,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.3736,
      "step": 12
    },
    {
      "epoch": 0.12149532710280374,
      "grad_norm": 0.0499500147998333,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.3741,
      "step": 13
    },
    {
      "epoch": 0.1308411214953271,
      "grad_norm": 0.05235056206583977,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.3751,
      "step": 14
    },
    {
      "epoch": 0.14018691588785046,
      "grad_norm": 0.04821014404296875,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.3755,
      "step": 15
    },
    {
      "epoch": 0.14953271028037382,
      "grad_norm": 0.041504986584186554,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.3758,
      "step": 16
    },
    {
      "epoch": 0.1588785046728972,
      "grad_norm": 0.04058471694588661,
      "learning_rate": 9.851478631379982e-05,
      "loss": 10.3735,
      "step": 17
    },
    {
      "epoch": 0.16822429906542055,
      "grad_norm": 0.04478996992111206,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.3761,
      "step": 18
    },
    {
      "epoch": 0.16822429906542055,
      "eval_loss": 10.374866485595703,
      "eval_runtime": 0.2881,
      "eval_samples_per_second": 312.39,
      "eval_steps_per_second": 41.652,
      "step": 18
    },
    {
      "epoch": 0.17757009345794392,
      "grad_norm": 0.04414283484220505,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3777,
      "step": 19
    },
    {
      "epoch": 0.18691588785046728,
      "grad_norm": 0.04838661104440689,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.3773,
      "step": 20
    },
    {
      "epoch": 0.19626168224299065,
      "grad_norm": 0.05458521470427513,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.3736,
      "step": 21
    },
    {
      "epoch": 0.205607476635514,
      "grad_norm": 0.048640232533216476,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.3745,
      "step": 22
    },
    {
      "epoch": 0.21495327102803738,
      "grad_norm": 0.06021261587738991,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.3743,
      "step": 23
    },
    {
      "epoch": 0.22429906542056074,
      "grad_norm": 0.04582176357507706,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.3751,
      "step": 24
    },
    {
      "epoch": 0.2336448598130841,
      "grad_norm": 0.056578073650598526,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3761,
      "step": 25
    },
    {
      "epoch": 0.24299065420560748,
      "grad_norm": 0.062350787222385406,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.3776,
      "step": 26
    },
    {
      "epoch": 0.2523364485981308,
      "grad_norm": 0.05235142260789871,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.3712,
      "step": 27
    },
    {
      "epoch": 0.2523364485981308,
      "eval_loss": 10.373592376708984,
      "eval_runtime": 0.2854,
      "eval_samples_per_second": 315.315,
      "eval_steps_per_second": 42.042,
      "step": 27
    },
    {
      "epoch": 0.2616822429906542,
      "grad_norm": 0.05420086532831192,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3731,
      "step": 28
    },
    {
      "epoch": 0.27102803738317754,
      "grad_norm": 0.045647576451301575,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.3714,
      "step": 29
    },
    {
      "epoch": 0.2803738317757009,
      "grad_norm": 0.055856239050626755,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.3732,
      "step": 30
    },
    {
      "epoch": 0.2897196261682243,
      "grad_norm": 0.05178695544600487,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.3725,
      "step": 31
    },
    {
      "epoch": 0.29906542056074764,
      "grad_norm": 0.058843404054641724,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.3714,
      "step": 32
    },
    {
      "epoch": 0.308411214953271,
      "grad_norm": 0.057961635291576385,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.3741,
      "step": 33
    },
    {
      "epoch": 0.3177570093457944,
      "grad_norm": 0.06160508096218109,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.3742,
      "step": 34
    },
    {
      "epoch": 0.32710280373831774,
