{
  "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": 5.563784122467041,
      "learning_rate": 1e-05,
      "loss": 1.993,
      "step": 1
    },
    {
      "epoch": 0.009345794392523364,
      "eval_loss": 2.3873634338378906,
      "eval_runtime": 10.6609,
      "eval_samples_per_second": 8.442,
      "eval_steps_per_second": 1.126,
      "step": 1
    },
    {
      "epoch": 0.018691588785046728,
      "grad_norm": 5.337281227111816,
      "learning_rate": 2e-05,
      "loss": 1.876,
      "step": 2
    },
    {
      "epoch": 0.028037383177570093,
      "grad_norm": 7.325715065002441,
      "learning_rate": 3e-05,
      "loss": 2.7801,
      "step": 3
    },
    {
      "epoch": 0.037383177570093455,
      "grad_norm": 9.704561233520508,
      "learning_rate": 4e-05,
      "loss": 3.0626,
      "step": 4
    },
    {
      "epoch": 0.04672897196261682,
      "grad_norm": 8.029546737670898,
      "learning_rate": 5e-05,
      "loss": 2.2454,
      "step": 5
    },
    {
      "epoch": 0.056074766355140186,
      "grad_norm": 7.176130294799805,
      "learning_rate": 6e-05,
      "loss": 1.6523,
      "step": 6
    },
    {
      "epoch": 0.06542056074766354,
      "grad_norm": 6.155409812927246,
      "learning_rate": 7e-05,
      "loss": 0.9898,
      "step": 7
    },
    {
      "epoch": 0.07476635514018691,
      "grad_norm": 5.576105117797852,
      "learning_rate": 8e-05,
      "loss": 0.5435,
      "step": 8
    },
    {
      "epoch": 0.08411214953271028,
      "grad_norm": 5.076796531677246,
      "learning_rate": 9e-05,
      "loss": 0.2227,
      "step": 9
    },
    {
      "epoch": 0.08411214953271028,
      "eval_loss": 0.2664138972759247,
      "eval_runtime": 9.9171,
      "eval_samples_per_second": 9.075,
      "eval_steps_per_second": 1.21,
      "step": 9
    },
    {
      "epoch": 0.09345794392523364,
      "grad_norm": 4.753925800323486,
      "learning_rate": 0.0001,
      "loss": 0.3985,
      "step": 10
    },
    {
      "epoch": 0.102803738317757,
      "grad_norm": 16.22331428527832,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.4426,
      "step": 11
    },
    {
      "epoch": 0.11214953271028037,
      "grad_norm": 8.677202224731445,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.4099,
      "step": 12
    },
    {
      "epoch": 0.12149532710280374,
      "grad_norm": 1.7714290618896484,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.2145,
      "step": 13
    },
    {
      "epoch": 0.1308411214953271,
      "grad_norm": 2.164073944091797,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.1979,
      "step": 14
    },
    {
      "epoch": 0.14018691588785046,
      "grad_norm": 2.8190300464630127,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.311,
      "step": 15
    },
    {
      "epoch": 0.14953271028037382,
      "grad_norm": 1.9204503297805786,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.1376,
      "step": 16
    },
    {
      "epoch": 0.1588785046728972,
      "grad_norm": 2.1276960372924805,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.1889,
      "step": 17
    },
    {
      "epoch": 0.16822429906542055,
      "grad_norm": 1.7273892164230347,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.1675,
      "step": 18
    },
    {
      "epoch": 0.16822429906542055,
      "eval_loss": 0.20133525133132935,
      "eval_runtime": 9.9182,
      "eval_samples_per_second": 9.074,
      "eval_steps_per_second": 1.21,
      "step": 18
    },
    {
      "epoch": 0.17757009345794392,
      "grad_norm": 1.9443976879119873,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.1344,
      "step": 19
    },
    {
      "epoch": 0.18691588785046728,
      "grad_norm": 1.6126904487609863,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0862,
      "step": 20
    },
    {
      "epoch": 0.19626168224299065,
      "grad_norm": 2.9263195991516113,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.365,
      "step": 21
    },
    {
      "epoch": 0.205607476635514,
      "grad_norm": 2.922905445098877,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.1932,
      "step": 22
    },
    {
      "epoch": 0.21495327102803738,
      "grad_norm": 1.589261531829834,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.1008,
      "step": 23
    },
    {
      "epoch": 0.22429906542056074,
      "grad_norm": 2.486962080001831,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.2308,
      "step": 24
    },
    {
      "epoch": 0.2336448598130841,
      "grad_norm": 2.5798962116241455,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.1533,
      "step": 25
    },
    {
      "epoch": 0.24299065420560748,
