{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2094240837696335,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0020942408376963353,
      "grad_norm": 0.34981271624565125,
      "learning_rate": 1e-05,
      "loss": 3.2781,
      "step": 1
    },
    {
      "epoch": 0.0020942408376963353,
      "eval_loss": 1.7277591228485107,
      "eval_runtime": 53.6735,
      "eval_samples_per_second": 7.508,
      "eval_steps_per_second": 0.95,
      "step": 1
    },
    {
      "epoch": 0.004188481675392671,
      "grad_norm": 0.801185667514801,
      "learning_rate": 2e-05,
      "loss": 3.5415,
      "step": 2
    },
    {
      "epoch": 0.0062827225130890054,
      "grad_norm": 0.3677161931991577,
      "learning_rate": 3e-05,
      "loss": 3.5543,
      "step": 3
    },
    {
      "epoch": 0.008376963350785341,
      "grad_norm": 0.448595255613327,
      "learning_rate": 4e-05,
      "loss": 3.4746,
      "step": 4
    },
    {
      "epoch": 0.010471204188481676,
      "grad_norm": 0.40933072566986084,
      "learning_rate": 5e-05,
      "loss": 3.3815,
      "step": 5
    },
    {
      "epoch": 0.012565445026178011,
      "grad_norm": 0.4692118465900421,
      "learning_rate": 6e-05,
      "loss": 3.5705,
      "step": 6
    },
    {
      "epoch": 0.014659685863874346,
      "grad_norm": 0.5187078714370728,
      "learning_rate": 7e-05,
      "loss": 3.3902,
      "step": 7
    },
    {
      "epoch": 0.016753926701570682,
      "grad_norm": 0.4143497347831726,
      "learning_rate": 8e-05,
      "loss": 3.1211,
      "step": 8
    },
    {
      "epoch": 0.018848167539267015,
      "grad_norm": 0.4992891848087311,
      "learning_rate": 9e-05,
      "loss": 3.3897,
      "step": 9
    },
    {
      "epoch": 0.018848167539267015,
      "eval_loss": 1.690635323524475,
      "eval_runtime": 54.4943,
      "eval_samples_per_second": 7.395,
      "eval_steps_per_second": 0.936,
      "step": 9
    },
    {
      "epoch": 0.020942408376963352,
      "grad_norm": 0.5181413292884827,
      "learning_rate": 0.0001,
      "loss": 3.1257,
      "step": 10
    },
    {
      "epoch": 0.023036649214659685,
      "grad_norm": 0.573737621307373,
      "learning_rate": 9.99695413509548e-05,
      "loss": 3.135,
      "step": 11
    },
    {
      "epoch": 0.025130890052356022,
      "grad_norm": 0.5204129219055176,
      "learning_rate": 9.987820251299122e-05,
      "loss": 3.2358,
      "step": 12
    },
    {
      "epoch": 0.027225130890052355,
      "grad_norm": 0.5474736094474792,
      "learning_rate": 9.972609476841367e-05,
      "loss": 3.2861,
      "step": 13
    },
    {
      "epoch": 0.02931937172774869,
      "grad_norm": 0.5524812340736389,
      "learning_rate": 9.951340343707852e-05,
      "loss": 3.2345,
      "step": 14
    },
    {
      "epoch": 0.031413612565445025,
      "grad_norm": 0.5993866324424744,
      "learning_rate": 9.924038765061042e-05,
      "loss": 3.025,
      "step": 15
    },
    {
      "epoch": 0.033507853403141365,
      "grad_norm": 0.5874714851379395,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.9435,
      "step": 16
    },
    {
      "epoch": 0.0356020942408377,
      "grad_norm": 0.5276877284049988,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.9228,
      "step": 17
    },
    {
      "epoch": 0.03769633507853403,
      "grad_norm": 0.5134425759315491,
      "learning_rate": 9.806308479691595e-05,
      "loss": 3.0417,
      "step": 18
    },
    {
      "epoch": 0.03769633507853403,
      "eval_loss": 1.5175120830535889,
      "eval_runtime": 54.491,
      "eval_samples_per_second": 7.396,
      "eval_steps_per_second": 0.936,
      "step": 18
    },
    {
      "epoch": 0.039790575916230364,
      "grad_norm": 0.6345006823539734,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.0776,
      "step": 19
    },
    {
      "epoch": 0.041884816753926704,
      "grad_norm": 0.5065171122550964,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.7851,
      "step": 20
    },
    {
      "epoch": 0.04397905759162304,
      "grad_norm": 0.6690090894699097,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.9525,
      "step": 21
    },
    {
      "epoch": 0.04607329842931937,
      "grad_norm": 0.5420049428939819,
      "learning_rate": 9.567727288213005e-05,
      "loss": 3.0601,
      "step": 22
    },
    {
      "epoch": 0.048167539267015703,
      "grad_norm": 0.6415935754776001,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.9687,
      "step": 23
    },
    {
      "epoch": 0.050261780104712044,
      "grad_norm": 0.4800170063972473,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.6966,
      "step": 24
    },
    {
      "epoch": 0.05235602094240838,
      "grad_norm": 0.5702900290489197,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.9085,
      "step": 25
