{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06209251785159888,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006209251785159888,
      "grad_norm": 0.059769123792648315,
      "learning_rate": 1e-05,
      "loss": 0.3185,
      "step": 1
    },
    {
      "epoch": 0.0006209251785159888,
      "eval_loss": 0.13959623873233795,
      "eval_runtime": 195.4758,
      "eval_samples_per_second": 6.937,
      "eval_steps_per_second": 0.87,
      "step": 1
    },
    {
      "epoch": 0.0012418503570319776,
      "grad_norm": 0.10517919063568115,
      "learning_rate": 2e-05,
      "loss": 0.256,
      "step": 2
    },
    {
      "epoch": 0.0018627755355479665,
      "grad_norm": 0.11081903427839279,
      "learning_rate": 3e-05,
      "loss": 0.5629,
      "step": 3
    },
    {
      "epoch": 0.0024837007140639552,
      "grad_norm": 0.06486257910728455,
      "learning_rate": 4e-05,
      "loss": 0.1716,
      "step": 4
    },
    {
      "epoch": 0.003104625892579944,
      "grad_norm": 0.09219924360513687,
      "learning_rate": 5e-05,
      "loss": 0.1809,
      "step": 5
    },
    {
      "epoch": 0.003725551071095933,
      "grad_norm": 0.0759315937757492,
      "learning_rate": 6e-05,
      "loss": 0.2458,
      "step": 6
    },
    {
      "epoch": 0.004346476249611922,
      "grad_norm": 0.12138082832098007,
      "learning_rate": 7e-05,
      "loss": 0.3938,
      "step": 7
    },
    {
      "epoch": 0.0049674014281279105,
      "grad_norm": 0.07585237920284271,
      "learning_rate": 8e-05,
      "loss": 0.365,
      "step": 8
    },
    {
      "epoch": 0.005588326606643899,
      "grad_norm": 0.10387030988931656,
      "learning_rate": 9e-05,
      "loss": 0.2495,
      "step": 9
    },
    {
      "epoch": 0.005588326606643899,
      "eval_loss": 0.12086986750364304,
      "eval_runtime": 196.9377,
      "eval_samples_per_second": 6.885,
      "eval_steps_per_second": 0.863,
      "step": 9
    },
    {
      "epoch": 0.006209251785159888,
      "grad_norm": 0.1180136501789093,
      "learning_rate": 0.0001,
      "loss": 0.251,
      "step": 10
    },
    {
      "epoch": 0.006830176963675877,
      "grad_norm": 0.1043090745806694,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.3495,
      "step": 11
    },
    {
      "epoch": 0.007451102142191866,
      "grad_norm": 0.07909780740737915,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.1299,
      "step": 12
    },
    {
      "epoch": 0.008072027320707855,
      "grad_norm": 0.10309865325689316,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.1467,
      "step": 13
    },
    {
      "epoch": 0.008692952499223843,
      "grad_norm": 0.07576113939285278,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.0304,
      "step": 14
    },
    {
      "epoch": 0.009313877677739833,
      "grad_norm": 0.08277754485607147,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.2009,
      "step": 15
    },
    {
      "epoch": 0.009934802856255821,
      "grad_norm": 0.12150026112794876,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.2354,
      "step": 16
    },
    {
      "epoch": 0.01055572803477181,
      "grad_norm": 0.07561292499303818,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.1034,
      "step": 17
    },
    {
      "epoch": 0.011176653213287799,
      "grad_norm": 0.0687914714217186,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.1705,
      "step": 18
    },
    {
      "epoch": 0.011176653213287799,
      "eval_loss": 0.09106625616550446,
      "eval_runtime": 196.4768,
      "eval_samples_per_second": 6.902,
      "eval_steps_per_second": 0.865,
      "step": 18
    },
    {
      "epoch": 0.011797578391803787,
      "grad_norm": 0.08030562102794647,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.2869,
      "step": 19
    },
    {
      "epoch": 0.012418503570319777,
      "grad_norm": 0.08804439008235931,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.1482,
      "step": 20
    },
    {
      "epoch": 0.013039428748835765,
      "grad_norm": 0.14267109334468842,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.0744,
      "step": 21
    },
    {
      "epoch": 0.013660353927351754,
      "grad_norm": 0.0642479732632637,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.1141,
      "step": 22
    },
    {
      "epoch": 0.014281279105867743,
      "grad_norm": 0.11642853915691376,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.2607,
      "step": 23
    },
    {
      "epoch": 0.014902204284383732,
      "grad_norm": 0.06851276010274887,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0412,
      "step": 24
    },
    {
      "epoch": 0.01552312946289972,
      "grad_norm": 0.09942375868558884,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.105,
      "step": 25
