{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008513898940019582,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.513898940019582e-05,
      "grad_norm": 0.06632853299379349,
      "learning_rate": 1e-05,
      "loss": 10.3844,
      "step": 1
    },
    {
      "epoch": 8.513898940019582e-05,
      "eval_loss": 10.380781173706055,
      "eval_runtime": 37.6703,
      "eval_samples_per_second": 262.567,
      "eval_steps_per_second": 32.838,
      "step": 1
    },
    {
      "epoch": 0.00017027797880039163,
      "grad_norm": 0.06305789947509766,
      "learning_rate": 2e-05,
      "loss": 10.3866,
      "step": 2
    },
    {
      "epoch": 0.0002554169682005875,
      "grad_norm": 0.09040896594524384,
      "learning_rate": 3e-05,
      "loss": 10.3699,
      "step": 3
    },
    {
      "epoch": 0.00034055595760078326,
      "grad_norm": 0.08260149508714676,
      "learning_rate": 4e-05,
      "loss": 10.3876,
      "step": 4
    },
    {
      "epoch": 0.0004256949470009791,
      "grad_norm": 0.09195930510759354,
      "learning_rate": 5e-05,
      "loss": 10.39,
      "step": 5
    },
    {
      "epoch": 0.000510833936401175,
      "grad_norm": 0.08319511264562607,
      "learning_rate": 6e-05,
      "loss": 10.3756,
      "step": 6
    },
    {
      "epoch": 0.0005959729258013707,
      "grad_norm": 0.07701607048511505,
      "learning_rate": 7e-05,
      "loss": 10.3714,
      "step": 7
    },
    {
      "epoch": 0.0006811119152015665,
      "grad_norm": 0.08848275989294052,
      "learning_rate": 8e-05,
      "loss": 10.3649,
      "step": 8
    },
    {
      "epoch": 0.0007662509046017624,
      "grad_norm": 0.07215868681669235,
      "learning_rate": 9e-05,
      "loss": 10.3825,
      "step": 9
    },
    {
      "epoch": 0.0007662509046017624,
      "eval_loss": 10.380110740661621,
      "eval_runtime": 37.0373,
      "eval_samples_per_second": 267.055,
      "eval_steps_per_second": 33.399,
      "step": 9
    },
    {
      "epoch": 0.0008513898940019582,
      "grad_norm": 0.0638326108455658,
      "learning_rate": 0.0001,
      "loss": 10.376,
      "step": 10
    },
    {
      "epoch": 0.000936528883402154,
      "grad_norm": 0.0767514705657959,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.3839,
      "step": 11
    },
    {
      "epoch": 0.00102166787280235,
      "grad_norm": 0.06683874130249023,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.3901,
      "step": 12
    },
    {
      "epoch": 0.0011068068622025456,
      "grad_norm": 0.06641669571399689,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.3774,
      "step": 13
    },
    {
      "epoch": 0.0011919458516027415,
      "grad_norm": 0.05661563575267792,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.3847,
      "step": 14
    },
    {
      "epoch": 0.0012770848410029374,
      "grad_norm": 0.08233150839805603,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.3761,
      "step": 15
    },
    {
      "epoch": 0.001362223830403133,
      "grad_norm": 0.06432665884494781,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.3694,
      "step": 16
    },
    {
      "epoch": 0.001447362819803329,
      "grad_norm": 0.08495861291885376,
      "learning_rate": 9.851478631379982e-05,
      "loss": 10.3777,
      "step": 17
    },
    {
      "epoch": 0.0015325018092035248,
      "grad_norm": 0.06713090091943741,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.3927,
      "step": 18
    },
    {
      "epoch": 0.0015325018092035248,
      "eval_loss": 10.378459930419922,
      "eval_runtime": 36.9921,
      "eval_samples_per_second": 267.381,
      "eval_steps_per_second": 33.44,
      "step": 18
    },
    {
      "epoch": 0.0016176407986037205,
      "grad_norm": 0.07406238466501236,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3736,
      "step": 19
    },
    {
      "epoch": 0.0017027797880039164,
      "grad_norm": 0.06992701441049576,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.3714,
      "step": 20
    },
    {
      "epoch": 0.001787918777404112,
      "grad_norm": 0.0749615877866745,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.372,
      "step": 21
    },
    {
      "epoch": 0.001873057766804308,
      "grad_norm": 0.06695009022951126,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.3943,
      "step": 22
    },
    {
      "epoch": 0.0019581967562045037,
      "grad_norm": 0.058970991522073746,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.3757,
      "step": 23
    },
    {
      "epoch": 0.0020433357456047,
      "grad_norm": 0.060394152998924255,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.3769,
      "step": 24
    },
    {
      "epoch": 0.0021284747350048955,
      "grad_norm": 0.07403624802827835,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3898,
      "step": 25
    },
    {
