{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5780346820809249,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005780346820809248,
      "grad_norm": 15.968648910522461,
      "learning_rate": 1e-05,
      "loss": 14.9647,
      "step": 1
    },
    {
      "epoch": 0.005780346820809248,
      "eval_loss": 15.624478340148926,
      "eval_runtime": 32.8752,
      "eval_samples_per_second": 4.441,
      "eval_steps_per_second": 0.578,
      "step": 1
    },
    {
      "epoch": 0.011560693641618497,
      "grad_norm": 13.408590316772461,
      "learning_rate": 2e-05,
      "loss": 15.3091,
      "step": 2
    },
    {
      "epoch": 0.017341040462427744,
      "grad_norm": 20.93248176574707,
      "learning_rate": 3e-05,
      "loss": 18.6105,
      "step": 3
    },
    {
      "epoch": 0.023121387283236993,
      "grad_norm": 14.510547637939453,
      "learning_rate": 4e-05,
      "loss": 16.3747,
      "step": 4
    },
    {
      "epoch": 0.028901734104046242,
      "grad_norm": 19.18450164794922,
      "learning_rate": 5e-05,
      "loss": 16.0686,
      "step": 5
    },
    {
      "epoch": 0.03468208092485549,
      "grad_norm": 14.488174438476562,
      "learning_rate": 6e-05,
      "loss": 15.2841,
      "step": 6
    },
    {
      "epoch": 0.04046242774566474,
      "grad_norm": 13.681251525878906,
      "learning_rate": 7e-05,
      "loss": 14.0598,
      "step": 7
    },
    {
      "epoch": 0.046242774566473986,
      "grad_norm": 18.5799503326416,
      "learning_rate": 8e-05,
      "loss": 15.2511,
      "step": 8
    },
    {
      "epoch": 0.05202312138728324,
      "grad_norm": 15.954649925231934,
      "learning_rate": 9e-05,
      "loss": 14.6362,
      "step": 9
    },
    {
      "epoch": 0.05202312138728324,
      "eval_loss": 13.5409517288208,
      "eval_runtime": 32.5769,
      "eval_samples_per_second": 4.482,
      "eval_steps_per_second": 0.583,
      "step": 9
    },
    {
      "epoch": 0.057803468208092484,
      "grad_norm": 16.607139587402344,
      "learning_rate": 0.0001,
      "loss": 12.2493,
      "step": 10
    },
    {
      "epoch": 0.06358381502890173,
      "grad_norm": 14.81494140625,
      "learning_rate": 9.99695413509548e-05,
      "loss": 11.0069,
      "step": 11
    },
    {
      "epoch": 0.06936416184971098,
      "grad_norm": 18.715105056762695,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.7712,
      "step": 12
    },
    {
      "epoch": 0.07514450867052024,
      "grad_norm": 17.899497985839844,
      "learning_rate": 9.972609476841367e-05,
      "loss": 9.3094,
      "step": 13
    },
    {
      "epoch": 0.08092485549132948,
      "grad_norm": 20.41404914855957,
      "learning_rate": 9.951340343707852e-05,
      "loss": 8.6157,
      "step": 14
    },
    {
      "epoch": 0.08670520231213873,
      "grad_norm": 18.074546813964844,
      "learning_rate": 9.924038765061042e-05,
      "loss": 6.4898,
      "step": 15
    },
    {
      "epoch": 0.09248554913294797,
      "grad_norm": 16.869441986083984,
      "learning_rate": 9.890738003669029e-05,
      "loss": 6.6331,
      "step": 16
    },
    {
      "epoch": 0.09826589595375723,
      "grad_norm": 16.82598876953125,
      "learning_rate": 9.851478631379982e-05,
      "loss": 4.8082,
      "step": 17
    },
    {
      "epoch": 0.10404624277456648,
      "grad_norm": 16.25006675720215,
      "learning_rate": 9.806308479691595e-05,
      "loss": 5.3876,
      "step": 18
    },
    {
      "epoch": 0.10404624277456648,
      "eval_loss": 5.071387767791748,
      "eval_runtime": 32.5402,
      "eval_samples_per_second": 4.487,
      "eval_steps_per_second": 0.584,
      "step": 18
    },
    {
      "epoch": 0.10982658959537572,
      "grad_norm": 17.678916931152344,
      "learning_rate": 9.755282581475769e-05,
      "loss": 4.8345,
      "step": 19
    },
    {
      "epoch": 0.11560693641618497,