      "grad_norm": 1.3371126651763916,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.1392,
      "step": 26
    },
    {
      "epoch": 0.2523364485981308,
      "grad_norm": 2.8493430614471436,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.3844,
      "step": 27
    },
    {
      "epoch": 0.2523364485981308,
      "eval_loss": 0.1533183753490448,
      "eval_runtime": 9.9456,
      "eval_samples_per_second": 9.049,
      "eval_steps_per_second": 1.207,
      "step": 27
    },
    {
      "epoch": 0.2616822429906542,
      "grad_norm": 2.042898654937744,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.193,
      "step": 28
    },
    {
      "epoch": 0.27102803738317754,
      "grad_norm": 2.989135503768921,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.2805,
      "step": 29
    },
    {
      "epoch": 0.2803738317757009,
      "grad_norm": 2.1197803020477295,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.1497,
      "step": 30
    },
    {
      "epoch": 0.2897196261682243,
      "grad_norm": 2.60103178024292,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.3375,
      "step": 31
    },
    {
      "epoch": 0.29906542056074764,
      "grad_norm": 1.7487047910690308,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.1548,
      "step": 32
    },
    {
      "epoch": 0.308411214953271,
      "grad_norm": 2.1897084712982178,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.2085,
      "step": 33
    },
    {
      "epoch": 0.3177570093457944,
      "grad_norm": 1.5416369438171387,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.1373,
      "step": 34
    },
    {
      "epoch": 0.32710280373831774,
      "grad_norm": 1.741955041885376,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.1334,
      "step": 35
    },
    {
      "epoch": 0.3364485981308411,
      "grad_norm": 1.1244958639144897,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0926,
      "step": 36
    },
    {
      "epoch": 0.3364485981308411,
      "eval_loss": 0.1806527078151703,
      "eval_runtime": 9.9263,
      "eval_samples_per_second": 9.067,
      "eval_steps_per_second": 1.209,
      "step": 36
    },
    {
      "epoch": 0.34579439252336447,
      "grad_norm": 0.8827672600746155,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0672,
      "step": 37
    },
    {
      "epoch": 0.35514018691588783,
      "grad_norm": 3.047365188598633,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.2127,
      "step": 38
    },
    {
      "epoch": 0.3644859813084112,
      "grad_norm": 2.438547134399414,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.4397,
      "step": 39
    },
    {
      "epoch": 0.37383177570093457,
      "grad_norm": 1.661272406578064,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1101,
      "step": 40
    },
    {
      "epoch": 0.38317757009345793,
      "grad_norm": 1.938929557800293,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.1924,
      "step": 41
    },
    {
      "epoch": 0.3925233644859813,
      "grad_norm": 1.2084273099899292,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.2993,
      "step": 42
    },
    {
      "epoch": 0.40186915887850466,
      "grad_norm": 2.1698427200317383,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.2302,
      "step": 43
    },
    {
      "epoch": 0.411214953271028,
      "grad_norm": 2.3812754154205322,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.1944,
      "step": 44
    },
    {
      "epoch": 0.4205607476635514,
      "grad_norm": 0.8029949069023132,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0606,
      "step": 45
    },
    {
      "epoch": 0.4205607476635514,
      "eval_loss": 0.15247972309589386,
      "eval_runtime": 9.9323,
      "eval_samples_per_second": 9.061,
      "eval_steps_per_second": 1.208,
      "step": 45
    },
    {
      "epoch": 0.42990654205607476,
      "grad_norm": 1.7329232692718506,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.1753,
      "step": 46
    },
    {
      "epoch": 0.4392523364485981,
      "grad_norm": 0.7043386101722717,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.0885,
      "step": 47
    },
    {
      "epoch": 0.4485981308411215,
      "grad_norm": 1.0490260124206543,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.1496,
      "step": 48
    },
    {
      "epoch": 0.45794392523364486,
      "grad_norm": 0.6998155117034912,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.078,
      "step": 49
    },
    {
      "epoch": 0.4672897196261682,
      "grad_norm": 1.908764362335205,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.1726,
      "step": 50
    },
    {
      "epoch": 0.4766355140186916,