      "epoch": 0.002213613724405091,
      "grad_norm": 0.06255259364843369,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.3848,
      "step": 26
    },
    {
      "epoch": 0.0022987527138052873,
      "grad_norm": 0.07093428820371628,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.3834,
      "step": 27
    },
    {
      "epoch": 0.0022987527138052873,
      "eval_loss": 10.376791000366211,
      "eval_runtime": 37.1822,
      "eval_samples_per_second": 266.014,
      "eval_steps_per_second": 33.269,
      "step": 27
    },
    {
      "epoch": 0.002383891703205483,
      "grad_norm": 0.06431137025356293,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3878,
      "step": 28
    },
    {
      "epoch": 0.0024690306926056786,
      "grad_norm": 0.06749837845563889,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.3917,
      "step": 29
    },
    {
      "epoch": 0.0025541696820058747,
      "grad_norm": 0.06856685876846313,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.3812,
      "step": 30
    },
    {
      "epoch": 0.0026393086714060704,
      "grad_norm": 0.07790417969226837,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.3734,
      "step": 31
    },
    {
      "epoch": 0.002724447660806266,
      "grad_norm": 0.06906121224164963,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.3667,
      "step": 32
    },
    {
      "epoch": 0.0028095866502064622,
      "grad_norm": 0.07379811257123947,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.3681,
      "step": 33
    },
    {
      "epoch": 0.002894725639606658,
      "grad_norm": 0.0777546837925911,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.3742,
      "step": 34
    },
    {
      "epoch": 0.0029798646290068536,
      "grad_norm": 0.09084642678499222,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.3725,
      "step": 35
    },
    {
      "epoch": 0.0030650036184070497,
      "grad_norm": 0.07533272355794907,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.3616,
      "step": 36
    },
    {
      "epoch": 0.0030650036184070497,
      "eval_loss": 10.3751859664917,
      "eval_runtime": 37.0132,
      "eval_samples_per_second": 267.229,
      "eval_steps_per_second": 33.42,
      "step": 36
    },
    {
      "epoch": 0.0031501426078072454,
      "grad_norm": 0.09557131677865982,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3627,
      "step": 37
    },
    {
      "epoch": 0.003235281597207441,
      "grad_norm": 0.086721271276474,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.3797,
      "step": 38
    },
    {
      "epoch": 0.003320420586607637,
      "grad_norm": 0.0951017513871193,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.3642,
      "step": 39
    },
    {
      "epoch": 0.003405559576007833,
      "grad_norm": 0.08322468400001526,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.3718,
      "step": 40
    },
    {
      "epoch": 0.0034906985654080285,
      "grad_norm": 0.08715411275625229,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.3912,
      "step": 41
    },
    {
      "epoch": 0.003575837554808224,
      "grad_norm": 0.07306662946939468,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.3831,
      "step": 42
    },
    {
      "epoch": 0.0036609765442084203,
      "grad_norm": 0.07265879958868027,
      "learning_rate": 7.033683215379002e-05,
      "loss": 10.3775,
      "step": 43
    },
    {
      "epoch": 0.003746115533608616,
      "grad_norm": 0.07239469140768051,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.3708,
      "step": 44
    },
    {
      "epoch": 0.0038312545230088117,
      "grad_norm": 0.06718676537275314,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.3772,
      "step": 45
    },
    {
      "epoch": 0.0038312545230088117,
      "eval_loss": 10.373581886291504,
      "eval_runtime": 36.9465,
      "eval_samples_per_second": 267.712,
      "eval_steps_per_second": 33.481,
      "step": 45
    },
    {
      "epoch": 0.003916393512409007,
      "grad_norm": 0.1044333428144455,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3736,
      "step": 46
    },
    {
      "epoch": 0.004001532501809204,
      "grad_norm": 0.09110475331544876,
      "learning_rate": 6.378186779084995e-05,
      "loss": 10.3743,
      "step": 47
    },
    {
      "epoch": 0.0040866714912094,
      "grad_norm": 0.08908325433731079,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.3715,
      "step": 48
    },
    {
      "epoch": 0.004171810480609595,
      "grad_norm": 0.09201818704605103,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 10.3745,
      "step": 49
    },
    {
      "epoch": 0.004256949470009791,
      "grad_norm": 0.08138486742973328,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.3831,
      "step": 50
    },
    {
      "epoch": 0.004342088459409987,
