{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03266372693124286,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00032663726931242854,
      "grad_norm": 0.03237062320113182,
      "learning_rate": 1e-05,
      "loss": 10.3758,
      "step": 1
    },
    {
      "epoch": 0.00032663726931242854,
      "eval_loss": 10.37636661529541,
      "eval_runtime": 21.2034,
      "eval_samples_per_second": 121.584,
      "eval_steps_per_second": 15.233,
      "step": 1
    },
    {
      "epoch": 0.0006532745386248571,
      "grad_norm": 0.04852365329861641,
      "learning_rate": 2e-05,
      "loss": 10.3803,
      "step": 2
    },
    {
      "epoch": 0.0009799118079372856,
      "grad_norm": 0.03296953812241554,
      "learning_rate": 3e-05,
      "loss": 10.3795,
      "step": 3
    },
    {
      "epoch": 0.0013065490772497142,
      "grad_norm": 0.028236396610736847,
      "learning_rate": 4e-05,
      "loss": 10.3786,
      "step": 4
    },
    {
      "epoch": 0.0016331863465621427,
      "grad_norm": 0.042653754353523254,
      "learning_rate": 5e-05,
      "loss": 10.3778,
      "step": 5
    },
    {
      "epoch": 0.0019598236158745713,
      "grad_norm": 0.03037174977362156,
      "learning_rate": 6e-05,
      "loss": 10.3766,
      "step": 6
    },
    {
      "epoch": 0.002286460885187,
      "grad_norm": 0.02649731934070587,
      "learning_rate": 7e-05,
      "loss": 10.3749,
      "step": 7
    },
    {
      "epoch": 0.0026130981544994283,
      "grad_norm": 0.027925627306103706,
      "learning_rate": 8e-05,
      "loss": 10.3755,
      "step": 8
    },
    {
      "epoch": 0.002939735423811857,
      "grad_norm": 0.043385352939367294,
      "learning_rate": 9e-05,
      "loss": 10.3776,
      "step": 9
    },
    {
      "epoch": 0.002939735423811857,
      "eval_loss": 10.376043319702148,
      "eval_runtime": 21.8447,
      "eval_samples_per_second": 118.015,
      "eval_steps_per_second": 14.786,
      "step": 9
    },
    {
      "epoch": 0.0032663726931242854,
      "grad_norm": 0.03745047375559807,
      "learning_rate": 0.0001,
      "loss": 10.3755,
      "step": 10
    },
    {
      "epoch": 0.003593009962436714,
      "grad_norm": 0.036895476281642914,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.3737,
      "step": 11
    },
    {
      "epoch": 0.0039196472317491425,
      "grad_norm": 0.0333566889166832,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.3757,
      "step": 12
    },
    {
      "epoch": 0.004246284501061571,
      "grad_norm": 0.0308595672249794,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.3742,
      "step": 13
    },
    {
      "epoch": 0.004572921770374,
      "grad_norm": 0.03860101103782654,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.3759,
      "step": 14
    },
    {
      "epoch": 0.004899559039686428,
      "grad_norm": 0.03834579139947891,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.3717,
      "step": 15
    },
    {
      "epoch": 0.005226196308998857,
      "grad_norm": 0.03277561068534851,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.3752,
      "step": 16
    },
    {
      "epoch": 0.005552833578311285,
      "grad_norm": 0.03677298128604889,
      "learning_rate": 9.851478631379982e-05,
      "loss": 10.3732,
      "step": 17
    },
    {
      "epoch": 0.005879470847623714,
      "grad_norm": 0.03571464121341705,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.3748,
      "step": 18
    },
    {
      "epoch": 0.005879470847623714,
      "eval_loss": 10.375162124633789,
      "eval_runtime": 22.0417,
      "eval_samples_per_second": 116.96,
      "eval_steps_per_second": 14.654,
      "step": 18
    },
    {
      "epoch": 0.006206108116936142,
      "grad_norm": 0.0428856797516346,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3732,
      "step": 19
    },
    {
      "epoch": 0.006532745386248571,
      "grad_norm": 0.03785776346921921,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.3741,
      "step": 20
    },
    {
      "epoch": 0.006859382655560999,
      "grad_norm": 0.03906534984707832,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.375,
      "step": 21
    },
    {
      "epoch": 0.007186019924873428,
      "grad_norm": 0.043429259210824966,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.3734,
      "step": 22
    },
    {
      "epoch": 0.0075126571941858565,
      "grad_norm": 0.04383184760808945,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.3738,
      "step": 23
    },
    {
      "epoch": 0.007839294463498285,
      "grad_norm": 0.04271635785698891,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.3761,
      "step": 24
    },
    {
      "epoch": 0.008165931732810714,
      "grad_norm": 0.04995786026120186,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3732,
      "step": 25
    },
    {