      "grad_norm": 18.625810623168945,
      "learning_rate": 9.698463103929542e-05,
      "loss": 4.9997,
      "step": 20
    },
    {
      "epoch": 0.12138728323699421,
      "grad_norm": 16.467483520507812,
      "learning_rate": 9.635919272833938e-05,
      "loss": 3.2066,
      "step": 21
    },
    {
      "epoch": 0.12716763005780346,
      "grad_norm": 13.615856170654297,
      "learning_rate": 9.567727288213005e-05,
      "loss": 4.5356,
      "step": 22
    },
    {
      "epoch": 0.1329479768786127,
      "grad_norm": 16.053314208984375,
      "learning_rate": 9.493970231495835e-05,
      "loss": 4.1894,
      "step": 23
    },
    {
      "epoch": 0.13872832369942195,
      "grad_norm": 15.482643127441406,
      "learning_rate": 9.414737964294636e-05,
      "loss": 3.2667,
      "step": 24
    },
    {
      "epoch": 0.14450867052023122,
      "grad_norm": 13.18624210357666,
      "learning_rate": 9.330127018922194e-05,
      "loss": 3.9883,
      "step": 25
    },
    {
      "epoch": 0.15028901734104047,
      "grad_norm": 16.426555633544922,
      "learning_rate": 9.24024048078213e-05,
      "loss": 3.6909,
      "step": 26
    },
    {
      "epoch": 0.15606936416184972,
      "grad_norm": 15.01686954498291,
      "learning_rate": 9.145187862775209e-05,
      "loss": 3.3086,
      "step": 27
    },
    {
      "epoch": 0.15606936416184972,
      "eval_loss": 3.5667498111724854,
      "eval_runtime": 32.5429,
      "eval_samples_per_second": 4.486,
      "eval_steps_per_second": 0.584,
      "step": 27
    },
    {
      "epoch": 0.16184971098265896,
      "grad_norm": 11.206390380859375,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.4312,
      "step": 28
    },
    {
      "epoch": 0.1676300578034682,
      "grad_norm": 11.284567832946777,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.7148,
      "step": 29
    },
    {
      "epoch": 0.17341040462427745,
      "grad_norm": 12.321219444274902,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.4042,
      "step": 30
    },
    {
      "epoch": 0.1791907514450867,
      "grad_norm": 12.103856086730957,
      "learning_rate": 8.715724127386972e-05,
      "loss": 3.0817,
      "step": 31
    },
    {
      "epoch": 0.18497109826589594,
      "grad_norm": 11.078689575195312,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.9151,
      "step": 32
    },
    {
      "epoch": 0.1907514450867052,
      "grad_norm": 10.692811965942383,
      "learning_rate": 8.473291852294987e-05,
      "loss": 3.5216,
      "step": 33
    },
    {
      "epoch": 0.19653179190751446,
      "grad_norm": 9.273629188537598,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.8621,
      "step": 34
    },
    {
      "epoch": 0.2023121387283237,
      "grad_norm": 11.989301681518555,
      "learning_rate": 8.213938048432697e-05,
      "loss": 3.2667,
      "step": 35
    },
    {
      "epoch": 0.20809248554913296,
      "grad_norm": 11.12063217163086,
      "learning_rate": 8.07830737662829e-05,
      "loss": 3.2634,
      "step": 36
    },
    {
      "epoch": 0.20809248554913296,
      "eval_loss": 3.065423011779785,
      "eval_runtime": 32.5461,
      "eval_samples_per_second": 4.486,
      "eval_steps_per_second": 0.584,
      "step": 36
    },
    {
      "epoch": 0.2138728323699422,
      "grad_norm": 10.847309112548828,
      "learning_rate": 7.938926261462366e-05,
      "loss": 3.4122,
      "step": 37
    },
    {
      "epoch": 0.21965317919075145,
      "grad_norm": 9.183465003967285,
      "learning_rate": 7.795964517353735e-05,
      "loss": 3.4336,
      "step": 38
    },
    {
      "epoch": 0.2254335260115607,
      "grad_norm": 12.96435546875,
      "learning_rate": 7.649596321166024e-05,
      "loss": 3.8089,
      "step": 39
    },
    {
      "epoch": 0.23121387283236994,
      "grad_norm": 12.382950782775879,