      "grad_norm": 0.0844358429312706,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.3747,
      "step": 51
    },
    {
      "epoch": 0.004427227448810182,
      "grad_norm": 0.09414055198431015,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.3813,
      "step": 52
    },
    {
      "epoch": 0.004512366438210379,
      "grad_norm": 0.08644277602434158,
      "learning_rate": 5.348782368720626e-05,
      "loss": 10.3869,
      "step": 53
    },
    {
      "epoch": 0.0045975054276105745,
      "grad_norm": 0.07738783955574036,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.3747,
      "step": 54
    },
    {
      "epoch": 0.0045975054276105745,
      "eval_loss": 10.372137069702148,
      "eval_runtime": 37.151,
      "eval_samples_per_second": 266.238,
      "eval_steps_per_second": 33.297,
      "step": 54
    },
    {
      "epoch": 0.00468264441701077,
      "grad_norm": 0.09179961681365967,
      "learning_rate": 5e-05,
      "loss": 10.373,
      "step": 55
    },
    {
      "epoch": 0.004767783406410966,
      "grad_norm": 0.07193462550640106,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.3692,
      "step": 56
    },
    {
      "epoch": 0.004852922395811162,
      "grad_norm": 0.09961500763893127,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.3609,
      "step": 57
    },
    {
      "epoch": 0.004938061385211357,
      "grad_norm": 0.08729062229394913,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.3676,
      "step": 58
    },
    {
      "epoch": 0.005023200374611553,
      "grad_norm": 0.10287671536207199,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 10.3811,
      "step": 59
    },
    {
      "epoch": 0.0051083393640117495,
      "grad_norm": 0.09059132635593414,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.3659,
      "step": 60
    },
    {
      "epoch": 0.005193478353411945,
      "grad_norm": 0.08913256973028183,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.3675,
      "step": 61
    },
    {
      "epoch": 0.005278617342812141,
      "grad_norm": 0.11724508553743362,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.3531,
      "step": 62
    },
    {
      "epoch": 0.0053637563322123365,
      "grad_norm": 0.08967398852109909,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.3838,
      "step": 63
    },
    {
      "epoch": 0.0053637563322123365,
      "eval_loss": 10.370929718017578,
      "eval_runtime": 36.968,
      "eval_samples_per_second": 267.556,
      "eval_steps_per_second": 33.461,
      "step": 63
    },
    {
      "epoch": 0.005448895321612532,
      "grad_norm": 0.1029573306441307,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.3673,
      "step": 64
    },
    {
      "epoch": 0.005534034311012728,
      "grad_norm": 0.09590195119380951,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.3727,
      "step": 65
    },
    {
      "epoch": 0.0056191733004129244,
      "grad_norm": 0.11425720155239105,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.3523,
      "step": 66
    },
    {
      "epoch": 0.00570431228981312,
      "grad_norm": 0.11035782098770142,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 10.3534,
      "step": 67
    },
    {
      "epoch": 0.005789451279213316,
      "grad_norm": 0.11257296800613403,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.381,
      "step": 68
    },
    {
      "epoch": 0.0058745902686135115,
      "grad_norm": 0.1037292331457138,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.3618,
      "step": 69
    },
    {
      "epoch": 0.005959729258013707,
      "grad_norm": 0.08522353321313858,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.3707,
      "step": 70
    },
    {
      "epoch": 0.006044868247413903,
      "grad_norm": 0.12336738407611847,
      "learning_rate": 2.350403678833976e-05,
      "loss": 10.373,
      "step": 71
    },
    {
      "epoch": 0.006130007236814099,
      "grad_norm": 0.103644460439682,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.367,
      "step": 72
    },
    {
      "epoch": 0.006130007236814099,
      "eval_loss": 10.370004653930664,
      "eval_runtime": 36.9487,
      "eval_samples_per_second": 267.696,
      "eval_steps_per_second": 33.479,
      "step": 72
    },
    {
      "epoch": 0.006215146226214295,
      "grad_norm": 0.09287124127149582,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3768,
      "step": 73
    },
    {
      "epoch": 0.006300285215614491,
      "grad_norm": 0.09806761145591736,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.3714,
      "step": 74
    },
    {
      "epoch": 0.0063854242050146864,
      "grad_norm": 0.10573066025972366,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.3675,
      "step": 75
    },
    {
      "epoch": 0.006470563194414882,
      "grad_norm": 0.08556344360113144,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 10.3805,