      "epoch": 0.008492569002123142,
      "grad_norm": 0.04129215329885483,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.374,
      "step": 26
    },
    {
      "epoch": 0.008819206271435572,
      "grad_norm": 0.0452185682952404,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.3727,
      "step": 27
    },
    {
      "epoch": 0.008819206271435572,
      "eval_loss": 10.374153137207031,
      "eval_runtime": 21.406,
      "eval_samples_per_second": 120.434,
      "eval_steps_per_second": 15.089,
      "step": 27
    },
    {
      "epoch": 0.009145843540748,
      "grad_norm": 0.04270987957715988,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3738,
      "step": 28
    },
    {
      "epoch": 0.009472480810060429,
      "grad_norm": 0.05155440792441368,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.3752,
      "step": 29
    },
    {
      "epoch": 0.009799118079372856,
      "grad_norm": 0.0561983697116375,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.3711,
      "step": 30
    },
    {
      "epoch": 0.010125755348685286,
      "grad_norm": 0.042896758764982224,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.3735,
      "step": 31
    },
    {
      "epoch": 0.010452392617997713,
      "grad_norm": 0.04372115805745125,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.3735,
      "step": 32
    },
    {
      "epoch": 0.010779029887310143,
      "grad_norm": 0.06329807639122009,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.3737,
      "step": 33
    },
    {
      "epoch": 0.01110566715662257,
      "grad_norm": 0.04135838523507118,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.3743,
      "step": 34
    },
    {
      "epoch": 0.011432304425935,
      "grad_norm": 0.04792993143200874,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.3752,
      "step": 35
    },
    {
      "epoch": 0.011758941695247428,
      "grad_norm": 0.05100570246577263,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.3727,
      "step": 36
    },
    {
      "epoch": 0.011758941695247428,
      "eval_loss": 10.373011589050293,
      "eval_runtime": 22.204,
      "eval_samples_per_second": 116.105,
      "eval_steps_per_second": 14.547,
      "step": 36
    },
    {
      "epoch": 0.012085578964559857,
      "grad_norm": 0.05363311618566513,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3726,
      "step": 37
    },
    {
      "epoch": 0.012412216233872285,
      "grad_norm": 0.06147367134690285,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.3733,
      "step": 38
    },
    {
      "epoch": 0.012738853503184714,
      "grad_norm": 0.04945583641529083,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.373,
      "step": 39
    },
    {
      "epoch": 0.013065490772497142,
      "grad_norm": 0.060909684747457504,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.3728,
      "step": 40
    },
    {
      "epoch": 0.013392128041809571,
      "grad_norm": 0.04293395206332207,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.3706,
      "step": 41
    },
    {
      "epoch": 0.013718765311121999,
      "grad_norm": 0.0527237206697464,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.3713,
      "step": 42
    },
    {
      "epoch": 0.014045402580434428,
      "grad_norm": 0.06157221272587776,
      "learning_rate": 7.033683215379002e-05,
      "loss": 10.3747,
      "step": 43
    },
    {
      "epoch": 0.014372039849746856,
      "grad_norm": 0.06624653190374374,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.3736,
      "step": 44
    },
    {
      "epoch": 0.014698677119059285,
      "grad_norm": 0.06559105962514877,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.3704,
      "step": 45
    },
    {
      "epoch": 0.014698677119059285,
      "eval_loss": 10.37177562713623,
      "eval_runtime": 21.8679,
      "eval_samples_per_second": 117.89,
      "eval_steps_per_second": 14.771,
      "step": 45
    },
    {
      "epoch": 0.015025314388371713,
      "grad_norm": 0.044589053839445114,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3708,
      "step": 46
    },
    {
      "epoch": 0.015351951657684142,
      "grad_norm": 0.06341821700334549,
      "learning_rate": 6.378186779084995e-05,
      "loss": 10.3708,
      "step": 47
    },
    {
      "epoch": 0.01567858892699657,
      "grad_norm": 0.04743089899420738,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.3722,
      "step": 48
    },
    {
      "epoch": 0.016005226196308998,
      "grad_norm": 0.06420129537582397,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 10.375,
      "step": 49
    },
    {
      "epoch": 0.01633186346562143,
      "grad_norm": 0.0634082779288292,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.3699,
      "step": 50
    },
    {
      "epoch": 0.016658500734933857,
