{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1367053998632946,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001367053998632946,
      "grad_norm": 0.021522950381040573,
      "learning_rate": 1e-05,
      "loss": 10.3797,
      "step": 1
    },
    {
      "epoch": 0.001367053998632946,
      "eval_loss": 10.379307746887207,
      "eval_runtime": 7.5126,
      "eval_samples_per_second": 81.995,
      "eval_steps_per_second": 10.249,
      "step": 1
    },
    {
      "epoch": 0.002734107997265892,
      "grad_norm": 0.023411447182297707,
      "learning_rate": 2e-05,
      "loss": 10.3802,
      "step": 2
    },
    {
      "epoch": 0.004101161995898838,
      "grad_norm": 0.020306671038269997,
      "learning_rate": 3e-05,
      "loss": 10.3789,
      "step": 3
    },
    {
      "epoch": 0.005468215994531784,
      "grad_norm": 0.020246416330337524,
      "learning_rate": 4e-05,
      "loss": 10.3779,
      "step": 4
    },
    {
      "epoch": 0.00683526999316473,
      "grad_norm": 0.02275925502181053,
      "learning_rate": 5e-05,
      "loss": 10.3798,
      "step": 5
    },
    {
      "epoch": 0.008202323991797676,
      "grad_norm": 0.02008518949151039,
      "learning_rate": 6e-05,
      "loss": 10.379,
      "step": 6
    },
    {
      "epoch": 0.009569377990430622,
      "grad_norm": 0.02189980261027813,
      "learning_rate": 7e-05,
      "loss": 10.3801,
      "step": 7
    },
    {
      "epoch": 0.010936431989063569,
      "grad_norm": 0.02176029607653618,
      "learning_rate": 8e-05,
      "loss": 10.3777,
      "step": 8
    },
    {
      "epoch": 0.012303485987696514,
      "grad_norm": 0.023842690512537956,
      "learning_rate": 9e-05,
      "loss": 10.3795,
      "step": 9
    },
    {
      "epoch": 0.012303485987696514,
      "eval_loss": 10.379066467285156,
      "eval_runtime": 7.4365,
      "eval_samples_per_second": 82.835,
      "eval_steps_per_second": 10.354,
      "step": 9
    },
    {
      "epoch": 0.01367053998632946,
      "grad_norm": 0.0210714228451252,
      "learning_rate": 0.0001,
      "loss": 10.3798,
      "step": 10
    },
    {
      "epoch": 0.015037593984962405,
      "grad_norm": 0.023068828508257866,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.377,
      "step": 11
    },
    {
      "epoch": 0.016404647983595352,
      "grad_norm": 0.020229408517479897,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.3776,
      "step": 12
    },
    {
      "epoch": 0.0177717019822283,
      "grad_norm": 0.022155430167913437,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.3806,
      "step": 13
    },
    {
      "epoch": 0.019138755980861243,
      "grad_norm": 0.024158868938684464,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.3797,
      "step": 14
    },
    {
      "epoch": 0.02050580997949419,
      "grad_norm": 0.023922177031636238,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.3794,
      "step": 15
    },
    {
      "epoch": 0.021872863978127138,
      "grad_norm": 0.024395423009991646,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.379,
      "step": 16
    },
    {
      "epoch": 0.02323991797676008,
      "grad_norm": 0.02309221588075161,
      "learning_rate": 9.851478631379982e-05,
      "loss": 10.3782,
      "step": 17
    },
    {
      "epoch": 0.02460697197539303,
      "grad_norm": 0.025574712082743645,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.378,
      "step": 18
    },
    {
      "epoch": 0.02460697197539303,
      "eval_loss": 10.378443717956543,
      "eval_runtime": 7.54,
      "eval_samples_per_second": 81.698,
      "eval_steps_per_second": 10.212,
      "step": 18
    },
    {
      "epoch": 0.025974025974025976,
      "grad_norm": 0.02530761808156967,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3779,
      "step": 19
    },
    {
      "epoch": 0.02734107997265892,
      "grad_norm": 0.026340413838624954,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.3779,
      "step": 20
    },
    {
      "epoch": 0.028708133971291867,
      "grad_norm": 0.024185722693800926,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.3771,
      "step": 21
    },
    {
      "epoch": 0.03007518796992481,
      "grad_norm": 0.026919597759842873,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.3808,
      "step": 22
    },
    {
      "epoch": 0.03144224196855776,
      "grad_norm": 0.02461450733244419,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.3772,
      "step": 23
    },
    {
      "epoch": 0.032809295967190705,
      "grad_norm": 0.026270925998687744,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.3782,
      "step": 24
    },
    {
      "epoch": 0.03417634996582365,
      "grad_norm": 0.026404548436403275,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3782,
      "step": 25
    },
    {