      "grad_norm": 0.05896352231502533,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.3718,
      "step": 35
    },
    {
      "epoch": 0.3364485981308411,
      "grad_norm": 0.0637802854180336,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.3724,
      "step": 36
    },
    {
      "epoch": 0.3364485981308411,
      "eval_loss": 10.372211456298828,
      "eval_runtime": 0.3189,
      "eval_samples_per_second": 282.243,
      "eval_steps_per_second": 37.632,
      "step": 36
    },
    {
      "epoch": 0.34579439252336447,
      "grad_norm": 0.05186713859438896,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3712,
      "step": 37
    },
    {
      "epoch": 0.35514018691588783,
      "grad_norm": 0.07059617340564728,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.3717,
      "step": 38
    },
    {
      "epoch": 0.3644859813084112,
      "grad_norm": 0.06824015825986862,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.373,
      "step": 39
    },
    {
      "epoch": 0.37383177570093457,
      "grad_norm": 0.06879343092441559,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.373,
      "step": 40
    },
    {
      "epoch": 0.38317757009345793,
      "grad_norm": 0.056424371898174286,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.3732,
      "step": 41
    },
    {
      "epoch": 0.3925233644859813,
      "grad_norm": 0.06976228207349777,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.3698,
      "step": 42
    },
    {
      "epoch": 0.40186915887850466,
      "grad_norm": 0.05020787566900253,
      "learning_rate": 7.033683215379002e-05,
      "loss": 10.3732,
      "step": 43
    },
    {
      "epoch": 0.411214953271028,
      "grad_norm": 0.07235042005777359,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.3674,
      "step": 44
    },
    {
      "epoch": 0.4205607476635514,
      "grad_norm": 0.0736556425690651,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.3682,
      "step": 45
    },
    {
      "epoch": 0.4205607476635514,
      "eval_loss": 10.37077522277832,
      "eval_runtime": 0.313,
      "eval_samples_per_second": 287.579,
      "eval_steps_per_second": 38.344,
      "step": 45
    },
    {
      "epoch": 0.42990654205607476,
      "grad_norm": 0.07060671597719193,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3696,
      "step": 46
    },
    {
      "epoch": 0.4392523364485981,
      "grad_norm": 0.08394503593444824,
      "learning_rate": 6.378186779084995e-05,
      "loss": 10.369,
      "step": 47
    },
    {
      "epoch": 0.4485981308411215,
      "grad_norm": 0.07056224346160889,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.373,
      "step": 48
    },
    {
      "epoch": 0.45794392523364486,
      "grad_norm": 0.07340491563081741,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 10.3706,
      "step": 49
    },
    {
      "epoch": 0.4672897196261682,
      "grad_norm": 0.07283254712820053,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.3713,
      "step": 50
    },
    {
      "epoch": 0.4766355140186916,
      "grad_norm": 0.07640334218740463,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.3724,
      "step": 51
    },
    {
      "epoch": 0.48598130841121495,
      "grad_norm": 0.07294671982526779,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.371,
      "step": 52
    },
    {
      "epoch": 0.4953271028037383,
      "grad_norm": 0.06577962636947632,
      "learning_rate": 5.348782368720626e-05,
      "loss": 10.369,
      "step": 53
    },
    {
      "epoch": 0.5046728971962616,
      "grad_norm": 0.054112158715724945,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.3709,
      "step": 54
    },
    {
      "epoch": 0.5046728971962616,
      "eval_loss": 10.369393348693848,
      "eval_runtime": 0.2938,
      "eval_samples_per_second": 306.299,
      "eval_steps_per_second": 40.84,
      "step": 54
    },
    {
      "epoch": 0.514018691588785,
      "grad_norm": 0.07879622280597687,
      "learning_rate": 5e-05,
      "loss": 10.3698,
      "step": 55
    },
    {
      "epoch": 0.5233644859813084,
      "grad_norm": 0.07182235270738602,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.3707,
      "step": 56
    },
    {
      "epoch": 0.5327102803738317,