      "grad_norm": 0.04990113526582718,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.3714,
      "step": 51
    },
    {
      "epoch": 0.016985138004246284,
      "grad_norm": 0.06637424975633621,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.3688,
      "step": 52
    },
    {
      "epoch": 0.017311775273558712,
      "grad_norm": 0.0678475871682167,
      "learning_rate": 5.348782368720626e-05,
      "loss": 10.3674,
      "step": 53
    },
    {
      "epoch": 0.017638412542871143,
      "grad_norm": 0.07442894577980042,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.3699,
      "step": 54
    },
    {
      "epoch": 0.017638412542871143,
      "eval_loss": 10.370558738708496,
      "eval_runtime": 21.5927,
      "eval_samples_per_second": 119.392,
      "eval_steps_per_second": 14.959,
      "step": 54
    },
    {
      "epoch": 0.01796504981218357,
      "grad_norm": 0.07772573083639145,
      "learning_rate": 5e-05,
      "loss": 10.3699,
      "step": 55
    },
    {
      "epoch": 0.018291687081496,
      "grad_norm": 0.060514897108078,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.3688,
      "step": 56
    },
    {
      "epoch": 0.018618324350808426,
      "grad_norm": 0.06120225787162781,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.372,
      "step": 57
    },
    {
      "epoch": 0.018944961620120857,
      "grad_norm": 0.0648784339427948,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.3732,
      "step": 58
    },
    {
      "epoch": 0.019271598889433285,
      "grad_norm": 0.07190015912055969,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 10.371,
      "step": 59
    },
    {
      "epoch": 0.019598236158745713,
      "grad_norm": 0.0784253478050232,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.3681,
      "step": 60
    },
    {
      "epoch": 0.01992487342805814,
      "grad_norm": 0.07030834257602692,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.3693,
      "step": 61
    },
    {
      "epoch": 0.02025151069737057,
      "grad_norm": 0.07749903947114944,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.3697,
      "step": 62
    },
    {
      "epoch": 0.020578147966683,
      "grad_norm": 0.07404929399490356,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.3712,
      "step": 63
    },
    {
      "epoch": 0.020578147966683,
      "eval_loss": 10.369466781616211,
      "eval_runtime": 22.1159,
      "eval_samples_per_second": 116.568,
      "eval_steps_per_second": 14.605,
      "step": 63
    },
    {
      "epoch": 0.020904785235995427,
      "grad_norm": 0.0778629407286644,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.369,
      "step": 64
    },
    {
      "epoch": 0.021231422505307854,
      "grad_norm": 0.07116811722517014,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.3683,
      "step": 65
    },
    {
      "epoch": 0.021558059774620286,
      "grad_norm": 0.06465199589729309,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.374,
      "step": 66
    },
    {
      "epoch": 0.021884697043932713,
      "grad_norm": 0.09270355850458145,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 10.3685,
      "step": 67
    },
    {
      "epoch": 0.02221133431324514,
      "grad_norm": 0.0799483060836792,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.3678,
      "step": 68
    },
    {
      "epoch": 0.02253797158255757,
      "grad_norm": 0.0683579221367836,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.3726,
      "step": 69
    },
    {
      "epoch": 0.02286460885187,
      "grad_norm": 0.07819787412881851,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.3682,
      "step": 70
    },
    {
      "epoch": 0.023191246121182427,
      "grad_norm": 0.0755452960729599,
      "learning_rate": 2.350403678833976e-05,
      "loss": 10.3687,
      "step": 71
    },
    {
      "epoch": 0.023517883390494855,
      "grad_norm": 0.09338651597499847,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.3684,
      "step": 72
    },
    {
      "epoch": 0.023517883390494855,
      "eval_loss": 10.368648529052734,
      "eval_runtime": 22.1111,
      "eval_samples_per_second": 116.593,
      "eval_steps_per_second": 14.608,
      "step": 72
    },
    {
      "epoch": 0.023844520659807283,
      "grad_norm": 0.07462280988693237,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3738,
      "step": 73
    },
    {
      "epoch": 0.024171157929119714,
      "grad_norm": 0.07140083611011505,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.3677,
      "step": 74
    },
    {
      "epoch": 0.02449779519843214,
      "grad_norm": 0.09304412454366684,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.3687,
      "step": 75
    },
    {
      "epoch": 0.02482443246774457,
      "grad_norm": 0.07405439764261246,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 10.3693,