      "epoch": 0.0355434039644566,
      "grad_norm": 0.02938682585954666,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.3787,
      "step": 26
    },
    {
      "epoch": 0.03691045796308954,
      "grad_norm": 0.02904021181166172,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.3791,
      "step": 27
    },
    {
      "epoch": 0.03691045796308954,
      "eval_loss": 10.377742767333984,
      "eval_runtime": 7.5411,
      "eval_samples_per_second": 81.686,
      "eval_steps_per_second": 10.211,
      "step": 27
    },
    {
      "epoch": 0.03827751196172249,
      "grad_norm": 0.0318170003592968,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3771,
      "step": 28
    },
    {
      "epoch": 0.039644565960355434,
      "grad_norm": 0.02432270534336567,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.3778,
      "step": 29
    },
    {
      "epoch": 0.04101161995898838,
      "grad_norm": 0.026823556050658226,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.3767,
      "step": 30
    },
    {
      "epoch": 0.04237867395762133,
      "grad_norm": 0.033317871391773224,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.3794,
      "step": 31
    },
    {
      "epoch": 0.043745727956254275,
      "grad_norm": 0.031059078872203827,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.3769,
      "step": 32
    },
    {
      "epoch": 0.045112781954887216,
      "grad_norm": 0.03409845754504204,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.3752,
      "step": 33
    },
    {
      "epoch": 0.04647983595352016,
      "grad_norm": 0.03169793263077736,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.3758,
      "step": 34
    },
    {
      "epoch": 0.04784688995215311,
      "grad_norm": 0.03686445206403732,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.3781,
      "step": 35
    },
    {
      "epoch": 0.04921394395078606,
      "grad_norm": 0.033234287053346634,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.3763,
      "step": 36
    },
    {
      "epoch": 0.04921394395078606,
      "eval_loss": 10.376964569091797,
      "eval_runtime": 7.5425,
      "eval_samples_per_second": 81.67,
      "eval_steps_per_second": 10.209,
      "step": 36
    },
    {
      "epoch": 0.050580997949419004,
      "grad_norm": 0.036596354097127914,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3761,
      "step": 37
    },
    {
      "epoch": 0.05194805194805195,
      "grad_norm": 0.037729229778051376,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.3797,
      "step": 38
    },
    {
      "epoch": 0.05331510594668489,
      "grad_norm": 0.033103104680776596,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.3753,
      "step": 39
    },
    {
      "epoch": 0.05468215994531784,
      "grad_norm": 0.03534068167209625,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.377,
      "step": 40
    },
    {
      "epoch": 0.056049213943950786,
      "grad_norm": 0.039501581341028214,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.3763,
      "step": 41
    },
    {
      "epoch": 0.05741626794258373,
      "grad_norm": 0.034217603504657745,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.3771,
      "step": 42
    },
    {
      "epoch": 0.05878332194121668,
      "grad_norm": 0.03207022696733475,
      "learning_rate": 7.033683215379002e-05,
      "loss": 10.3783,
      "step": 43
    },
    {
      "epoch": 0.06015037593984962,
      "grad_norm": 0.032752349972724915,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.3758,
      "step": 44
    },
    {
      "epoch": 0.06151742993848257,
      "grad_norm": 0.03998551517724991,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.3773,
      "step": 45
    },
    {
      "epoch": 0.06151742993848257,
      "eval_loss": 10.376114845275879,
      "eval_runtime": 7.5351,
      "eval_samples_per_second": 81.75,
      "eval_steps_per_second": 10.219,
      "step": 45
    },
    {
      "epoch": 0.06288448393711552,
      "grad_norm": 0.04494759440422058,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3791,
      "step": 46
    },
    {
      "epoch": 0.06425153793574846,
      "grad_norm": 0.04423767328262329,
      "learning_rate": 6.378186779084995e-05,
      "loss": 10.3764,
      "step": 47
    },
    {
      "epoch": 0.06561859193438141,
      "grad_norm": 0.040932126343250275,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.3753,
      "step": 48
    },
    {
      "epoch": 0.06698564593301436,
      "grad_norm": 0.03703533113002777,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 10.3754,
      "step": 49
    },
    {
      "epoch": 0.0683526999316473,
      "grad_norm": 0.045363329350948334,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.3755,
      "step": 50
    },
    {
      "epoch": 0.06971975393028025,
