{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02600442075152776,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002600442075152776,
      "grad_norm": 0.02279164083302021,
      "learning_rate": 1e-05,
      "loss": 10.3782,
      "step": 1
    },
    {
      "epoch": 0.0002600442075152776,
      "eval_loss": 10.382096290588379,
      "eval_runtime": 24.8644,
      "eval_samples_per_second": 130.267,
      "eval_steps_per_second": 16.288,
      "step": 1
    },
    {
      "epoch": 0.0005200884150305552,
      "grad_norm": 0.027484985068440437,
      "learning_rate": 2e-05,
      "loss": 10.3802,
      "step": 2
    },
    {
      "epoch": 0.0007801326225458328,
      "grad_norm": 0.024028444662690163,
      "learning_rate": 3e-05,
      "loss": 10.3797,
      "step": 3
    },
    {
      "epoch": 0.0010401768300611104,
      "grad_norm": 0.029752936214208603,
      "learning_rate": 4e-05,
      "loss": 10.3782,
      "step": 4
    },
    {
      "epoch": 0.001300221037576388,
      "grad_norm": 0.026785146445035934,
      "learning_rate": 5e-05,
      "loss": 10.3819,
      "step": 5
    },
    {
      "epoch": 0.0015602652450916656,
      "grad_norm": 0.024060087278485298,
      "learning_rate": 6e-05,
      "loss": 10.3817,
      "step": 6
    },
    {
      "epoch": 0.0018203094526069432,
      "grad_norm": 0.023959027603268623,
      "learning_rate": 7e-05,
      "loss": 10.3831,
      "step": 7
    },
    {
      "epoch": 0.002080353660122221,
      "grad_norm": 0.025802776217460632,
      "learning_rate": 8e-05,
      "loss": 10.3809,
      "step": 8
    },
    {
      "epoch": 0.0023403978676374984,
      "grad_norm": 0.02310967445373535,
      "learning_rate": 9e-05,
      "loss": 10.3836,
      "step": 9
    },
    {
      "epoch": 0.0023403978676374984,
      "eval_loss": 10.381851196289062,
      "eval_runtime": 25.7478,
      "eval_samples_per_second": 125.797,
      "eval_steps_per_second": 15.73,
      "step": 9
    },
    {
      "epoch": 0.002600442075152776,
      "grad_norm": 0.026796067133545876,
      "learning_rate": 0.0001,
      "loss": 10.3811,
      "step": 10
    },
    {
      "epoch": 0.0028604862826680537,
      "grad_norm": 0.04965611919760704,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.3798,
      "step": 11
    },
    {
      "epoch": 0.0031205304901833313,
      "grad_norm": 0.024298246949911118,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.3828,
      "step": 12
    },
    {
      "epoch": 0.003380574697698609,
      "grad_norm": 0.024884523823857307,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.3814,
      "step": 13
    },
    {
      "epoch": 0.0036406189052138865,
      "grad_norm": 0.023707769811153412,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.3819,
      "step": 14
    },
    {
      "epoch": 0.003900663112729164,
      "grad_norm": 0.027032267302274704,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.3842,
      "step": 15
    },
    {
      "epoch": 0.004160707320244442,
      "grad_norm": 0.020228637382388115,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.3777,
      "step": 16
    },
    {
      "epoch": 0.004420751527759719,
      "grad_norm": 0.021995818242430687,
      "learning_rate": 9.851478631379982e-05,
      "loss": 10.3832,
      "step": 17
    },
    {
      "epoch": 0.004680795735274997,
      "grad_norm": 0.02389182150363922,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.3844,
      "step": 18
    },
    {
      "epoch": 0.004680795735274997,
      "eval_loss": 10.38124942779541,
      "eval_runtime": 25.5914,
      "eval_samples_per_second": 126.566,
      "eval_steps_per_second": 15.826,
      "step": 18
    },
    {
      "epoch": 0.0049408399427902745,
      "grad_norm": 0.021635526791214943,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3828,
      "step": 19
    },
    {
      "epoch": 0.005200884150305552,
      "grad_norm": 0.023616788908839226,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.3831,
      "step": 20
    },
    {
      "epoch": 0.00546092835782083,
      "grad_norm": 0.02443654276430607,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.3821,
      "step": 21
    },
    {
      "epoch": 0.005720972565336107,
      "grad_norm": 0.02596656046807766,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.3781,
      "step": 22
    },
    {
      "epoch": 0.005981016772851385,
      "grad_norm": 0.02593740075826645,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.379,
      "step": 23
    },
    {
      "epoch": 0.0062410609803666625,
      "grad_norm": 0.026120077818632126,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.382,
      "step": 24
    },
    {
      "epoch": 0.00650110518788194,
      "grad_norm": 0.02591986022889614,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3816,
      "step": 25
    },
    {