    },
    {
      "epoch": 0.05445026178010471,
      "grad_norm": 0.5642029047012329,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.8261,
      "step": 26
    },
    {
      "epoch": 0.05654450261780105,
      "grad_norm": 0.6375811100006104,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.9975,
      "step": 27
    },
    {
      "epoch": 0.05654450261780105,
      "eval_loss": 1.4399325847625732,
      "eval_runtime": 54.4669,
      "eval_samples_per_second": 7.399,
      "eval_steps_per_second": 0.936,
      "step": 27
    },
    {
      "epoch": 0.05863874345549738,
      "grad_norm": 0.5609163045883179,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.794,
      "step": 28
    },
    {
      "epoch": 0.060732984293193716,
      "grad_norm": 0.6879402995109558,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.7103,
      "step": 29
    },
    {
      "epoch": 0.06282722513089005,
      "grad_norm": 0.5450217127799988,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.7324,
      "step": 30
    },
    {
      "epoch": 0.06492146596858639,
      "grad_norm": 0.6222276091575623,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.9903,
      "step": 31
    },
    {
      "epoch": 0.06701570680628273,
      "grad_norm": 0.5290335416793823,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.8003,
      "step": 32
    },
    {
      "epoch": 0.06910994764397906,
      "grad_norm": 0.643876850605011,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.7036,
      "step": 33
    },
    {
      "epoch": 0.0712041884816754,
      "grad_norm": 0.6455150842666626,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.758,
      "step": 34
    },
    {
      "epoch": 0.07329842931937172,
      "grad_norm": 0.6009905934333801,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.86,
      "step": 35
    },
    {
      "epoch": 0.07539267015706806,
      "grad_norm": 0.5729888081550598,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.7763,
      "step": 36
    },
    {
      "epoch": 0.07539267015706806,
      "eval_loss": 1.404931902885437,
      "eval_runtime": 54.4896,
      "eval_samples_per_second": 7.396,
      "eval_steps_per_second": 0.936,
      "step": 36
    },
    {
      "epoch": 0.0774869109947644,
      "grad_norm": 0.6812015175819397,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.8235,
      "step": 37
    },
    {
      "epoch": 0.07958115183246073,
      "grad_norm": 0.5715813636779785,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.6603,
      "step": 38
    },
    {
      "epoch": 0.08167539267015707,
      "grad_norm": 0.5004135966300964,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.7355,
      "step": 39
    },
    {
      "epoch": 0.08376963350785341,
      "grad_norm": 0.5744718313217163,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.8711,
      "step": 40
    },
    {
      "epoch": 0.08586387434554973,
      "grad_norm": 0.6692417860031128,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.6734,
      "step": 41
    },
    {
      "epoch": 0.08795811518324607,
      "grad_norm": 0.601163923740387,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.7693,
      "step": 42
    },
    {
      "epoch": 0.09005235602094241,
      "grad_norm": 0.5379462838172913,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.8922,
      "step": 43
    },
    {
      "epoch": 0.09214659685863874,
      "grad_norm": 0.5941004753112793,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.5804,
      "step": 44
    },
    {
      "epoch": 0.09424083769633508,
      "grad_norm": 0.5219014286994934,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.9221,
      "step": 45
    },
    {
      "epoch": 0.09424083769633508,
      "eval_loss": 1.3878324031829834,
      "eval_runtime": 54.4731,
      "eval_samples_per_second": 7.398,
      "eval_steps_per_second": 0.936,
      "step": 45
    },
    {
      "epoch": 0.09633507853403141,
      "grad_norm": 0.6687893271446228,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.7832,
      "step": 46
    },
    {
      "epoch": 0.09842931937172775,
      "grad_norm": 0.5477647185325623,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.6517,
      "step": 47
    },
    {
      "epoch": 0.10052356020942409,
      "grad_norm": 0.5874961018562317,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.6161,
      "step": 48
    },
    {
      "epoch": 0.10261780104712041,
      "grad_norm": 0.518980860710144,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.7782,
      "step": 49
    },
    {
      "epoch": 0.10471204188481675,
      "grad_norm": 0.8065228462219238,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.7772,
      "step": 50
    },
    {
      "epoch": 0.1068062827225131,
      "grad_norm": 0.5900649428367615,