      "grad_norm": 0.049810998141765594,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.3735,
      "step": 51
    },
    {
      "epoch": 0.0710868079289132,
      "grad_norm": 0.043195340782403946,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.375,
      "step": 52
    },
    {
      "epoch": 0.07245386192754613,
      "grad_norm": 0.047868385910987854,
      "learning_rate": 5.348782368720626e-05,
      "loss": 10.3728,
      "step": 53
    },
    {
      "epoch": 0.07382091592617908,
      "grad_norm": 0.03871385008096695,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.3749,
      "step": 54
    },
    {
      "epoch": 0.07382091592617908,
      "eval_loss": 10.37525463104248,
      "eval_runtime": 7.4518,
      "eval_samples_per_second": 82.665,
      "eval_steps_per_second": 10.333,
      "step": 54
    },
    {
      "epoch": 0.07518796992481203,
      "grad_norm": 0.046165093779563904,
      "learning_rate": 5e-05,
      "loss": 10.3771,
      "step": 55
    },
    {
      "epoch": 0.07655502392344497,
      "grad_norm": 0.04805214703083038,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.3757,
      "step": 56
    },
    {
      "epoch": 0.07792207792207792,
      "grad_norm": 0.04241994395852089,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.3731,
      "step": 57
    },
    {
      "epoch": 0.07928913192071087,
      "grad_norm": 0.05413554608821869,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.3751,
      "step": 58
    },
    {
      "epoch": 0.08065618591934381,
      "grad_norm": 0.05318213999271393,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 10.3759,
      "step": 59
    },
    {
      "epoch": 0.08202323991797676,
      "grad_norm": 0.04020492359995842,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.3745,
      "step": 60
    },
    {
      "epoch": 0.08339029391660971,
      "grad_norm": 0.05230384320020676,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.3756,
      "step": 61
    },
    {
      "epoch": 0.08475734791524266,
      "grad_norm": 0.05986716225743294,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.3746,
      "step": 62
    },
    {
      "epoch": 0.0861244019138756,
      "grad_norm": 0.05598291754722595,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.3747,
      "step": 63
    },
    {
      "epoch": 0.0861244019138756,
      "eval_loss": 10.374478340148926,
      "eval_runtime": 7.5341,
      "eval_samples_per_second": 81.762,
      "eval_steps_per_second": 10.22,
      "step": 63
    },
    {
      "epoch": 0.08749145591250855,
      "grad_norm": 0.048764973878860474,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.374,
      "step": 64
    },
    {
      "epoch": 0.08885850991114148,
      "grad_norm": 0.05037747696042061,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.375,
      "step": 65
    },
    {
      "epoch": 0.09022556390977443,
      "grad_norm": 0.05323159694671631,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.3725,
      "step": 66
    },
    {
      "epoch": 0.09159261790840738,
      "grad_norm": 0.05076790973544121,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 10.3727,
      "step": 67
    },
    {
      "epoch": 0.09295967190704033,
      "grad_norm": 0.05909010395407677,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.373,
      "step": 68
    },
    {
      "epoch": 0.09432672590567327,
      "grad_norm": 0.05870535224676132,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.373,
      "step": 69
    },
    {
      "epoch": 0.09569377990430622,
      "grad_norm": 0.05204598605632782,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.3745,
      "step": 70
    },
    {
      "epoch": 0.09706083390293917,
      "grad_norm": 0.05706306919455528,
      "learning_rate": 2.350403678833976e-05,
      "loss": 10.3738,
      "step": 71
    },
    {
      "epoch": 0.09842788790157211,
      "grad_norm": 0.052603580057621,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.3744,
      "step": 72
    },
    {
      "epoch": 0.09842788790157211,
      "eval_loss": 10.373908996582031,
      "eval_runtime": 7.5206,
      "eval_samples_per_second": 81.909,
      "eval_steps_per_second": 10.239,
      "step": 72
    },
    {
      "epoch": 0.09979494190020506,
      "grad_norm": 0.05649203807115555,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3732,
      "step": 73
    },
    {
      "epoch": 0.10116199589883801,
      "grad_norm": 0.052477333694696426,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.373,
      "step": 74
    },
    {
      "epoch": 0.10252904989747096,
      "grad_norm": 0.053809039294719696,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.3712,
      "step": 75
    },
    {
      "epoch": 0.1038961038961039,
      "grad_norm": 0.05715708062052727,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 10.3724,
