{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06655574043261231,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006655574043261231,
      "grad_norm": 4.726227283477783,
      "learning_rate": 1e-05,
      "loss": 5.267,
      "step": 1
    },
    {
      "epoch": 0.0006655574043261231,
      "eval_loss": 5.295533657073975,
      "eval_runtime": 129.161,
      "eval_samples_per_second": 9.794,
      "eval_steps_per_second": 1.231,
      "step": 1
    },
    {
      "epoch": 0.0013311148086522463,
      "grad_norm": 5.535492897033691,
      "learning_rate": 2e-05,
      "loss": 5.5588,
      "step": 2
    },
    {
      "epoch": 0.0019966722129783694,
      "grad_norm": 4.94236946105957,
      "learning_rate": 3e-05,
      "loss": 5.395,
      "step": 3
    },
    {
      "epoch": 0.0026622296173044926,
      "grad_norm": 4.16589879989624,
      "learning_rate": 4e-05,
      "loss": 5.0795,
      "step": 4
    },
    {
      "epoch": 0.0033277870216306157,
      "grad_norm": 4.108709812164307,
      "learning_rate": 5e-05,
      "loss": 5.0469,
      "step": 5
    },
    {
      "epoch": 0.003993344425956739,
      "grad_norm": 4.008864402770996,
      "learning_rate": 6e-05,
      "loss": 5.228,
      "step": 6
    },
    {
      "epoch": 0.004658901830282862,
      "grad_norm": 5.204665660858154,
      "learning_rate": 7e-05,
      "loss": 5.3354,
      "step": 7
    },
    {
      "epoch": 0.005324459234608985,
      "grad_norm": 5.301698207855225,
      "learning_rate": 8e-05,
      "loss": 4.9774,
      "step": 8
    },
    {
      "epoch": 0.005990016638935108,
      "grad_norm": 4.774656295776367,
      "learning_rate": 9e-05,
      "loss": 4.2287,
      "step": 9
    },
    {
      "epoch": 0.005990016638935108,
      "eval_loss": 4.107702255249023,
      "eval_runtime": 128.887,
      "eval_samples_per_second": 9.815,
      "eval_steps_per_second": 1.234,
      "step": 9
    },
    {
      "epoch": 0.0066555740432612314,
      "grad_norm": 4.776927947998047,
      "learning_rate": 0.0001,
      "loss": 4.3933,
      "step": 10
    },
    {
      "epoch": 0.007321131447587354,
      "grad_norm": 4.198732852935791,
      "learning_rate": 9.99695413509548e-05,
      "loss": 3.3878,
      "step": 11
    },
    {
      "epoch": 0.007986688851913478,
      "grad_norm": 5.392261028289795,
      "learning_rate": 9.987820251299122e-05,
      "loss": 3.2997,
      "step": 12
    },
    {
      "epoch": 0.008652246256239601,
      "grad_norm": 4.520054817199707,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.6609,
      "step": 13
    },
    {
      "epoch": 0.009317803660565723,
      "grad_norm": 4.442749977111816,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.4345,
      "step": 14
    },
    {
      "epoch": 0.009983361064891847,
      "grad_norm": 4.220266342163086,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.2565,
      "step": 15
    },
    {
      "epoch": 0.01064891846921797,
      "grad_norm": 4.163025379180908,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.21,
      "step": 16
    },
    {
      "epoch": 0.011314475873544094,
      "grad_norm": 4.160350799560547,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.9844,
      "step": 17
    },
    {
      "epoch": 0.011980033277870216,
      "grad_norm": 4.945196628570557,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.1445,
      "step": 18
    },
    {
      "epoch": 0.011980033277870216,
      "eval_loss": 1.8205780982971191,
      "eval_runtime": 128.9398,
      "eval_samples_per_second": 9.811,
      "eval_steps_per_second": 1.233,
      "step": 18
    },
    {
      "epoch": 0.01264559068219634,
      "grad_norm": 3.850393295288086,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.7251,
      "step": 19
    },
    {
      "epoch": 0.013311148086522463,
      "grad_norm": 4.836368083953857,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.931,
      "step": 20
    },
    {
      "epoch": 0.013976705490848586,
      "grad_norm": 6.969814300537109,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.9043,
      "step": 21
    },
    {
      "epoch": 0.014642262895174708,
      "grad_norm": 3.554103374481201,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.4826,
      "step": 22
    },
    {
      "epoch": 0.015307820299500832,
      "grad_norm": 4.150091648101807,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.7453,
      "step": 23
    },
    {
      "epoch": 0.015973377703826955,
      "grad_norm": 3.157205581665039,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.3333,
      "step": 24
    },
    {
      "epoch": 0.016638935108153077,
      "grad_norm": 3.256354331970215,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.1752,
      "step": 25