      "learning_rate": 7.500000000000001e-05,
      "loss": 4.228,
      "step": 40
    },
    {
      "epoch": 0.23699421965317918,
      "grad_norm": 10.22998332977295,
      "learning_rate": 7.347357813929454e-05,
      "loss": 3.4248,
      "step": 41
    },
    {
      "epoch": 0.24277456647398843,
      "grad_norm": 8.89307975769043,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.8756,
      "step": 42
    },
    {
      "epoch": 0.24855491329479767,
      "grad_norm": 11.401252746582031,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.5123,
      "step": 43
    },
    {
      "epoch": 0.2543352601156069,
      "grad_norm": 8.95361614227295,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.7822,
      "step": 44
    },
    {
      "epoch": 0.26011560693641617,
      "grad_norm": 9.463065147399902,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.9082,
      "step": 45
    },
    {
      "epoch": 0.26011560693641617,
      "eval_loss": 2.7541401386260986,
      "eval_runtime": 32.5376,
      "eval_samples_per_second": 4.487,
      "eval_steps_per_second": 0.584,
      "step": 45
    },
    {
      "epoch": 0.2658959537572254,
      "grad_norm": 17.087799072265625,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.9372,
      "step": 46
    },
    {
      "epoch": 0.27167630057803466,
      "grad_norm": 11.281935691833496,
      "learning_rate": 6.378186779084995e-05,
      "loss": 3.2312,
      "step": 47
    },
    {
      "epoch": 0.2774566473988439,
      "grad_norm": 10.025297164916992,
      "learning_rate": 6.209609477998338e-05,
      "loss": 3.4024,
      "step": 48
    },
    {
      "epoch": 0.2832369942196532,
      "grad_norm": 8.300965309143066,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 3.3219,
      "step": 49
    },
    {
      "epoch": 0.28901734104046245,
      "grad_norm": 9.206721305847168,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.2398,
      "step": 50
    },
    {
      "epoch": 0.2947976878612717,
      "grad_norm": 10.664775848388672,
      "learning_rate": 5.695865504800327e-05,
      "loss": 2.5739,
      "step": 51
    },
    {
      "epoch": 0.30057803468208094,
      "grad_norm": 10.420068740844727,
      "learning_rate": 5.522642316338268e-05,
      "loss": 3.1879,
      "step": 52
    },
    {
      "epoch": 0.3063583815028902,
      "grad_norm": 10.875478744506836,
      "learning_rate": 5.348782368720626e-05,
      "loss": 3.2304,
      "step": 53
    },
    {
      "epoch": 0.31213872832369943,
      "grad_norm": 10.427178382873535,
      "learning_rate": 5.174497483512506e-05,
      "loss": 2.0526,
      "step": 54
    },
    {
      "epoch": 0.31213872832369943,
      "eval_loss": 2.549694061279297,
      "eval_runtime": 32.5376,
      "eval_samples_per_second": 4.487,
      "eval_steps_per_second": 0.584,
      "step": 54
    },
    {
      "epoch": 0.3179190751445087,
      "grad_norm": 8.758641242980957,
      "learning_rate": 5e-05,
      "loss": 2.3939,
      "step": 55
    },
    {
      "epoch": 0.3236994219653179,
      "grad_norm": 9.106585502624512,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.9922,
      "step": 56
    },
    {
      "epoch": 0.32947976878612717,
      "grad_norm": 12.400283813476562,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 3.073,
      "step": 57
    },
    {
      "epoch": 0.3352601156069364,
      "grad_norm": 9.305767059326172,
      "learning_rate": 4.477357683661734e-05,
      "loss": 3.0633,
      "step": 58
    },
    {
      "epoch": 0.34104046242774566,
      "grad_norm": 6.69735860824585,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.8706,
      "step": 59
    },
    {
      "epoch": 0.3468208092485549,
      "grad_norm": 8.447138786315918,
      "learning_rate": 4.131759111665349e-05,
      "loss": 2.9715,
      "step": 60
    },
    {
      "epoch": 0.35260115606936415,