      "epoch": 0.006761149395397218,
      "grad_norm": 0.025706559419631958,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.3823,
      "step": 26
    },
    {
      "epoch": 0.007021193602912495,
      "grad_norm": 0.02481803484261036,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.3805,
      "step": 27
    },
    {
      "epoch": 0.007021193602912495,
      "eval_loss": 10.380610466003418,
      "eval_runtime": 25.0856,
      "eval_samples_per_second": 129.118,
      "eval_steps_per_second": 16.145,
      "step": 27
    },
    {
      "epoch": 0.007281237810427773,
      "grad_norm": 0.030223438516259193,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3822,
      "step": 28
    },
    {
      "epoch": 0.0075412820179430505,
      "grad_norm": 0.025263188406825066,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.3801,
      "step": 29
    },
    {
      "epoch": 0.007801326225458328,
      "grad_norm": 0.02552811987698078,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.3793,
      "step": 30
    },
    {
      "epoch": 0.008061370432973605,
      "grad_norm": 0.028646033257246017,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.3795,
      "step": 31
    },
    {
      "epoch": 0.008321414640488883,
      "grad_norm": 0.03234689310193062,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.3834,
      "step": 32
    },
    {
      "epoch": 0.00858145884800416,
      "grad_norm": 0.030488982796669006,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.377,
      "step": 33
    },
    {
      "epoch": 0.008841503055519439,
      "grad_norm": 0.029688188806176186,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.3787,
      "step": 34
    },
    {
      "epoch": 0.009101547263034715,
      "grad_norm": 0.03060000017285347,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.3764,
      "step": 35
    },
    {
      "epoch": 0.009361591470549994,
      "grad_norm": 0.02977304719388485,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.3778,
      "step": 36
    },
    {
      "epoch": 0.009361591470549994,
      "eval_loss": 10.379910469055176,
      "eval_runtime": 25.7816,
      "eval_samples_per_second": 125.632,
      "eval_steps_per_second": 15.709,
      "step": 36
    },
    {
      "epoch": 0.00962163567806527,
      "grad_norm": 0.025964127853512764,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3808,
      "step": 37
    },
    {
      "epoch": 0.009881679885580549,
      "grad_norm": 0.024992648512125015,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.3817,
      "step": 38
    },
    {
      "epoch": 0.010141724093095826,
      "grad_norm": 0.04504212737083435,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.3787,
      "step": 39
    },
    {
      "epoch": 0.010401768300611104,
      "grad_norm": 0.0340939424932003,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.3802,
      "step": 40
    },
    {
      "epoch": 0.010661812508126381,
      "grad_norm": 0.03986920788884163,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.3812,
      "step": 41
    },
    {
      "epoch": 0.01092185671564166,
      "grad_norm": 0.030954543501138687,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.3783,
      "step": 42
    },
    {
      "epoch": 0.011181900923156936,
      "grad_norm": 0.040646303445100784,
      "learning_rate": 7.033683215379002e-05,
      "loss": 10.3811,
      "step": 43
    },
    {
      "epoch": 0.011441945130672215,
      "grad_norm": 0.036880068480968475,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.3813,
      "step": 44
    },
    {
      "epoch": 0.011701989338187491,
      "grad_norm": 0.03328927606344223,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.3795,
      "step": 45
    },
    {
      "epoch": 0.011701989338187491,
      "eval_loss": 10.379190444946289,
      "eval_runtime": 25.8433,
      "eval_samples_per_second": 125.332,
      "eval_steps_per_second": 15.671,
      "step": 45
    },
    {
      "epoch": 0.01196203354570277,
      "grad_norm": 0.03431277722120285,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3757,
      "step": 46
    },
    {
      "epoch": 0.012222077753218047,
      "grad_norm": 0.03707456961274147,
      "learning_rate": 6.378186779084995e-05,
      "loss": 10.3791,
      "step": 47
    },
    {
      "epoch": 0.012482121960733325,
      "grad_norm": 0.0343763530254364,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.3798,
      "step": 48
    },
    {
      "epoch": 0.012742166168248602,
      "grad_norm": 0.035991370677948,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 10.3768,
      "step": 49
    },
    {
      "epoch": 0.01300221037576388,
      "grad_norm": 0.04727911949157715,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.3791,
      "step": 50
    },
    {
      "epoch": 0.013262254583279157,
