{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08481764206955046,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008481764206955047,
      "grad_norm": 14.318007469177246,
      "learning_rate": 1e-05,
      "loss": 6.0266,
      "step": 1
    },
    {
      "epoch": 0.0008481764206955047,
      "eval_loss": 5.938344478607178,
      "eval_runtime": 29.7987,
      "eval_samples_per_second": 33.324,
      "eval_steps_per_second": 4.195,
      "step": 1
    },
    {
      "epoch": 0.0016963528413910093,
      "grad_norm": 12.189530372619629,
      "learning_rate": 2e-05,
      "loss": 5.9766,
      "step": 2
    },
    {
      "epoch": 0.002544529262086514,
      "grad_norm": 12.671658515930176,
      "learning_rate": 3e-05,
      "loss": 5.8605,
      "step": 3
    },
    {
      "epoch": 0.0033927056827820186,
      "grad_norm": 12.592327117919922,
      "learning_rate": 4e-05,
      "loss": 5.9025,
      "step": 4
    },
    {
      "epoch": 0.004240882103477523,
      "grad_norm": 13.333489418029785,
      "learning_rate": 5e-05,
      "loss": 5.6609,
      "step": 5
    },
    {
      "epoch": 0.005089058524173028,
      "grad_norm": 13.644075393676758,
      "learning_rate": 6e-05,
      "loss": 5.3589,
      "step": 6
    },
    {
      "epoch": 0.005937234944868533,
      "grad_norm": 12.345027923583984,
      "learning_rate": 7e-05,
      "loss": 4.8207,
      "step": 7
    },
    {
      "epoch": 0.006785411365564037,
      "grad_norm": 13.133736610412598,
      "learning_rate": 8e-05,
      "loss": 4.2425,
      "step": 8
    },
    {
      "epoch": 0.007633587786259542,
      "grad_norm": 13.290817260742188,
      "learning_rate": 9e-05,
      "loss": 3.7581,
      "step": 9
    },
    {
      "epoch": 0.007633587786259542,
      "eval_loss": 2.8263907432556152,
      "eval_runtime": 28.8558,
      "eval_samples_per_second": 34.413,
      "eval_steps_per_second": 4.332,
      "step": 9
    },
    {
      "epoch": 0.008481764206955046,
      "grad_norm": 10.202874183654785,
      "learning_rate": 0.0001,
      "loss": 2.7553,
      "step": 10
    },
    {
      "epoch": 0.009329940627650551,
      "grad_norm": 8.777361869812012,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.9677,
      "step": 11
    },
    {
      "epoch": 0.010178117048346057,
      "grad_norm": 7.6035990715026855,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.5619,
      "step": 12
    },
    {
      "epoch": 0.01102629346904156,
      "grad_norm": 9.740479469299316,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.7213,
      "step": 13
    },
    {
      "epoch": 0.011874469889737066,
      "grad_norm": 3.958515167236328,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.0046,
      "step": 14
    },
    {
      "epoch": 0.01272264631043257,
      "grad_norm": 3.2152061462402344,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.8369,
      "step": 15
    },
    {
      "epoch": 0.013570822731128074,
      "grad_norm": 9.387269973754883,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.0265,
      "step": 16
    },
    {
      "epoch": 0.01441899915182358,
      "grad_norm": 5.709386825561523,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.7527,
      "step": 17
    },
    {
      "epoch": 0.015267175572519083,
      "grad_norm": 4.907479286193848,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.6546,
      "step": 18
    },
    {
      "epoch": 0.015267175572519083,
      "eval_loss": 0.6198061108589172,
      "eval_runtime": 28.8798,
      "eval_samples_per_second": 34.384,
      "eval_steps_per_second": 4.328,
      "step": 18
    },
    {
      "epoch": 0.016115351993214587,
      "grad_norm": 9.104463577270508,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.7803,
      "step": 19
    },
    {
      "epoch": 0.016963528413910092,
      "grad_norm": 2.6081435680389404,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.5736,
      "step": 20
    },
    {
      "epoch": 0.017811704834605598,
      "grad_norm": 2.2690072059631348,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.5417,
      "step": 21
    },
    {
      "epoch": 0.018659881255301103,
      "grad_norm": 2.4608511924743652,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.5057,
      "step": 22
    },
    {
      "epoch": 0.019508057675996608,
      "grad_norm": 3.5970542430877686,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.5794,
      "step": 23
    },
    {
      "epoch": 0.020356234096692113,
      "grad_norm": 2.4997997283935547,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.5209,
      "step": 24
    },
    {
      "epoch": 0.021204410517387615,
      "grad_norm": 2.0091772079467773,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.5523,
      "step": 25