      "grad_norm": 0.0747784897685051,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.3705,
      "step": 57
    },
    {
      "epoch": 0.5420560747663551,
      "grad_norm": 0.0817614495754242,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.3691,
      "step": 58
    },
    {
      "epoch": 0.5514018691588785,
      "grad_norm": 0.09186830371618271,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 10.3674,
      "step": 59
    },
    {
      "epoch": 0.5607476635514018,
      "grad_norm": 0.08026149123907089,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.3697,
      "step": 60
    },
    {
      "epoch": 0.5700934579439252,
      "grad_norm": 0.07351516932249069,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.3726,
      "step": 61
    },
    {
      "epoch": 0.5794392523364486,
      "grad_norm": 0.060523565858602524,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.3726,
      "step": 62
    },
    {
      "epoch": 0.5887850467289719,
      "grad_norm": 0.09330922365188599,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.3672,
      "step": 63
    },
    {
      "epoch": 0.5887850467289719,
      "eval_loss": 10.36823558807373,
      "eval_runtime": 0.3289,
      "eval_samples_per_second": 273.649,
      "eval_steps_per_second": 36.486,
      "step": 63
    },
    {
      "epoch": 0.5981308411214953,
      "grad_norm": 0.05925269052386284,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.371,
      "step": 64
    },
    {
      "epoch": 0.6074766355140186,
      "grad_norm": 0.09052824229001999,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.3673,
      "step": 65
    },
    {
      "epoch": 0.616822429906542,
      "grad_norm": 0.07934991270303726,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.3671,
      "step": 66
    },
    {
      "epoch": 0.6261682242990654,
      "grad_norm": 0.09313682466745377,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 10.3702,
      "step": 67
    },
    {
      "epoch": 0.6355140186915887,
      "grad_norm": 0.09552256762981415,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.3684,
      "step": 68
    },
    {
      "epoch": 0.6448598130841121,
      "grad_norm": 0.08164523541927338,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.3668,
      "step": 69
    },
    {
      "epoch": 0.6542056074766355,
      "grad_norm": 0.08624476194381714,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.37,
      "step": 70
    },
    {
      "epoch": 0.6635514018691588,
      "grad_norm": 0.09074212610721588,
      "learning_rate": 2.350403678833976e-05,
      "loss": 10.371,
      "step": 71
    },
    {
      "epoch": 0.6728971962616822,
      "grad_norm": 0.07962147146463394,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.3705,
      "step": 72
    },
    {
      "epoch": 0.6728971962616822,
      "eval_loss": 10.36740779876709,
      "eval_runtime": 0.2917,
      "eval_samples_per_second": 308.573,
      "eval_steps_per_second": 41.143,
      "step": 72
    },
    {
      "epoch": 0.6822429906542056,
      "grad_norm": 0.08764558285474777,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3679,
      "step": 73
    },
    {
      "epoch": 0.6915887850467289,
      "grad_norm": 0.09333019703626633,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.3694,
      "step": 74
    },
    {
      "epoch": 0.7009345794392523,
      "grad_norm": 0.09206650406122208,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.3647,
      "step": 75
    },
    {
      "epoch": 0.7102803738317757,
      "grad_norm": 0.08344841003417969,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 10.3688,
      "step": 76
    },
    {
      "epoch": 0.719626168224299,
      "grad_norm": 0.09193700551986694,
      "learning_rate": 1.526708147705013e-05,
      "loss": 10.3698,
      "step": 77
    },
    {
      "epoch": 0.7289719626168224,
      "grad_norm": 0.09748734533786774,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.3678,
      "step": 78
    },
    {
      "epoch": 0.7383177570093458,
      "grad_norm": 0.08940058946609497,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 10.3659,
      "step": 79