      "grad_norm": 0.03601168096065521,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.3785,
      "step": 51
    },
    {
      "epoch": 0.013522298790794435,
      "grad_norm": 0.0392109639942646,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.3772,
      "step": 52
    },
    {
      "epoch": 0.013782342998309712,
      "grad_norm": 0.038347356021404266,
      "learning_rate": 5.348782368720626e-05,
      "loss": 10.3782,
      "step": 53
    },
    {
      "epoch": 0.01404238720582499,
      "grad_norm": 0.05170854181051254,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.3791,
      "step": 54
    },
    {
      "epoch": 0.01404238720582499,
      "eval_loss": 10.378482818603516,
      "eval_runtime": 25.1756,
      "eval_samples_per_second": 128.657,
      "eval_steps_per_second": 16.087,
      "step": 54
    },
    {
      "epoch": 0.014302431413340267,
      "grad_norm": 0.0428142324090004,
      "learning_rate": 5e-05,
      "loss": 10.3794,
      "step": 55
    },
    {
      "epoch": 0.014562475620855546,
      "grad_norm": 0.037890929728746414,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.3741,
      "step": 56
    },
    {
      "epoch": 0.014822519828370823,
      "grad_norm": 0.03927186131477356,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.3771,
      "step": 57
    },
    {
      "epoch": 0.015082564035886101,
      "grad_norm": 0.03995467722415924,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.3758,
      "step": 58
    },
    {
      "epoch": 0.015342608243401378,
      "grad_norm": 0.04345840960741043,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 10.3802,
      "step": 59
    },
    {
      "epoch": 0.015602652450916656,
      "grad_norm": 0.03900769725441933,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.3786,
      "step": 60
    },
    {
      "epoch": 0.015862696658431933,
      "grad_norm": 0.04522537812590599,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.3794,
      "step": 61
    },
    {
      "epoch": 0.01612274086594721,
      "grad_norm": 0.04456991329789162,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.38,
      "step": 62
    },
    {
      "epoch": 0.01638278507346249,
      "grad_norm": 0.04366768151521683,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.38,
      "step": 63
    },
    {
      "epoch": 0.01638278507346249,
      "eval_loss": 10.377856254577637,
      "eval_runtime": 25.6986,
      "eval_samples_per_second": 126.038,
      "eval_steps_per_second": 15.76,
      "step": 63
    },
    {
      "epoch": 0.016642829280977767,
      "grad_norm": 0.037021130323410034,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.3788,
      "step": 64
    },
    {
      "epoch": 0.016902873488493043,
      "grad_norm": 0.05037117004394531,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.3793,
      "step": 65
    },
    {
      "epoch": 0.01716291769600832,
      "grad_norm": 0.04364752769470215,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.3806,
      "step": 66
    },
    {
      "epoch": 0.0174229619035236,
      "grad_norm": 0.0497322604060173,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 10.3793,
      "step": 67
    },
    {
      "epoch": 0.017683006111038877,
      "grad_norm": 0.0477624237537384,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.3787,
      "step": 68
    },
    {
      "epoch": 0.017943050318554154,
      "grad_norm": 0.04558240994811058,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.3801,
      "step": 69
    },
    {
      "epoch": 0.01820309452606943,
      "grad_norm": 0.03950976952910423,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.3733,
      "step": 70
    },
    {
      "epoch": 0.01846313873358471,
      "grad_norm": 0.04475395381450653,
      "learning_rate": 2.350403678833976e-05,
      "loss": 10.3772,
      "step": 71
    },
    {
      "epoch": 0.018723182941099988,
      "grad_norm": 0.058802977204322815,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.3766,
      "step": 72
    },
    {
      "epoch": 0.018723182941099988,
      "eval_loss": 10.377392768859863,
      "eval_runtime": 25.9933,
      "eval_samples_per_second": 124.609,
      "eval_steps_per_second": 15.581,
      "step": 72
    },
    {
      "epoch": 0.018983227148615264,
      "grad_norm": 0.04606263339519501,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3784,
      "step": 73
    },
    {
      "epoch": 0.01924327135613054,
      "grad_norm": 0.044724252074956894,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.3761,
      "step": 74
    },
    {
      "epoch": 0.01950331556364582,
      "grad_norm": 0.04722006618976593,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.3747,
      "step": 75
    },
    {
      "epoch": 0.019763359771161098,
      "grad_norm": 0.045965924859046936,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 10.3776,