      "step": 76
    },
    {
      "epoch": 0.025151069737056997,
      "grad_norm": 0.0959295704960823,
      "learning_rate": 1.526708147705013e-05,
      "loss": 10.3671,
      "step": 77
    },
    {
      "epoch": 0.025477707006369428,
      "grad_norm": 0.0648365393280983,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.3704,
      "step": 78
    },
    {
      "epoch": 0.025804344275681856,
      "grad_norm": 0.0828406810760498,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 10.368,
      "step": 79
    },
    {
      "epoch": 0.026130981544994283,
      "grad_norm": 0.08714064955711365,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.3676,
      "step": 80
    },
    {
      "epoch": 0.02645761881430671,
      "grad_norm": 0.10075332224369049,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 10.3672,
      "step": 81
    },
    {
      "epoch": 0.02645761881430671,
      "eval_loss": 10.36816120147705,
      "eval_runtime": 21.5241,
      "eval_samples_per_second": 119.773,
      "eval_steps_per_second": 15.006,
      "step": 81
    },
    {
      "epoch": 0.026784256083619142,
      "grad_norm": 0.10861089080572128,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.3657,
      "step": 82
    },
    {
      "epoch": 0.02711089335293157,
      "grad_norm": 0.07788481563329697,
      "learning_rate": 8.548121372247918e-06,
      "loss": 10.3682,
      "step": 83
    },
    {
      "epoch": 0.027437530622243998,
      "grad_norm": 0.07634954899549484,
      "learning_rate": 7.597595192178702e-06,
      "loss": 10.3706,
      "step": 84
    },
    {
      "epoch": 0.027764167891556425,
      "grad_norm": 0.09162547439336777,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.3662,
      "step": 85
    },
    {
      "epoch": 0.028090805160868856,
      "grad_norm": 0.08597175776958466,
      "learning_rate": 5.852620357053651e-06,
      "loss": 10.3692,
      "step": 86
    },
    {
      "epoch": 0.028417442430181284,
      "grad_norm": 0.08688751608133316,
      "learning_rate": 5.060297685041659e-06,
      "loss": 10.3656,
      "step": 87
    },
    {
      "epoch": 0.02874407969949371,
      "grad_norm": 0.08870881795883179,
      "learning_rate": 4.322727117869951e-06,
      "loss": 10.3652,
      "step": 88
    },
    {
      "epoch": 0.02907071696880614,
      "grad_norm": 0.09233355522155762,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 10.3674,
      "step": 89
    },
    {
      "epoch": 0.02939735423811857,
      "grad_norm": 0.08547327667474747,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.3674,
      "step": 90
    },
    {
      "epoch": 0.02939735423811857,
      "eval_loss": 10.367944717407227,
      "eval_runtime": 22.0868,
      "eval_samples_per_second": 116.721,
      "eval_steps_per_second": 14.624,
      "step": 90
    },
    {
      "epoch": 0.029723991507430998,
      "grad_norm": 0.10347817093133926,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.366,
      "step": 91
    },
    {
      "epoch": 0.030050628776743426,
      "grad_norm": 0.09250044822692871,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 10.3687,
      "step": 92
    },
    {
      "epoch": 0.030377266046055854,
      "grad_norm": 0.07645335793495178,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 10.3715,
      "step": 93
    },
    {
      "epoch": 0.030703903315368285,
      "grad_norm": 0.09881287068128586,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.3702,
      "step": 94
    },
    {
      "epoch": 0.031030540584680712,
      "grad_norm": 0.08971241861581802,
      "learning_rate": 7.596123493895991e-07,
      "loss": 10.3699,
      "step": 95
    },
    {
      "epoch": 0.03135717785399314,
      "grad_norm": 0.09617859870195389,
      "learning_rate": 4.865965629214819e-07,
      "loss": 10.3684,
      "step": 96
    },
    {
      "epoch": 0.03168381512330557,
      "grad_norm": 0.09534001350402832,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 10.3673,
      "step": 97
    },
    {
      "epoch": 0.032010452392617995,
      "grad_norm": 0.11082008481025696,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 10.3673,
      "step": 98
    },
    {
      "epoch": 0.03233708966193043,
      "grad_norm": 0.08359237015247345,
      "learning_rate": 3.04586490452119e-08,
      "loss": 10.3677,
      "step": 99
    },
    {
      "epoch": 0.03233708966193043,
      "eval_loss": 10.367908477783203,
      "eval_runtime": 21.9179,
      "eval_samples_per_second": 117.621,
      "eval_steps_per_second": 14.737,
      "step": 99
    },
    {
      "epoch": 0.03266372693124286,
      "grad_norm": 0.09743411839008331,
      "learning_rate": 0.0,
      "loss": 10.3647,
      "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": 5884025241600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}