      "learning_rate": 5.695865504800327e-05,
      "loss": 2.806,
      "step": 51
    },
    {
      "epoch": 0.10890052356020942,
      "grad_norm": 0.7086355090141296,
      "learning_rate": 5.522642316338268e-05,
      "loss": 2.747,
      "step": 52
    },
    {
      "epoch": 0.11099476439790576,
      "grad_norm": 0.8284993171691895,
      "learning_rate": 5.348782368720626e-05,
      "loss": 2.7135,
      "step": 53
    },
    {
      "epoch": 0.1130890052356021,
      "grad_norm": 0.6236894130706787,
      "learning_rate": 5.174497483512506e-05,
      "loss": 2.786,
      "step": 54
    },
    {
      "epoch": 0.1130890052356021,
      "eval_loss": 1.374350666999817,
      "eval_runtime": 54.5065,
      "eval_samples_per_second": 7.394,
      "eval_steps_per_second": 0.936,
      "step": 54
    },
    {
      "epoch": 0.11518324607329843,
      "grad_norm": 0.7123720645904541,
      "learning_rate": 5e-05,
      "loss": 2.8848,
      "step": 55
    },
    {
      "epoch": 0.11727748691099477,
      "grad_norm": 0.5804649591445923,
      "learning_rate": 4.825502516487497e-05,
      "loss": 2.566,
      "step": 56
    },
    {
      "epoch": 0.1193717277486911,
      "grad_norm": 0.6089434027671814,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 2.8531,
      "step": 57
    },
    {
      "epoch": 0.12146596858638743,
      "grad_norm": 0.5974732041358948,
      "learning_rate": 4.477357683661734e-05,
      "loss": 2.4952,
      "step": 58
    },
    {
      "epoch": 0.12356020942408377,
      "grad_norm": 0.5893568396568298,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 2.6991,
      "step": 59
    },
    {
      "epoch": 0.1256544502617801,
      "grad_norm": 0.5280726552009583,
      "learning_rate": 4.131759111665349e-05,
      "loss": 2.7225,
      "step": 60
    },
    {
      "epoch": 0.12774869109947645,
      "grad_norm": 0.6076133847236633,
      "learning_rate": 3.960441545911204e-05,
      "loss": 2.7786,
      "step": 61
    },
    {
      "epoch": 0.12984293193717278,
      "grad_norm": 0.6655527949333191,
      "learning_rate": 3.790390522001662e-05,
      "loss": 2.9073,
      "step": 62
    },
    {
      "epoch": 0.1319371727748691,
      "grad_norm": 0.7784544229507446,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 2.9591,
      "step": 63
    },
    {
      "epoch": 0.1319371727748691,
      "eval_loss": 1.3667219877243042,
      "eval_runtime": 54.5135,
      "eval_samples_per_second": 7.393,
      "eval_steps_per_second": 0.936,
      "step": 63
    },
    {
      "epoch": 0.13403141361256546,
      "grad_norm": 0.6011307239532471,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.6829,
      "step": 64
    },
    {
      "epoch": 0.13612565445026178,
      "grad_norm": 0.6874279379844666,
      "learning_rate": 3.289899283371657e-05,
      "loss": 2.6009,
      "step": 65
    },
    {
      "epoch": 0.1382198952879581,
      "grad_norm": 0.5835795998573303,
      "learning_rate": 3.12696703292044e-05,
      "loss": 2.7479,
      "step": 66
    },
    {
      "epoch": 0.14031413612565444,
      "grad_norm": 0.702832818031311,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 2.8118,
      "step": 67
    },
    {
      "epoch": 0.1424083769633508,
      "grad_norm": 0.5409141778945923,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 2.8181,
      "step": 68
    },
    {
      "epoch": 0.14450261780104712,
      "grad_norm": 0.5922812819480896,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 2.6452,
      "step": 69
    },
    {
      "epoch": 0.14659685863874344,
      "grad_norm": 0.6153621673583984,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.6273,
      "step": 70
    },
    {
      "epoch": 0.1486910994764398,
      "grad_norm": 0.8154770731925964,
      "learning_rate": 2.350403678833976e-05,
      "loss": 2.8673,
      "step": 71
    },
    {
      "epoch": 0.15078534031413612,
      "grad_norm": 0.5778376460075378,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 2.6154,
      "step": 72
    },
    {
      "epoch": 0.15078534031413612,
      "eval_loss": 1.3605839014053345,
      "eval_runtime": 54.5463,
      "eval_samples_per_second": 7.388,
      "eval_steps_per_second": 0.935,
      "step": 72
    },
    {
      "epoch": 0.15287958115183245,
      "grad_norm": 0.7559208869934082,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.9207,
      "step": 73
    },
    {
      "epoch": 0.1549738219895288,
      "grad_norm": 0.6899783611297607,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 2.8501,
      "step": 74
    },
    {
      "epoch": 0.15706806282722513,
      "grad_norm": 0.5878341794013977,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 2.6975,
      "step": 75
    },
    {
      "epoch": 0.15916230366492146,
      "grad_norm": 0.7345188856124878,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 2.6499,