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 0.08325794339179993,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.3641,
      "step": 80
    },
    {
      "epoch": 0.7570093457943925,
      "grad_norm": 0.08492863178253174,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 10.3654,
      "step": 81
    },
    {
      "epoch": 0.7570093457943925,
      "eval_loss": 10.366915702819824,
      "eval_runtime": 0.2998,
      "eval_samples_per_second": 300.207,
      "eval_steps_per_second": 40.028,
      "step": 81
    },
    {
      "epoch": 0.7663551401869159,
      "grad_norm": 0.06268931925296783,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.3717,
      "step": 82
    },
    {
      "epoch": 0.7757009345794392,
      "grad_norm": 0.08986851572990417,
      "learning_rate": 8.548121372247918e-06,
      "loss": 10.3669,
      "step": 83
    },
    {
      "epoch": 0.7850467289719626,
      "grad_norm": 0.08876341581344604,
      "learning_rate": 7.597595192178702e-06,
      "loss": 10.3672,
      "step": 84
    },
    {
      "epoch": 0.794392523364486,
      "grad_norm": 0.10019825398921967,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.3678,
      "step": 85
    },
    {
      "epoch": 0.8037383177570093,
      "grad_norm": 0.08450726419687271,
      "learning_rate": 5.852620357053651e-06,
      "loss": 10.3678,
      "step": 86
    },
    {
      "epoch": 0.8130841121495327,
      "grad_norm": 0.0758834034204483,
      "learning_rate": 5.060297685041659e-06,
      "loss": 10.3679,
      "step": 87
    },
    {
      "epoch": 0.822429906542056,
      "grad_norm": 0.0939643457531929,
      "learning_rate": 4.322727117869951e-06,
      "loss": 10.3673,
      "step": 88
    },
    {
      "epoch": 0.8317757009345794,
      "grad_norm": 0.07556302100419998,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 10.369,
      "step": 89
    },
    {
      "epoch": 0.8411214953271028,
      "grad_norm": 0.09754074364900589,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.3666,
      "step": 90
    },
    {
      "epoch": 0.8411214953271028,
      "eval_loss": 10.366714477539062,
      "eval_runtime": 0.2858,
      "eval_samples_per_second": 314.903,
      "eval_steps_per_second": 41.987,
      "step": 90
    },
    {
      "epoch": 0.8504672897196262,
      "grad_norm": 0.0869024321436882,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.3646,
      "step": 91
    },
    {
      "epoch": 0.8598130841121495,
      "grad_norm": 0.09132889658212662,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 10.3655,
      "step": 92
    },
    {
      "epoch": 0.8691588785046729,
      "grad_norm": 0.09490873664617538,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 10.3639,
      "step": 93
    },
    {
      "epoch": 0.8785046728971962,
      "grad_norm": 0.10507091134786606,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.3653,
      "step": 94
    },
    {
      "epoch": 0.8878504672897196,
      "grad_norm": 0.08295506238937378,
      "learning_rate": 7.596123493895991e-07,
      "loss": 10.3659,
      "step": 95
    },
    {
      "epoch": 0.897196261682243,
      "grad_norm": 0.10487104207277298,
      "learning_rate": 4.865965629214819e-07,
      "loss": 10.3678,
      "step": 96
    },
    {
      "epoch": 0.9065420560747663,
      "grad_norm": 0.10390753298997879,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 10.3661,
      "step": 97
    },
    {
      "epoch": 0.9158878504672897,
      "grad_norm": 0.09552055597305298,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 10.3639,
      "step": 98
    },
    {
      "epoch": 0.9252336448598131,
      "grad_norm": 0.09366817027330399,
      "learning_rate": 3.04586490452119e-08,
      "loss": 10.3666,
      "step": 99
    },
    {
      "epoch": 0.9252336448598131,
      "eval_loss": 10.366670608520508,
      "eval_runtime": 0.3019,
      "eval_samples_per_second": 298.072,
      "eval_steps_per_second": 39.743,
      "step": 99
    },
    {
      "epoch": 0.9345794392523364,
      "grad_norm": 0.09344561398029327,
      "learning_rate": 0.0,
      "loss": 10.3681,
      "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": 8237635338240.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}