    },
    {
      "epoch": 0.017304492512479203,
      "grad_norm": 3.9030933380126953,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.5031,
      "step": 26
    },
    {
      "epoch": 0.017970049916805324,
      "grad_norm": 2.8744611740112305,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.0775,
      "step": 27
    },
    {
      "epoch": 0.017970049916805324,
      "eval_loss": 1.133913516998291,
      "eval_runtime": 128.9709,
      "eval_samples_per_second": 9.808,
      "eval_steps_per_second": 1.233,
      "step": 27
    },
    {
      "epoch": 0.018635607321131446,
      "grad_norm": 3.0283942222595215,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.9521,
      "step": 28
    },
    {
      "epoch": 0.01930116472545757,
      "grad_norm": 3.7651560306549072,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.0143,
      "step": 29
    },
    {
      "epoch": 0.019966722129783693,
      "grad_norm": 5.762377738952637,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.4457,
      "step": 30
    },
    {
      "epoch": 0.020632279534109815,
      "grad_norm": 3.3134381771087646,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.7964,
      "step": 31
    },
    {
      "epoch": 0.02129783693843594,
      "grad_norm": 2.7525556087493896,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.7412,
      "step": 32
    },
    {
      "epoch": 0.021963394342762062,
      "grad_norm": 4.0130743980407715,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.8848,
      "step": 33
    },
    {
      "epoch": 0.022628951747088188,
      "grad_norm": 5.26675271987915,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.108,
      "step": 34
    },
    {
      "epoch": 0.02329450915141431,
      "grad_norm": 5.337582111358643,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.9832,
      "step": 35
    },
    {
      "epoch": 0.02396006655574043,
      "grad_norm": 4.908247947692871,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.7829,
      "step": 36
    },
    {
      "epoch": 0.02396006655574043,
      "eval_loss": 0.669974148273468,
      "eval_runtime": 128.8958,
      "eval_samples_per_second": 9.814,
      "eval_steps_per_second": 1.234,
      "step": 36
    },
    {
      "epoch": 0.024625623960066557,
      "grad_norm": 3.0787861347198486,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.6727,
      "step": 37
    },
    {
      "epoch": 0.02529118136439268,
      "grad_norm": 4.301119327545166,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.9116,
      "step": 38
    },
    {
      "epoch": 0.0259567387687188,
      "grad_norm": 3.8116776943206787,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.7031,
      "step": 39
    },
    {
      "epoch": 0.026622296173044926,
      "grad_norm": 4.841736793518066,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.615,
      "step": 40
    },
    {
      "epoch": 0.027287853577371048,
      "grad_norm": 3.1814475059509277,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.4463,
      "step": 41
    },
    {
      "epoch": 0.027953410981697173,
      "grad_norm": 4.409448623657227,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.5314,
      "step": 42
    },
    {
      "epoch": 0.028618968386023295,
      "grad_norm": 3.7353148460388184,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.2872,
      "step": 43
    },
    {
      "epoch": 0.029284525790349417,
      "grad_norm": 4.216848850250244,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.6368,
      "step": 44
    },
    {
      "epoch": 0.029950083194675542,
      "grad_norm": 3.024632215499878,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.274,
      "step": 45
    },
    {
      "epoch": 0.029950083194675542,
      "eval_loss": 0.47742539644241333,
      "eval_runtime": 128.9201,
      "eval_samples_per_second": 9.812,
      "eval_steps_per_second": 1.233,
      "step": 45
    },
    {
      "epoch": 0.030615640599001664,
      "grad_norm": 5.100956916809082,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3197,
      "step": 46
    },
    {
      "epoch": 0.031281198003327786,
      "grad_norm": 4.926100730895996,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.6387,
      "step": 47
    },
    {
      "epoch": 0.03194675540765391,
      "grad_norm": 4.116820335388184,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.4339,
      "step": 48
    },
    {
      "epoch": 0.032612312811980036,
      "grad_norm": 7.327733516693115,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.4984,
      "step": 49
    },
    {
      "epoch": 0.033277870216306155,
      "grad_norm": 5.371652603149414,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.5401,
      "step": 50
    },
    {