    },
    {
      "epoch": 0.01614405464141571,
      "grad_norm": 0.08792968839406967,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.1057,
      "step": 26
    },
    {
      "epoch": 0.016764979819931698,
      "grad_norm": 0.11934582889080048,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.3323,
      "step": 27
    },
    {
      "epoch": 0.016764979819931698,
      "eval_loss": 0.08386289328336716,
      "eval_runtime": 196.8416,
      "eval_samples_per_second": 6.889,
      "eval_steps_per_second": 0.864,
      "step": 27
    },
    {
      "epoch": 0.017385904998447686,
      "grad_norm": 0.10690551996231079,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.2852,
      "step": 28
    },
    {
      "epoch": 0.018006830176963674,
      "grad_norm": 0.10729014128446579,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.1705,
      "step": 29
    },
    {
      "epoch": 0.018627755355479666,
      "grad_norm": 0.08282957226037979,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.1005,
      "step": 30
    },
    {
      "epoch": 0.019248680533995654,
      "grad_norm": 0.0728306695818901,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.1307,
      "step": 31
    },
    {
      "epoch": 0.019869605712511642,
      "grad_norm": 0.09638900309801102,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.1735,
      "step": 32
    },
    {
      "epoch": 0.02049053089102763,
      "grad_norm": 0.16475456953048706,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.1015,
      "step": 33
    },
    {
      "epoch": 0.02111145606954362,
      "grad_norm": 0.06533080339431763,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.1143,
      "step": 34
    },
    {
      "epoch": 0.02173238124805961,
      "grad_norm": 0.10168042778968811,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.1452,
      "step": 35
    },
    {
      "epoch": 0.022353306426575598,
      "grad_norm": 0.07452461123466492,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.1062,
      "step": 36
    },
    {
      "epoch": 0.022353306426575598,
      "eval_loss": 0.0813056007027626,
      "eval_runtime": 196.8112,
      "eval_samples_per_second": 6.89,
      "eval_steps_per_second": 0.864,
      "step": 36
    },
    {
      "epoch": 0.022974231605091586,
      "grad_norm": 0.07804828137159348,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.1323,
      "step": 37
    },
    {
      "epoch": 0.023595156783607574,
      "grad_norm": 0.08380841463804245,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.1257,
      "step": 38
    },
    {
      "epoch": 0.024216081962123565,
      "grad_norm": 0.10386836528778076,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.1927,
      "step": 39
    },
    {
      "epoch": 0.024837007140639553,
      "grad_norm": 0.08352355659008026,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.215,
      "step": 40
    },
    {
      "epoch": 0.02545793231915554,
      "grad_norm": 0.202205091714859,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.1606,
      "step": 41
    },
    {
      "epoch": 0.02607885749767153,
      "grad_norm": 0.08188100904226303,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0946,
      "step": 42
    },
    {
      "epoch": 0.02669978267618752,
      "grad_norm": 0.07515822350978851,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.1653,
      "step": 43
    },
    {
      "epoch": 0.02732070785470351,
      "grad_norm": 0.09081997722387314,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.1845,
      "step": 44
    },
    {
      "epoch": 0.027941633033219497,
      "grad_norm": 0.09180609881877899,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.1406,
      "step": 45
    },
    {
      "epoch": 0.027941633033219497,
      "eval_loss": 0.07980942726135254,
      "eval_runtime": 196.6543,
      "eval_samples_per_second": 6.895,
      "eval_steps_per_second": 0.864,
      "step": 45
    },
    {
      "epoch": 0.028562558211735485,
      "grad_norm": 0.09287755936384201,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.1577,
      "step": 46
    },
    {
      "epoch": 0.029183483390251473,
      "grad_norm": 0.043771930038928986,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.0785,
      "step": 47
    },
    {
      "epoch": 0.029804408568767465,
      "grad_norm": 0.04385403171181679,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0575,
      "step": 48
    },
    {
      "epoch": 0.030425333747283453,
      "grad_norm": 0.07490763813257217,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.2689,
      "step": 49
    },
    {
      "epoch": 0.03104625892579944,
      "grad_norm": 0.07791085541248322,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.1212,
      "step": 50
    },
    {