      "grad_norm": 13.5150785446167,
      "learning_rate": 3.960441545911204e-05,
      "loss": 2.821,
      "step": 61
    },
    {
      "epoch": 0.3583815028901734,
      "grad_norm": 11.817837715148926,
      "learning_rate": 3.790390522001662e-05,
      "loss": 2.703,
      "step": 62
    },
    {
      "epoch": 0.36416184971098264,
      "grad_norm": 8.648508071899414,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 2.5483,
      "step": 63
    },
    {
      "epoch": 0.36416184971098264,
      "eval_loss": 2.419341802597046,
      "eval_runtime": 32.5501,
      "eval_samples_per_second": 4.485,
      "eval_steps_per_second": 0.584,
      "step": 63
    },
    {
      "epoch": 0.3699421965317919,
      "grad_norm": 8.482972145080566,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.9693,
      "step": 64
    },
    {
      "epoch": 0.37572254335260113,
      "grad_norm": 12.55648136138916,
      "learning_rate": 3.289899283371657e-05,
      "loss": 3.5878,
      "step": 65
    },
    {
      "epoch": 0.3815028901734104,
      "grad_norm": 9.748519897460938,
      "learning_rate": 3.12696703292044e-05,
      "loss": 2.6196,
      "step": 66
    },
    {
      "epoch": 0.3872832369942196,
      "grad_norm": 8.55542278289795,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 2.1163,
      "step": 67
    },
    {
      "epoch": 0.3930635838150289,
      "grad_norm": 11.708406448364258,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.5113,
      "step": 68
    },
    {
      "epoch": 0.3988439306358382,
      "grad_norm": 8.71663761138916,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 2.3383,
      "step": 69
    },
    {
      "epoch": 0.4046242774566474,
      "grad_norm": 9.08695125579834,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.4021,
      "step": 70
    },
    {
      "epoch": 0.41040462427745666,
      "grad_norm": 9.509957313537598,
      "learning_rate": 2.350403678833976e-05,
      "loss": 2.2241,
      "step": 71
    },
    {
      "epoch": 0.4161849710982659,
      "grad_norm": 12.932137489318848,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.9278,
      "step": 72
    },
    {
      "epoch": 0.4161849710982659,
      "eval_loss": 2.322727680206299,
      "eval_runtime": 32.534,
      "eval_samples_per_second": 4.488,
      "eval_steps_per_second": 0.584,
      "step": 72
    },
    {
      "epoch": 0.42196531791907516,
      "grad_norm": 11.085196495056152,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.4868,
      "step": 73
    },
    {
      "epoch": 0.4277456647398844,
      "grad_norm": 9.265618324279785,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.9614,
      "step": 74
    },
    {
      "epoch": 0.43352601156069365,
      "grad_norm": 10.728690147399902,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 2.531,
      "step": 75
    },
    {
      "epoch": 0.4393063583815029,
      "grad_norm": 14.048025131225586,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 2.4943,
      "step": 76
    },
    {
      "epoch": 0.44508670520231214,
      "grad_norm": 14.55485725402832,
      "learning_rate": 1.526708147705013e-05,
      "loss": 2.5831,
      "step": 77
    },
    {
      "epoch": 0.4508670520231214,
      "grad_norm": 9.47404670715332,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.9441,
      "step": 78
    },
    {
      "epoch": 0.45664739884393063,
      "grad_norm": 8.202113151550293,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 2.12,
      "step": 79
    },
    {
      "epoch": 0.4624277456647399,
      "grad_norm": 8.428282737731934,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 2.413,
      "step": 80
    },
    {
      "epoch": 0.4682080924855491,
      "grad_norm": 19.201919555664062,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 3.3535,
      "step": 81
    },
    {