      "grad_norm": 0.965490996837616,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.1322,
      "step": 51
    },
    {
      "epoch": 0.48598130841121495,
      "grad_norm": 1.3906739950180054,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.1442,
      "step": 52
    },
    {
      "epoch": 0.4953271028037383,
      "grad_norm": 0.9148610830307007,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.0929,
      "step": 53
    },
    {
      "epoch": 0.5046728971962616,
      "grad_norm": 0.6932138204574585,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.065,
      "step": 54
    },
    {
      "epoch": 0.5046728971962616,
      "eval_loss": 0.14502766728401184,
      "eval_runtime": 9.9224,
      "eval_samples_per_second": 9.07,
      "eval_steps_per_second": 1.209,
      "step": 54
    },
    {
      "epoch": 0.514018691588785,
      "grad_norm": 0.9336224794387817,
      "learning_rate": 5e-05,
      "loss": 0.0873,
      "step": 55
    },
    {
      "epoch": 0.5233644859813084,
      "grad_norm": 2.6763319969177246,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.2321,
      "step": 56
    },
    {
      "epoch": 0.5327102803738317,
      "grad_norm": 1.5140315294265747,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.1293,
      "step": 57
    },
    {
      "epoch": 0.5420560747663551,
      "grad_norm": 2.876084089279175,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.1911,
      "step": 58
    },
    {
      "epoch": 0.5514018691588785,
      "grad_norm": 1.4481045007705688,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.1164,
      "step": 59
    },
    {
      "epoch": 0.5607476635514018,
      "grad_norm": 1.3687912225723267,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.1107,
      "step": 60
    },
    {
      "epoch": 0.5700934579439252,
      "grad_norm": 1.4447373151779175,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.1582,
      "step": 61
    },
    {
      "epoch": 0.5794392523364486,
      "grad_norm": 1.689139723777771,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.1598,
      "step": 62
    },
    {
      "epoch": 0.5887850467289719,
      "grad_norm": 1.8605122566223145,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.1788,
      "step": 63
    },
    {
      "epoch": 0.5887850467289719,
      "eval_loss": 0.13512177765369415,
      "eval_runtime": 9.9312,
      "eval_samples_per_second": 9.062,
      "eval_steps_per_second": 1.208,
      "step": 63
    },
    {
      "epoch": 0.5981308411214953,
      "grad_norm": 2.114910364151001,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.1979,
      "step": 64
    },
    {
      "epoch": 0.6074766355140186,
      "grad_norm": 1.8224011659622192,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.1093,
      "step": 65
    },
    {
      "epoch": 0.616822429906542,
      "grad_norm": 1.9861820936203003,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.131,
      "step": 66
    },
    {
      "epoch": 0.6261682242990654,
      "grad_norm": 0.9865180850028992,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.0963,
      "step": 67
    },
    {
      "epoch": 0.6355140186915887,
      "grad_norm": 1.2104160785675049,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.18,
      "step": 68
    },
    {
      "epoch": 0.6448598130841121,
      "grad_norm": 1.9187355041503906,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.2033,
      "step": 69
    },
    {
      "epoch": 0.6542056074766355,
      "grad_norm": 2.4192073345184326,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.1503,
      "step": 70
    },
    {
      "epoch": 0.6635514018691588,
      "grad_norm": 1.5752084255218506,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.2479,
      "step": 71
    },
    {
      "epoch": 0.6728971962616822,
      "grad_norm": 1.5975793600082397,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.2147,
      "step": 72
    },
    {
      "epoch": 0.6728971962616822,
      "eval_loss": 0.1422102302312851,
      "eval_runtime": 9.9317,
      "eval_samples_per_second": 9.062,
      "eval_steps_per_second": 1.208,
      "step": 72
    },
    {
      "epoch": 0.6822429906542056,
      "grad_norm": 1.5921026468276978,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.1298,
      "step": 73
    },
    {
      "epoch": 0.6915887850467289,
      "grad_norm": 1.4968714714050293,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.1324,
      "step": 74
    },
    {
      "epoch": 0.7009345794392523,
      "grad_norm": 1.4271581172943115,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.1311,
      "step": 75
    },
    {
      "epoch": 0.7102803738317757,