      "step": 76
    },
    {
      "epoch": 0.006555702183815078,
      "grad_norm": 0.10135341435670853,
      "learning_rate": 1.526708147705013e-05,
      "loss": 10.3807,
      "step": 77
    },
    {
      "epoch": 0.006640841173215274,
      "grad_norm": 0.10160138458013535,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.3755,
      "step": 78
    },
    {
      "epoch": 0.00672598016261547,
      "grad_norm": 0.10789739340543747,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 10.3772,
      "step": 79
    },
    {
      "epoch": 0.006811119152015666,
      "grad_norm": 0.09456997364759445,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.3725,
      "step": 80
    },
    {
      "epoch": 0.006896258141415861,
      "grad_norm": 0.09812531620264053,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 10.375,
      "step": 81
    },
    {
      "epoch": 0.006896258141415861,
      "eval_loss": 10.369479179382324,
      "eval_runtime": 37.0829,
      "eval_samples_per_second": 266.726,
      "eval_steps_per_second": 33.358,
      "step": 81
    },
    {
      "epoch": 0.006981397130816057,
      "grad_norm": 0.0770481675863266,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.3743,
      "step": 82
    },
    {
      "epoch": 0.007066536120216253,
      "grad_norm": 0.1046832948923111,
      "learning_rate": 8.548121372247918e-06,
      "loss": 10.3652,
      "step": 83
    },
    {
      "epoch": 0.007151675109616448,
      "grad_norm": 0.09526332467794418,
      "learning_rate": 7.597595192178702e-06,
      "loss": 10.3581,
      "step": 84
    },
    {
      "epoch": 0.007236814099016645,
      "grad_norm": 0.1255982220172882,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.3702,
      "step": 85
    },
    {
      "epoch": 0.007321953088416841,
      "grad_norm": 0.07898397743701935,
      "learning_rate": 5.852620357053651e-06,
      "loss": 10.3798,
      "step": 86
    },
    {
      "epoch": 0.007407092077817036,
      "grad_norm": 0.09931027144193649,
      "learning_rate": 5.060297685041659e-06,
      "loss": 10.3753,
      "step": 87
    },
    {
      "epoch": 0.007492231067217232,
      "grad_norm": 0.1049114540219307,
      "learning_rate": 4.322727117869951e-06,
      "loss": 10.3643,
      "step": 88
    },
    {
      "epoch": 0.007577370056617428,
      "grad_norm": 0.10006126761436462,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 10.3656,
      "step": 89
    },
    {
      "epoch": 0.007662509046017623,
      "grad_norm": 0.09538846462965012,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.3636,
      "step": 90
    },
    {
      "epoch": 0.007662509046017623,
      "eval_loss": 10.369254112243652,
      "eval_runtime": 36.9598,
      "eval_samples_per_second": 267.615,
      "eval_steps_per_second": 33.469,
      "step": 90
    },
    {
      "epoch": 0.00774764803541782,
      "grad_norm": 0.08441486954689026,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.3764,
      "step": 91
    },
    {
      "epoch": 0.007832787024818015,
      "grad_norm": 0.11270693689584732,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 10.3591,
      "step": 92
    },
    {
      "epoch": 0.00791792601421821,
      "grad_norm": 0.11153753101825714,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 10.368,
      "step": 93
    },
    {
      "epoch": 0.008003065003618408,
      "grad_norm": 0.09465039521455765,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.3681,
      "step": 94
    },
    {
      "epoch": 0.008088203993018604,
      "grad_norm": 0.09789907187223434,
      "learning_rate": 7.596123493895991e-07,
      "loss": 10.362,
      "step": 95
    },
    {
      "epoch": 0.0081733429824188,
      "grad_norm": 0.10044945031404495,
      "learning_rate": 4.865965629214819e-07,
      "loss": 10.3688,
      "step": 96
    },
    {
      "epoch": 0.008258481971818995,
      "grad_norm": 0.1057361587882042,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 10.3687,
      "step": 97
    },
    {
      "epoch": 0.00834362096121919,
      "grad_norm": 0.10818056762218475,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 10.3696,
      "step": 98
    },
    {
      "epoch": 0.008428759950619386,
      "grad_norm": 0.11640747636556625,
      "learning_rate": 3.04586490452119e-08,
      "loss": 10.3775,
      "step": 99
    },
    {
      "epoch": 0.008428759950619386,
      "eval_loss": 10.369211196899414,
      "eval_runtime": 36.9506,
      "eval_samples_per_second": 267.682,
      "eval_steps_per_second": 33.477,
      "step": 99
    },
    {
      "epoch": 0.008513898940019582,
      "grad_norm": 0.07348009943962097,
      "learning_rate": 0.0,
      "loss": 10.381,
      "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": 9754406289408.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}