    },
    {
      "epoch": 0.02205258693808312,
      "grad_norm": 2.9645886421203613,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.5708,
      "step": 26
    },
    {
      "epoch": 0.022900763358778626,
      "grad_norm": 2.077575922012329,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.4646,
      "step": 27
    },
    {
      "epoch": 0.022900763358778626,
      "eval_loss": 0.48650485277175903,
      "eval_runtime": 28.9407,
      "eval_samples_per_second": 34.312,
      "eval_steps_per_second": 4.319,
      "step": 27
    },
    {
      "epoch": 0.02374893977947413,
      "grad_norm": 1.3554171323776245,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.4826,
      "step": 28
    },
    {
      "epoch": 0.024597116200169637,
      "grad_norm": 1.6642234325408936,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.4937,
      "step": 29
    },
    {
      "epoch": 0.02544529262086514,
      "grad_norm": 1.637468934059143,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.5004,
      "step": 30
    },
    {
      "epoch": 0.026293469041560644,
      "grad_norm": 2.1573736667633057,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.456,
      "step": 31
    },
    {
      "epoch": 0.02714164546225615,
      "grad_norm": 1.3219460248947144,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.428,
      "step": 32
    },
    {
      "epoch": 0.027989821882951654,
      "grad_norm": 1.4489333629608154,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.5236,
      "step": 33
    },
    {
      "epoch": 0.02883799830364716,
      "grad_norm": 0.9528306126594543,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.4771,
      "step": 34
    },
    {
      "epoch": 0.029686174724342665,
      "grad_norm": 0.9525566697120667,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.4884,
      "step": 35
    },
    {
      "epoch": 0.030534351145038167,
      "grad_norm": 5.734241962432861,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.5496,
      "step": 36
    },
    {
      "epoch": 0.030534351145038167,
      "eval_loss": 0.4875996708869934,
      "eval_runtime": 28.8306,
      "eval_samples_per_second": 34.443,
      "eval_steps_per_second": 4.336,
      "step": 36
    },
    {
      "epoch": 0.031382527565733676,
      "grad_norm": 1.5124987363815308,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.5263,
      "step": 37
    },
    {
      "epoch": 0.032230703986429174,
      "grad_norm": 1.2907754182815552,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.4894,
      "step": 38
    },
    {
      "epoch": 0.03307888040712468,
      "grad_norm": 0.8150112628936768,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.47,
      "step": 39
    },
    {
      "epoch": 0.033927056827820185,
      "grad_norm": 1.1699497699737549,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.4706,
      "step": 40
    },
    {
      "epoch": 0.03477523324851569,
      "grad_norm": 1.4197578430175781,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.4537,
      "step": 41
    },
    {
      "epoch": 0.035623409669211195,
      "grad_norm": 0.6217430233955383,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.4533,
      "step": 42
    },
    {
      "epoch": 0.0364715860899067,
      "grad_norm": 1.0930975675582886,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.4813,
      "step": 43
    },
    {
      "epoch": 0.037319762510602206,
      "grad_norm": 1.2884628772735596,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.5025,
      "step": 44
    },
    {
      "epoch": 0.03816793893129771,
      "grad_norm": 2.1661903858184814,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.5309,
      "step": 45
    },
    {
      "epoch": 0.03816793893129771,
      "eval_loss": 0.48306483030319214,
      "eval_runtime": 28.8269,
      "eval_samples_per_second": 34.447,
      "eval_steps_per_second": 4.336,
      "step": 45
    },
    {
      "epoch": 0.039016115351993216,
      "grad_norm": 3.116976022720337,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.5825,
      "step": 46
    },
    {
      "epoch": 0.03986429177268872,
      "grad_norm": 1.477339744567871,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.4475,
      "step": 47
    },
    {
      "epoch": 0.04071246819338423,
      "grad_norm": 1.4223567247390747,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.4632,
      "step": 48
    },
    {
      "epoch": 0.041560644614079725,
      "grad_norm": 1.7375524044036865,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.515,
      "step": 49
    },
    {
      "epoch": 0.04240882103477523,
      "grad_norm": 2.708205223083496,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.5253,
      "step": 50
    },
    {