      "grad_norm": 0.96708083152771,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.1007,
      "step": 76
    },
    {
      "epoch": 0.719626168224299,
      "grad_norm": 1.6786830425262451,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.0911,
      "step": 77
    },
    {
      "epoch": 0.7289719626168224,
      "grad_norm": 0.927327036857605,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.1049,
      "step": 78
    },
    {
      "epoch": 0.7383177570093458,
      "grad_norm": 1.7776973247528076,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.127,
      "step": 79
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 3.183727264404297,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.3637,
      "step": 80
    },
    {
      "epoch": 0.7570093457943925,
      "grad_norm": 2.603325843811035,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.3141,
      "step": 81
    },
    {
      "epoch": 0.7570093457943925,
      "eval_loss": 0.14180181920528412,
      "eval_runtime": 9.9223,
      "eval_samples_per_second": 9.07,
      "eval_steps_per_second": 1.209,
      "step": 81
    },
    {
      "epoch": 0.7663551401869159,
      "grad_norm": 2.0244991779327393,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.2154,
      "step": 82
    },
    {
      "epoch": 0.7757009345794392,
      "grad_norm": 1.4853664636611938,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.1545,
      "step": 83
    },
    {
      "epoch": 0.7850467289719626,
      "grad_norm": 1.7622134685516357,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.1585,
      "step": 84
    },
    {
      "epoch": 0.794392523364486,
      "grad_norm": 1.6791046857833862,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.1472,
      "step": 85
    },
    {
      "epoch": 0.8037383177570093,
      "grad_norm": 0.5698386430740356,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0236,
      "step": 86
    },
    {
      "epoch": 0.8130841121495327,
      "grad_norm": 1.4814032316207886,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.1654,
      "step": 87
    },
    {
      "epoch": 0.822429906542056,
      "grad_norm": 1.687814712524414,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.1412,
      "step": 88
    },
    {
      "epoch": 0.8317757009345794,
      "grad_norm": 0.9833457469940186,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.0574,
      "step": 89
    },
    {
      "epoch": 0.8411214953271028,
      "grad_norm": 2.030860662460327,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.1786,
      "step": 90
    },
    {
      "epoch": 0.8411214953271028,
      "eval_loss": 0.13933759927749634,
      "eval_runtime": 9.9295,
      "eval_samples_per_second": 9.064,
      "eval_steps_per_second": 1.209,
      "step": 90
    },
    {
      "epoch": 0.8504672897196262,
      "grad_norm": 1.0907182693481445,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0638,
      "step": 91
    },
    {
      "epoch": 0.8598130841121495,
      "grad_norm": 1.5568088293075562,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.1218,
      "step": 92
    },
    {
      "epoch": 0.8691588785046729,
      "grad_norm": 1.7905406951904297,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.0971,
      "step": 93
    },
    {
      "epoch": 0.8785046728971962,
      "grad_norm": 2.2480037212371826,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.1525,
      "step": 94
    },
    {
      "epoch": 0.8878504672897196,
      "grad_norm": 1.4726840257644653,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.114,
      "step": 95
    },
    {
      "epoch": 0.897196261682243,
      "grad_norm": 1.3955063819885254,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.11,
      "step": 96
    },
    {
      "epoch": 0.9065420560747663,
      "grad_norm": 2.6144371032714844,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.1461,
      "step": 97
    },
    {
      "epoch": 0.9158878504672897,
      "grad_norm": 1.691392183303833,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.1275,
      "step": 98
    },
    {
      "epoch": 0.9252336448598131,
      "grad_norm": 0.864076554775238,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0793,
      "step": 99
    },
    {
      "epoch": 0.9252336448598131,
      "eval_loss": 0.13823653757572174,
      "eval_runtime": 9.9251,
      "eval_samples_per_second": 9.068,
      "eval_steps_per_second": 1.209,
      "step": 99
    },
    {
      "epoch": 0.9345794392523364,
      "grad_norm": 1.9234707355499268,
      "learning_rate": 0.0,
      "loss": 0.1388,
      "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": 7.41887283560448e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}