      "epoch": 0.4682080924855491,
      "eval_loss": 2.2803900241851807,
      "eval_runtime": 32.5338,
      "eval_samples_per_second": 4.488,
      "eval_steps_per_second": 0.584,
      "step": 81
    },
    {
      "epoch": 0.47398843930635837,
      "grad_norm": 13.889911651611328,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.5221,
      "step": 82
    },
    {
      "epoch": 0.4797687861271676,
      "grad_norm": 11.334454536437988,
      "learning_rate": 8.548121372247918e-06,
      "loss": 3.4398,
      "step": 83
    },
    {
      "epoch": 0.48554913294797686,
      "grad_norm": 12.778782844543457,
      "learning_rate": 7.597595192178702e-06,
      "loss": 2.5363,
      "step": 84
    },
    {
      "epoch": 0.4913294797687861,
      "grad_norm": 11.753548622131348,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.576,
      "step": 85
    },
    {
      "epoch": 0.49710982658959535,
      "grad_norm": 11.410307884216309,
      "learning_rate": 5.852620357053651e-06,
      "loss": 3.1354,
      "step": 86
    },
    {
      "epoch": 0.5028901734104047,
      "grad_norm": 8.957868576049805,
      "learning_rate": 5.060297685041659e-06,
      "loss": 2.5224,
      "step": 87
    },
    {
      "epoch": 0.5086705202312138,
      "grad_norm": 15.306970596313477,
      "learning_rate": 4.322727117869951e-06,
      "loss": 2.7779,
      "step": 88
    },
    {
      "epoch": 0.5144508670520231,
      "grad_norm": 10.743468284606934,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 2.8461,
      "step": 89
    },
    {
      "epoch": 0.5202312138728323,
      "grad_norm": 9.884764671325684,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 2.5365,
      "step": 90
    },
    {
      "epoch": 0.5202312138728323,
      "eval_loss": 2.251675605773926,
      "eval_runtime": 32.5325,
      "eval_samples_per_second": 4.488,
      "eval_steps_per_second": 0.584,
      "step": 90
    },
    {
      "epoch": 0.5260115606936416,
      "grad_norm": 9.051831245422363,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.9364,
      "step": 91
    },
    {
      "epoch": 0.5317919075144508,
      "grad_norm": 13.44649887084961,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 3.2922,
      "step": 92
    },
    {
      "epoch": 0.5375722543352601,
      "grad_norm": 9.797504425048828,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 2.5593,
      "step": 93
    },
    {
      "epoch": 0.5433526011560693,
      "grad_norm": 11.674943923950195,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.9699,
      "step": 94
    },
    {
      "epoch": 0.5491329479768786,
      "grad_norm": 8.266894340515137,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.7054,
      "step": 95
    },
    {
      "epoch": 0.5549132947976878,
      "grad_norm": 12.257719039916992,
      "learning_rate": 4.865965629214819e-07,
      "loss": 2.0088,
      "step": 96
    },
    {
      "epoch": 0.5606936416184971,
      "grad_norm": 12.329103469848633,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 4.0794,
      "step": 97
    },
    {
      "epoch": 0.5664739884393064,
      "grad_norm": 13.644766807556152,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.8662,
      "step": 98
    },
    {
      "epoch": 0.5722543352601156,
      "grad_norm": 7.874459743499756,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.4249,
      "step": 99
    },
    {
      "epoch": 0.5722543352601156,
      "eval_loss": 2.246007204055786,
      "eval_runtime": 32.5444,
      "eval_samples_per_second": 4.486,
      "eval_steps_per_second": 0.584,
      "step": 99
    },
    {
      "epoch": 0.5780346820809249,
      "grad_norm": 10.751273155212402,
      "learning_rate": 0.0,
      "loss": 2.4663,
      "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": 1.483774567120896e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}