      "epoch": 0.043256997455470736,
      "grad_norm": 1.370880365371704,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.4788,
      "step": 51
    },
    {
      "epoch": 0.04410517387616624,
      "grad_norm": 2.499513626098633,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.5015,
      "step": 52
    },
    {
      "epoch": 0.04495335029686175,
      "grad_norm": 1.1132203340530396,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.4478,
      "step": 53
    },
    {
      "epoch": 0.04580152671755725,
      "grad_norm": 1.6377148628234863,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.4741,
      "step": 54
    },
    {
      "epoch": 0.04580152671755725,
      "eval_loss": 0.472432017326355,
      "eval_runtime": 28.8421,
      "eval_samples_per_second": 34.429,
      "eval_steps_per_second": 4.334,
      "step": 54
    },
    {
      "epoch": 0.04664970313825276,
      "grad_norm": 2.505544900894165,
      "learning_rate": 5e-05,
      "loss": 0.4802,
      "step": 55
    },
    {
      "epoch": 0.04749787955894826,
      "grad_norm": 10.943180084228516,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.8622,
      "step": 56
    },
    {
      "epoch": 0.04834605597964377,
      "grad_norm": 0.8310089707374573,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.4541,
      "step": 57
    },
    {
      "epoch": 0.04919423240033927,
      "grad_norm": 1.5465755462646484,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.4799,
      "step": 58
    },
    {
      "epoch": 0.05004240882103478,
      "grad_norm": 0.8638088703155518,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.475,
      "step": 59
    },
    {
      "epoch": 0.05089058524173028,
      "grad_norm": 0.470604807138443,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.4695,
      "step": 60
    },
    {
      "epoch": 0.05173876166242578,
      "grad_norm": 0.7916291952133179,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.4777,
      "step": 61
    },
    {
      "epoch": 0.05258693808312129,
      "grad_norm": 0.5852257013320923,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.4792,
      "step": 62
    },
    {
      "epoch": 0.05343511450381679,
      "grad_norm": 1.6295372247695923,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.4252,
      "step": 63
    },
    {
      "epoch": 0.05343511450381679,
      "eval_loss": 0.4759678542613983,
      "eval_runtime": 28.8312,
      "eval_samples_per_second": 34.442,
      "eval_steps_per_second": 4.336,
      "step": 63
    },
    {
      "epoch": 0.0542832909245123,
      "grad_norm": 1.2610458135604858,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.499,
      "step": 64
    },
    {
      "epoch": 0.0551314673452078,
      "grad_norm": 1.2499618530273438,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.462,
      "step": 65
    },
    {
      "epoch": 0.05597964376590331,
      "grad_norm": 0.6781721115112305,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.4748,
      "step": 66
    },
    {
      "epoch": 0.056827820186598814,
      "grad_norm": 0.5098745822906494,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.4545,
      "step": 67
    },
    {
      "epoch": 0.05767599660729432,
      "grad_norm": 0.37473785877227783,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.4633,
      "step": 68
    },
    {
      "epoch": 0.058524173027989825,
      "grad_norm": 0.880598783493042,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.4556,
      "step": 69
    },
    {
      "epoch": 0.05937234944868533,
      "grad_norm": 0.47864964604377747,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.4591,
      "step": 70
    },
    {
      "epoch": 0.06022052586938083,
      "grad_norm": 0.9437469840049744,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.4695,
      "step": 71
    },
    {
      "epoch": 0.061068702290076333,
      "grad_norm": 1.843366026878357,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.5117,
      "step": 72
    },
    {
      "epoch": 0.061068702290076333,
      "eval_loss": 0.47027653455734253,
      "eval_runtime": 28.8329,
      "eval_samples_per_second": 34.44,
      "eval_steps_per_second": 4.335,
      "step": 72
    },
    {
      "epoch": 0.06191687871077184,
      "grad_norm": 0.9933050274848938,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.4504,
      "step": 73
    },
    {
      "epoch": 0.06276505513146735,
      "grad_norm": 1.8623085021972656,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.5068,
      "step": 74
    },
    {
      "epoch": 0.06361323155216285,
      "grad_norm": 1.1844606399536133,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.4464,
      "step": 75
    },
    {
      "epoch": 0.06446140797285835,