      "step": 76
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 0.05752133950591087,
      "learning_rate": 1.526708147705013e-05,
      "loss": 10.3749,
      "step": 77
    },
    {
      "epoch": 0.10663021189336978,
      "grad_norm": 0.05503221973776817,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.3729,
      "step": 78
    },
    {
      "epoch": 0.10799726589200273,
      "grad_norm": 0.05126158893108368,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 10.375,
      "step": 79
    },
    {
      "epoch": 0.10936431989063568,
      "grad_norm": 0.05652277544140816,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.3714,
      "step": 80
    },
    {
      "epoch": 0.11073137388926863,
      "grad_norm": 0.05654437467455864,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 10.3755,
      "step": 81
    },
    {
      "epoch": 0.11073137388926863,
      "eval_loss": 10.373574256896973,
      "eval_runtime": 7.4889,
      "eval_samples_per_second": 82.256,
      "eval_steps_per_second": 10.282,
      "step": 81
    },
    {
      "epoch": 0.11209842788790157,
      "grad_norm": 0.053494893014431,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.3745,
      "step": 82
    },
    {
      "epoch": 0.11346548188653452,
      "grad_norm": 0.052283793687820435,
      "learning_rate": 8.548121372247918e-06,
      "loss": 10.3738,
      "step": 83
    },
    {
      "epoch": 0.11483253588516747,
      "grad_norm": 0.05515560507774353,
      "learning_rate": 7.597595192178702e-06,
      "loss": 10.3753,
      "step": 84
    },
    {
      "epoch": 0.11619958988380041,
      "grad_norm": 0.06458757072687149,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.374,
      "step": 85
    },
    {
      "epoch": 0.11756664388243336,
      "grad_norm": 0.05971672385931015,
      "learning_rate": 5.852620357053651e-06,
      "loss": 10.374,
      "step": 86
    },
    {
      "epoch": 0.11893369788106631,
      "grad_norm": 0.055294219404459,
      "learning_rate": 5.060297685041659e-06,
      "loss": 10.3703,
      "step": 87
    },
    {
      "epoch": 0.12030075187969924,
      "grad_norm": 0.0639239251613617,
      "learning_rate": 4.322727117869951e-06,
      "loss": 10.3722,
      "step": 88
    },
    {
      "epoch": 0.12166780587833219,
      "grad_norm": 0.06268282234668732,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 10.3723,
      "step": 89
    },
    {
      "epoch": 0.12303485987696514,
      "grad_norm": 0.0572989284992218,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.3748,
      "step": 90
    },
    {
      "epoch": 0.12303485987696514,
      "eval_loss": 10.373421669006348,
      "eval_runtime": 7.487,
      "eval_samples_per_second": 82.276,
      "eval_steps_per_second": 10.284,
      "step": 90
    },
    {
      "epoch": 0.12440191387559808,
      "grad_norm": 0.05932777374982834,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.3744,
      "step": 91
    },
    {
      "epoch": 0.12576896787423103,
      "grad_norm": 0.05577975884079933,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 10.3739,
      "step": 92
    },
    {
      "epoch": 0.127136021872864,
      "grad_norm": 0.05579007416963577,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 10.3712,
      "step": 93
    },
    {
      "epoch": 0.12850307587149692,
      "grad_norm": 0.060124702751636505,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.3745,
      "step": 94
    },
    {
      "epoch": 0.12987012987012986,
      "grad_norm": 0.05368928983807564,
      "learning_rate": 7.596123493895991e-07,
      "loss": 10.3729,
      "step": 95
    },
    {
      "epoch": 0.13123718386876282,
      "grad_norm": 0.06362160295248032,
      "learning_rate": 4.865965629214819e-07,
      "loss": 10.3745,
      "step": 96
    },
    {
      "epoch": 0.13260423786739575,
      "grad_norm": 0.05649407580494881,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 10.3725,
      "step": 97
    },
    {
      "epoch": 0.1339712918660287,
      "grad_norm": 0.06166595220565796,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 10.3738,
      "step": 98
    },
    {
      "epoch": 0.13533834586466165,
      "grad_norm": 0.054897576570510864,
      "learning_rate": 3.04586490452119e-08,
      "loss": 10.3746,
      "step": 99
    },
    {
      "epoch": 0.13533834586466165,
      "eval_loss": 10.37338924407959,
      "eval_runtime": 7.5766,
      "eval_samples_per_second": 81.303,
      "eval_steps_per_second": 10.163,
      "step": 99
    },
    {
      "epoch": 0.1367053998632946,
      "grad_norm": 0.05194012448191643,
      "learning_rate": 0.0,
      "loss": 10.3743,
      "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": 10460489318400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}