      "epoch": 0.03394342762063228,
      "grad_norm": 6.905318737030029,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.2936,
      "step": 51
    },
    {
      "epoch": 0.034608985024958405,
      "grad_norm": 3.5402543544769287,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.2763,
      "step": 52
    },
    {
      "epoch": 0.035274542429284524,
      "grad_norm": 5.859736442565918,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.6242,
      "step": 53
    },
    {
      "epoch": 0.03594009983361065,
      "grad_norm": 5.486581325531006,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.5799,
      "step": 54
    },
    {
      "epoch": 0.03594009983361065,
      "eval_loss": 0.36419036984443665,
      "eval_runtime": 128.9077,
      "eval_samples_per_second": 9.813,
      "eval_steps_per_second": 1.233,
      "step": 54
    },
    {
      "epoch": 0.036605657237936774,
      "grad_norm": 4.571095943450928,
      "learning_rate": 5e-05,
      "loss": 0.4744,
      "step": 55
    },
    {
      "epoch": 0.03727121464226289,
      "grad_norm": 3.6389660835266113,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.3371,
      "step": 56
    },
    {
      "epoch": 0.03793677204658902,
      "grad_norm": 3.095595598220825,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.279,
      "step": 57
    },
    {
      "epoch": 0.03860232945091514,
      "grad_norm": 2.50360107421875,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.2331,
      "step": 58
    },
    {
      "epoch": 0.03926788685524126,
      "grad_norm": 3.3427207469940186,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.3408,
      "step": 59
    },
    {
      "epoch": 0.03993344425956739,
      "grad_norm": 2.150428056716919,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.1876,
      "step": 60
    },
    {
      "epoch": 0.04059900166389351,
      "grad_norm": 3.427457809448242,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.2515,
      "step": 61
    },
    {
      "epoch": 0.04126455906821963,
      "grad_norm": 6.998630523681641,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.518,
      "step": 62
    },
    {
      "epoch": 0.041930116472545756,
      "grad_norm": 4.818533420562744,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.1538,
      "step": 63
    },
    {
      "epoch": 0.041930116472545756,
      "eval_loss": 0.28987985849380493,
      "eval_runtime": 128.9461,
      "eval_samples_per_second": 9.81,
      "eval_steps_per_second": 1.233,
      "step": 63
    },
    {
      "epoch": 0.04259567387687188,
      "grad_norm": 4.08487606048584,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2289,
      "step": 64
    },
    {
      "epoch": 0.04326123128119801,
      "grad_norm": 2.054035186767578,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.1527,
      "step": 65
    },
    {
      "epoch": 0.043926788685524125,
      "grad_norm": 2.675480604171753,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.1623,
      "step": 66
    },
    {
      "epoch": 0.04459234608985025,
      "grad_norm": 7.059667110443115,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.3663,
      "step": 67
    },
    {
      "epoch": 0.045257903494176376,
      "grad_norm": 5.064462184906006,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.3349,
      "step": 68
    },
    {
      "epoch": 0.045923460898502494,
      "grad_norm": 4.9036359786987305,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.6395,
      "step": 69
    },
    {
      "epoch": 0.04658901830282862,
      "grad_norm": 4.005232810974121,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.1899,
      "step": 70
    },
    {
      "epoch": 0.047254575707154745,
      "grad_norm": 7.462133407592773,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.5265,
      "step": 71
    },
    {
      "epoch": 0.04792013311148086,
      "grad_norm": 3.7536137104034424,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.2666,
      "step": 72
    },
    {
      "epoch": 0.04792013311148086,
      "eval_loss": 0.23793905973434448,
      "eval_runtime": 128.9359,
      "eval_samples_per_second": 9.811,
      "eval_steps_per_second": 1.233,
      "step": 72
    },
    {
      "epoch": 0.04858569051580699,
      "grad_norm": 4.212645053863525,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.2125,
      "step": 73
    },
    {
      "epoch": 0.049251247920133114,
      "grad_norm": 3.5476250648498535,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.3124,
      "step": 74
    },
    {
      "epoch": 0.04991680532445923,
      "grad_norm": 4.556929588317871,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.274,
      "step": 75
    },
    {
      "epoch": 0.05058236272878536,