      "grad_norm": 0.5965391993522644,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.4651,
      "step": 76
    },
    {
      "epoch": 0.06530958439355386,
      "grad_norm": 0.6338193416595459,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.4456,
      "step": 77
    },
    {
      "epoch": 0.06615776081424936,
      "grad_norm": 0.3467748165130615,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.4615,
      "step": 78
    },
    {
      "epoch": 0.06700593723494487,
      "grad_norm": 1.386129379272461,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.4637,
      "step": 79
    },
    {
      "epoch": 0.06785411365564037,
      "grad_norm": 1.2354660034179688,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.4714,
      "step": 80
    },
    {
      "epoch": 0.06870229007633588,
      "grad_norm": 0.4873424768447876,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.4542,
      "step": 81
    },
    {
      "epoch": 0.06870229007633588,
      "eval_loss": 0.46868446469306946,
      "eval_runtime": 29.0217,
      "eval_samples_per_second": 34.216,
      "eval_steps_per_second": 4.307,
      "step": 81
    },
    {
      "epoch": 0.06955046649703138,
      "grad_norm": 1.060185194015503,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.4299,
      "step": 82
    },
    {
      "epoch": 0.07039864291772689,
      "grad_norm": 0.6003854274749756,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.4664,
      "step": 83
    },
    {
      "epoch": 0.07124681933842239,
      "grad_norm": 0.601787805557251,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.454,
      "step": 84
    },
    {
      "epoch": 0.0720949957591179,
      "grad_norm": 1.4092165231704712,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.4443,
      "step": 85
    },
    {
      "epoch": 0.0729431721798134,
      "grad_norm": 1.0296019315719604,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.4481,
      "step": 86
    },
    {
      "epoch": 0.0737913486005089,
      "grad_norm": 0.7165821194648743,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.4655,
      "step": 87
    },
    {
      "epoch": 0.07463952502120441,
      "grad_norm": 0.7949168682098389,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.4624,
      "step": 88
    },
    {
      "epoch": 0.07548770144189991,
      "grad_norm": 1.36370849609375,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.4611,
      "step": 89
    },
    {
      "epoch": 0.07633587786259542,
      "grad_norm": 0.7988469004631042,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.4684,
      "step": 90
    },
    {
      "epoch": 0.07633587786259542,
      "eval_loss": 0.4706438183784485,
      "eval_runtime": 28.8299,
      "eval_samples_per_second": 34.443,
      "eval_steps_per_second": 4.336,
      "step": 90
    },
    {
      "epoch": 0.07718405428329092,
      "grad_norm": 1.1426377296447754,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.4921,
      "step": 91
    },
    {
      "epoch": 0.07803223070398643,
      "grad_norm": 1.0854405164718628,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.4708,
      "step": 92
    },
    {
      "epoch": 0.07888040712468193,
      "grad_norm": 1.211848497390747,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.4789,
      "step": 93
    },
    {
      "epoch": 0.07972858354537744,
      "grad_norm": 1.167067527770996,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.4487,
      "step": 94
    },
    {
      "epoch": 0.08057675996607294,
      "grad_norm": 1.2036820650100708,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.4864,
      "step": 95
    },
    {
      "epoch": 0.08142493638676845,
      "grad_norm": 1.0609307289123535,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.4492,
      "step": 96
    },
    {
      "epoch": 0.08227311280746395,
      "grad_norm": 0.47746893763542175,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.4749,
      "step": 97
    },
    {
      "epoch": 0.08312128922815945,
      "grad_norm": 2.1157803535461426,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.5022,
      "step": 98
    },
    {
      "epoch": 0.08396946564885496,
      "grad_norm": 1.4069894552230835,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.4857,
      "step": 99
    },
    {
      "epoch": 0.08396946564885496,
      "eval_loss": 0.4704572558403015,
      "eval_runtime": 28.8321,
      "eval_samples_per_second": 34.441,
      "eval_steps_per_second": 4.335,
      "step": 99
    },
    {
      "epoch": 0.08481764206955046,
      "grad_norm": 0.7878907918930054,
      "learning_rate": 0.0,
      "loss": 0.4399,
      "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": 1.02936877203456e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}