      "step": 76
    },
    {
      "epoch": 0.020023403978676375,
      "grad_norm": 0.04359443113207817,
      "learning_rate": 1.526708147705013e-05,
      "loss": 10.3771,
      "step": 77
    },
    {
      "epoch": 0.02028344818619165,
      "grad_norm": 0.045900508761405945,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.378,
      "step": 78
    },
    {
      "epoch": 0.02054349239370693,
      "grad_norm": 0.054575856775045395,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 10.3755,
      "step": 79
    },
    {
      "epoch": 0.02080353660122221,
      "grad_norm": 0.04699670523405075,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.3778,
      "step": 80
    },
    {
      "epoch": 0.021063580808737485,
      "grad_norm": 0.059355478733778,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 10.3729,
      "step": 81
    },
    {
      "epoch": 0.021063580808737485,
      "eval_loss": 10.377110481262207,
      "eval_runtime": 25.0267,
      "eval_samples_per_second": 129.422,
      "eval_steps_per_second": 16.183,
      "step": 81
    },
    {
      "epoch": 0.021323625016252762,
      "grad_norm": 0.05459514260292053,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.3779,
      "step": 82
    },
    {
      "epoch": 0.021583669223768042,
      "grad_norm": 0.04532025381922722,
      "learning_rate": 8.548121372247918e-06,
      "loss": 10.3779,
      "step": 83
    },
    {
      "epoch": 0.02184371343128332,
      "grad_norm": 0.051146797835826874,
      "learning_rate": 7.597595192178702e-06,
      "loss": 10.3819,
      "step": 84
    },
    {
      "epoch": 0.022103757638798596,
      "grad_norm": 0.05978747457265854,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.375,
      "step": 85
    },
    {
      "epoch": 0.022363801846313872,
      "grad_norm": 0.04381445050239563,
      "learning_rate": 5.852620357053651e-06,
      "loss": 10.3791,
      "step": 86
    },
    {
      "epoch": 0.022623846053829152,
      "grad_norm": 0.059307560324668884,
      "learning_rate": 5.060297685041659e-06,
      "loss": 10.376,
      "step": 87
    },
    {
      "epoch": 0.02288389026134443,
      "grad_norm": 0.0550258494913578,
      "learning_rate": 4.322727117869951e-06,
      "loss": 10.377,
      "step": 88
    },
    {
      "epoch": 0.023143934468859706,
      "grad_norm": 0.04555179178714752,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 10.3759,
      "step": 89
    },
    {
      "epoch": 0.023403978676374983,
      "grad_norm": 0.05648469924926758,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.3772,
      "step": 90
    },
    {
      "epoch": 0.023403978676374983,
      "eval_loss": 10.376992225646973,
      "eval_runtime": 25.6416,
      "eval_samples_per_second": 126.318,
      "eval_steps_per_second": 15.795,
      "step": 90
    },
    {
      "epoch": 0.023664022883890263,
      "grad_norm": 0.050564419478178024,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.3792,
      "step": 91
    },
    {
      "epoch": 0.02392406709140554,
      "grad_norm": 0.05184341222047806,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 10.3734,
      "step": 92
    },
    {
      "epoch": 0.024184111298920816,
      "grad_norm": 0.04729103296995163,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 10.3784,
      "step": 93
    },
    {
      "epoch": 0.024444155506436093,
      "grad_norm": 0.04831608757376671,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.3771,
      "step": 94
    },
    {
      "epoch": 0.024704199713951373,
      "grad_norm": 0.055237192660570145,
      "learning_rate": 7.596123493895991e-07,
      "loss": 10.3786,
      "step": 95
    },
    {
      "epoch": 0.02496424392146665,
      "grad_norm": 0.051754217594861984,
      "learning_rate": 4.865965629214819e-07,
      "loss": 10.3785,
      "step": 96
    },
    {
      "epoch": 0.025224288128981927,
      "grad_norm": 0.048474401235580444,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 10.3787,
      "step": 97
    },
    {
      "epoch": 0.025484332336497204,
      "grad_norm": 0.04937809333205223,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 10.3745,
      "step": 98
    },
    {
      "epoch": 0.025744376544012484,
      "grad_norm": 0.04878290742635727,
      "learning_rate": 3.04586490452119e-08,
      "loss": 10.3776,
      "step": 99
    },
    {
      "epoch": 0.025744376544012484,
      "eval_loss": 10.376970291137695,
      "eval_runtime": 25.8552,
      "eval_samples_per_second": 125.275,
      "eval_steps_per_second": 15.664,
      "step": 99
    },
    {
      "epoch": 0.02600442075152776,
      "grad_norm": 0.0496150404214859,
      "learning_rate": 0.0,
      "loss": 10.3777,
      "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": 5727117901824.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}