      "step": 76
    },
    {
      "epoch": 0.1612565445026178,
      "grad_norm": 0.7230733036994934,
      "learning_rate": 1.526708147705013e-05,
      "loss": 2.7264,
      "step": 77
    },
    {
      "epoch": 0.16335078534031414,
      "grad_norm": 0.6331895589828491,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 2.6676,
      "step": 78
    },
    {
      "epoch": 0.16544502617801046,
      "grad_norm": 0.5962709188461304,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 2.6949,
      "step": 79
    },
    {
      "epoch": 0.16753926701570682,
      "grad_norm": 0.6756764650344849,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 2.5997,
      "step": 80
    },
    {
      "epoch": 0.16963350785340314,
      "grad_norm": 0.5043853521347046,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 2.6372,
      "step": 81
    },
    {
      "epoch": 0.16963350785340314,
      "eval_loss": 1.3571741580963135,
      "eval_runtime": 54.507,
      "eval_samples_per_second": 7.394,
      "eval_steps_per_second": 0.936,
      "step": 81
    },
    {
      "epoch": 0.17172774869109947,
      "grad_norm": 0.5730753540992737,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.7383,
      "step": 82
    },
    {
      "epoch": 0.17382198952879582,
      "grad_norm": 0.6609073877334595,
      "learning_rate": 8.548121372247918e-06,
      "loss": 2.4678,
      "step": 83
    },
    {
      "epoch": 0.17591623036649215,
      "grad_norm": 0.7464276552200317,
      "learning_rate": 7.597595192178702e-06,
      "loss": 2.7108,
      "step": 84
    },
    {
      "epoch": 0.17801047120418848,
      "grad_norm": 0.6932152509689331,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.7522,
      "step": 85
    },
    {
      "epoch": 0.18010471204188483,
      "grad_norm": 0.693647563457489,
      "learning_rate": 5.852620357053651e-06,
      "loss": 2.8346,
      "step": 86
    },
    {
      "epoch": 0.18219895287958116,
      "grad_norm": 0.6403724551200867,
      "learning_rate": 5.060297685041659e-06,
      "loss": 2.8161,
      "step": 87
    },
    {
      "epoch": 0.18429319371727748,
      "grad_norm": 0.6382010579109192,
      "learning_rate": 4.322727117869951e-06,
      "loss": 2.8568,
      "step": 88
    },
    {
      "epoch": 0.18638743455497384,
      "grad_norm": 0.6189000010490417,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 2.6409,
      "step": 89
    },
    {
      "epoch": 0.18848167539267016,
      "grad_norm": 0.66209876537323,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 2.7499,
      "step": 90
    },
    {
      "epoch": 0.18848167539267016,
      "eval_loss": 1.3558423519134521,
      "eval_runtime": 54.5491,
      "eval_samples_per_second": 7.388,
      "eval_steps_per_second": 0.935,
      "step": 90
    },
    {
      "epoch": 0.1905759162303665,
      "grad_norm": 0.6726245880126953,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.5282,
      "step": 91
    },
    {
      "epoch": 0.19267015706806281,
      "grad_norm": 0.6591723561286926,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 2.7147,
      "step": 92
    },
    {
      "epoch": 0.19476439790575917,
      "grad_norm": 0.587321937084198,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 2.7536,
      "step": 93
    },
    {
      "epoch": 0.1968586387434555,
      "grad_norm": 0.672417402267456,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.586,
      "step": 94
    },
    {
      "epoch": 0.19895287958115182,
      "grad_norm": 0.6691716313362122,
      "learning_rate": 7.596123493895991e-07,
      "loss": 2.5708,
      "step": 95
    },
    {
      "epoch": 0.20104712041884817,
      "grad_norm": 0.6790332198143005,
      "learning_rate": 4.865965629214819e-07,
      "loss": 2.6005,
      "step": 96
    },
    {
      "epoch": 0.2031413612565445,
      "grad_norm": 0.6420785188674927,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 2.5068,
      "step": 97
    },
    {
      "epoch": 0.20523560209424083,
      "grad_norm": 0.6517630219459534,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.6767,
      "step": 98
    },
    {
      "epoch": 0.20732984293193718,
      "grad_norm": 0.6084813475608826,
      "learning_rate": 3.04586490452119e-08,
      "loss": 2.6547,
      "step": 99
    },
    {
      "epoch": 0.20732984293193718,
      "eval_loss": 1.3555799722671509,
      "eval_runtime": 54.5552,
      "eval_samples_per_second": 7.387,
      "eval_steps_per_second": 0.935,
      "step": 99
    },
    {
      "epoch": 0.2094240837696335,
      "grad_norm": 0.6263311505317688,
      "learning_rate": 0.0,
      "loss": 2.6251,
      "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": 6.53464644354048e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}