      "grad_norm": 5.972333908081055,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.3983,
      "step": 76
    },
    {
      "epoch": 0.05124792013311148,
      "grad_norm": 4.970418930053711,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.2292,
      "step": 77
    },
    {
      "epoch": 0.0519134775374376,
      "grad_norm": 3.250725030899048,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.1587,
      "step": 78
    },
    {
      "epoch": 0.052579034941763726,
      "grad_norm": 1.929383397102356,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.1082,
      "step": 79
    },
    {
      "epoch": 0.05324459234608985,
      "grad_norm": 2.099276304244995,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.1091,
      "step": 80
    },
    {
      "epoch": 0.05391014975041598,
      "grad_norm": 4.829376220703125,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.2974,
      "step": 81
    },
    {
      "epoch": 0.05391014975041598,
      "eval_loss": 0.21195295453071594,
      "eval_runtime": 128.9352,
      "eval_samples_per_second": 9.811,
      "eval_steps_per_second": 1.233,
      "step": 81
    },
    {
      "epoch": 0.054575707154742095,
      "grad_norm": 3.0689616203308105,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.1708,
      "step": 82
    },
    {
      "epoch": 0.05524126455906822,
      "grad_norm": 3.2259533405303955,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.2147,
      "step": 83
    },
    {
      "epoch": 0.055906821963394346,
      "grad_norm": 3.743279457092285,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.2843,
      "step": 84
    },
    {
      "epoch": 0.056572379367720464,
      "grad_norm": 3.8382668495178223,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.1838,
      "step": 85
    },
    {
      "epoch": 0.05723793677204659,
      "grad_norm": 3.651982307434082,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.1764,
      "step": 86
    },
    {
      "epoch": 0.057903494176372715,
      "grad_norm": 6.519517421722412,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.2541,
      "step": 87
    },
    {
      "epoch": 0.05856905158069883,
      "grad_norm": 3.807999849319458,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.2566,
      "step": 88
    },
    {
      "epoch": 0.05923460898502496,
      "grad_norm": 3.6574578285217285,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.1891,
      "step": 89
    },
    {
      "epoch": 0.059900166389351084,
      "grad_norm": 3.1083388328552246,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.2098,
      "step": 90
    },
    {
      "epoch": 0.059900166389351084,
      "eval_loss": 0.19934000074863434,
      "eval_runtime": 128.9277,
      "eval_samples_per_second": 9.812,
      "eval_steps_per_second": 1.233,
      "step": 90
    },
    {
      "epoch": 0.0605657237936772,
      "grad_norm": 3.158428430557251,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.1998,
      "step": 91
    },
    {
      "epoch": 0.06123128119800333,
      "grad_norm": 3.8215372562408447,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.2293,
      "step": 92
    },
    {
      "epoch": 0.06189683860232945,
      "grad_norm": 4.208840370178223,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.3915,
      "step": 93
    },
    {
      "epoch": 0.06256239600665557,
      "grad_norm": 3.0414741039276123,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.1946,
      "step": 94
    },
    {
      "epoch": 0.0632279534109817,
      "grad_norm": 3.209970474243164,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.1571,
      "step": 95
    },
    {
      "epoch": 0.06389351081530782,
      "grad_norm": 5.132108688354492,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.4325,
      "step": 96
    },
    {
      "epoch": 0.06455906821963395,
      "grad_norm": 3.055175304412842,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.168,
      "step": 97
    },
    {
      "epoch": 0.06522462562396007,
      "grad_norm": 2.978544235229492,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.1467,
      "step": 98
    },
    {
      "epoch": 0.06589018302828618,
      "grad_norm": 2.435636043548584,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.154,
      "step": 99
    },
    {
      "epoch": 0.06589018302828618,
      "eval_loss": 0.1956445723772049,
      "eval_runtime": 128.9252,
      "eval_samples_per_second": 9.812,
      "eval_steps_per_second": 1.233,
      "step": 99
    },
    {
      "epoch": 0.06655574043261231,
      "grad_norm": 4.698106288909912,
      "learning_rate": 0.0,
      "loss": 0.2,
      "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": 6.6109411688448e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}