      "epoch": 0.03166718410431543,
      "grad_norm": 0.07903222739696503,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.1891,
      "step": 51
    },
    {
      "epoch": 0.03228810928283142,
      "grad_norm": 0.07027075439691544,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.1198,
      "step": 52
    },
    {
      "epoch": 0.03290903446134741,
      "grad_norm": 0.07146333903074265,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.056,
      "step": 53
    },
    {
      "epoch": 0.033529959639863396,
      "grad_norm": 0.06251576542854309,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.1302,
      "step": 54
    },
    {
      "epoch": 0.033529959639863396,
      "eval_loss": 0.07887319475412369,
      "eval_runtime": 197.0406,
      "eval_samples_per_second": 6.882,
      "eval_steps_per_second": 0.863,
      "step": 54
    },
    {
      "epoch": 0.034150884818379384,
      "grad_norm": 0.09780936688184738,
      "learning_rate": 5e-05,
      "loss": 0.1407,
      "step": 55
    },
    {
      "epoch": 0.03477180999689537,
      "grad_norm": 0.1112448126077652,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.3002,
      "step": 56
    },
    {
      "epoch": 0.03539273517541136,
      "grad_norm": 0.08623827248811722,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.149,
      "step": 57
    },
    {
      "epoch": 0.03601366035392735,
      "grad_norm": 0.06050853431224823,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.1211,
      "step": 58
    },
    {
      "epoch": 0.036634585532443344,
      "grad_norm": 0.11154228448867798,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.261,
      "step": 59
    },
    {
      "epoch": 0.03725551071095933,
      "grad_norm": 0.09761973470449448,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.2088,
      "step": 60
    },
    {
      "epoch": 0.03787643588947532,
      "grad_norm": 0.09448567777872086,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.2188,
      "step": 61
    },
    {
      "epoch": 0.03849736106799131,
      "grad_norm": 0.14334271848201752,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.3294,
      "step": 62
    },
    {
      "epoch": 0.039118286246507296,
      "grad_norm": 0.05232716351747513,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.1154,
      "step": 63
    },
    {
      "epoch": 0.039118286246507296,
      "eval_loss": 0.0781964585185051,
      "eval_runtime": 196.8985,
      "eval_samples_per_second": 6.887,
      "eval_steps_per_second": 0.863,
      "step": 63
    },
    {
      "epoch": 0.039739211425023284,
      "grad_norm": 0.0912960097193718,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2111,
      "step": 64
    },
    {
      "epoch": 0.04036013660353927,
      "grad_norm": 0.12232377380132675,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.1729,
      "step": 65
    },
    {
      "epoch": 0.04098106178205526,
      "grad_norm": 0.08245333284139633,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.1402,
      "step": 66
    },
    {
      "epoch": 0.04160198696057125,
      "grad_norm": 0.12183276563882828,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.1373,
      "step": 67
    },
    {
      "epoch": 0.04222291213908724,
      "grad_norm": 0.06348512321710587,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.1206,
      "step": 68
    },
    {
      "epoch": 0.04284383731760323,
      "grad_norm": 0.09386453032493591,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.1482,
      "step": 69
    },
    {
      "epoch": 0.04346476249611922,
      "grad_norm": 0.05416074022650719,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.1152,
      "step": 70
    },
    {
      "epoch": 0.04408568767463521,
      "grad_norm": 0.08359821140766144,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.155,
      "step": 71
    },
    {
      "epoch": 0.044706612853151195,
      "grad_norm": 0.07346191257238388,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.1311,
      "step": 72
    },
    {
      "epoch": 0.044706612853151195,
      "eval_loss": 0.07774772495031357,
      "eval_runtime": 196.8503,
      "eval_samples_per_second": 6.888,
      "eval_steps_per_second": 0.864,
      "step": 72
    },
    {
      "epoch": 0.04532753803166718,
      "grad_norm": 0.06992657482624054,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0874,
      "step": 73
    },
    {
      "epoch": 0.04594846321018317,
      "grad_norm": 0.0818590447306633,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0875,
      "step": 74
    },
    {
      "epoch": 0.04656938838869916,
      "grad_norm": 0.04817086458206177,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0864,
      "step": 75
    },
    {
      "epoch": 0.04719031356721515,
      "grad_norm": 0.1407470554113388,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.2138,
      "step": 76
    },
    {
      "epoch": 0.04781123874573114,
      "grad_norm": 0.0823465958237648,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.1361,
      "step": 77
    },
    {
      "epoch": 0.04843216392424713,
      "grad_norm": 0.09610020369291306,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.1357,
      "step": 78
    },
    {
      "epoch": 0.04905308910276312,
      "grad_norm": 0.06676094979047775,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.1109,
      "step": 79
    },
    {
      "epoch": 0.04967401428127911,
      "grad_norm": 0.07106545567512512,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0834,
      "step": 80
    },
    {
      "epoch": 0.050294939459795095,
      "grad_norm": 0.06571792811155319,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.2109,
      "step": 81
    },
    {
      "epoch": 0.050294939459795095,
      "eval_loss": 0.07751059532165527,
      "eval_runtime": 196.8663,
      "eval_samples_per_second": 6.888,
      "eval_steps_per_second": 0.864,
      "step": 81
    },
    {
      "epoch": 0.05091586463831108,
      "grad_norm": 0.06973174959421158,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.085,
      "step": 82
    },
    {
      "epoch": 0.05153678981682707,
      "grad_norm": 0.09078380465507507,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.1149,
      "step": 83
    },
    {
      "epoch": 0.05215771499534306,
      "grad_norm": 0.08853405714035034,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.1259,
      "step": 84
    },
    {
      "epoch": 0.05277864017385905,
      "grad_norm": 0.046835608780384064,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0831,
      "step": 85
    },
    {
      "epoch": 0.05339956535237504,
      "grad_norm": 0.06550367176532745,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.103,
      "step": 86
    },
    {
      "epoch": 0.05402049053089103,
      "grad_norm": 0.10945193469524384,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.1612,
      "step": 87
    },
    {
      "epoch": 0.05464141570940702,
      "grad_norm": 0.07449627667665482,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.1054,
      "step": 88
    },
    {
      "epoch": 0.055262340887923006,
      "grad_norm": 0.06876291334629059,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.1125,
      "step": 89
    },
    {
      "epoch": 0.055883266066438994,
      "grad_norm": 0.0853685587644577,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.2923,
      "step": 90
    },
    {
      "epoch": 0.055883266066438994,
      "eval_loss": 0.07741052657365799,
      "eval_runtime": 196.569,
      "eval_samples_per_second": 6.898,
      "eval_steps_per_second": 0.865,
      "step": 90
    },
    {
      "epoch": 0.05650419124495498,
      "grad_norm": 0.07243622839450836,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0354,
      "step": 91
    },
    {
      "epoch": 0.05712511642347097,
      "grad_norm": 0.07864990830421448,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.1801,
      "step": 92
    },
    {
      "epoch": 0.05774604160198696,
      "grad_norm": 0.06895054131746292,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.1401,
      "step": 93
    },
    {
      "epoch": 0.058366966780502946,
      "grad_norm": 0.055806513875722885,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.1258,
      "step": 94
    },
    {
      "epoch": 0.05898789195901894,
      "grad_norm": 0.08117268234491348,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.1295,
      "step": 95
    },
    {
      "epoch": 0.05960881713753493,
      "grad_norm": 0.0856701135635376,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0834,
      "step": 96
    },
    {
      "epoch": 0.06022974231605092,
      "grad_norm": 0.05110366269946098,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.1204,
      "step": 97
    },
    {
      "epoch": 0.060850667494566905,
      "grad_norm": 0.07894067466259003,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0513,
      "step": 98
    },
    {
      "epoch": 0.061471592673082893,
      "grad_norm": 0.08335493505001068,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.191,
      "step": 99
    },
    {
      "epoch": 0.061471592673082893,
      "eval_loss": 0.07739631831645966,
      "eval_runtime": 196.8437,
      "eval_samples_per_second": 6.889,
      "eval_steps_per_second": 0.864,
      "step": 99
    },
    {
      "epoch": 0.06209251785159888,
      "grad_norm": 0.07276061922311783,
      "learning_rate": 0.0,
      "loss": 0.1111,
      "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": 2.5264363250122752e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}