{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 242,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01652892561983471,
      "grad_norm": 12.011792182922363,
      "learning_rate": 2.857142857142857e-05,
      "loss": 4.7518,
      "step": 2
    },
    {
      "epoch": 0.03305785123966942,
      "grad_norm": 12.689871788024902,
      "learning_rate": 5.714285714285714e-05,
      "loss": 4.687,
      "step": 4
    },
    {
      "epoch": 0.049586776859504134,
      "grad_norm": 11.848198890686035,
      "learning_rate": 8.571428571428571e-05,
      "loss": 4.4922,
      "step": 6
    },
    {
      "epoch": 0.06611570247933884,
      "grad_norm": 10.378408432006836,
      "learning_rate": 0.00011428571428571428,
      "loss": 3.4839,
      "step": 8
    },
    {
      "epoch": 0.08264462809917356,
      "grad_norm": 9.543920516967773,
      "learning_rate": 0.00014285714285714287,
      "loss": 2.4164,
      "step": 10
    },
    {
      "epoch": 0.09917355371900827,
      "grad_norm": 5.602456092834473,
      "learning_rate": 0.00017142857142857143,
      "loss": 1.838,
      "step": 12
    },
    {
      "epoch": 0.11570247933884298,
      "grad_norm": 1.7414193153381348,
      "learning_rate": 0.0002,
      "loss": 1.4404,
      "step": 14
    },
    {
      "epoch": 0.1322314049586777,
      "grad_norm": 1.0191770792007446,
      "learning_rate": 0.0001999910643210378,
      "loss": 1.3474,
      "step": 16
    },
    {
      "epoch": 0.1487603305785124,
      "grad_norm": 3.509352922439575,
      "learning_rate": 0.0001999642588810784,
      "loss": 1.3789,
      "step": 18
    },
    {
      "epoch": 0.1652892561983471,
      "grad_norm": 2.426680088043213,
      "learning_rate": 0.00019991958847061784,
      "loss": 1.2245,
      "step": 20
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.8060101270675659,
      "learning_rate": 0.00019985706107286514,
      "loss": 1.2259,
      "step": 22
    },
    {
      "epoch": 0.19834710743801653,
      "grad_norm": 1.6215940713882446,
      "learning_rate": 0.00019977668786231534,
      "loss": 1.1992,
      "step": 24
    },
    {
      "epoch": 0.21487603305785125,
      "grad_norm": 2.476259231567383,
      "learning_rate": 0.0001996784832027525,
      "loss": 1.2782,
      "step": 26
    },
    {
      "epoch": 0.23140495867768596,
      "grad_norm": 2.04018235206604,
      "learning_rate": 0.00019956246464468294,
      "loss": 1.23,
      "step": 28
    },
    {
      "epoch": 0.24793388429752067,
      "grad_norm": 1.8799017667770386,
      "learning_rate": 0.00019942865292219838,
      "loss": 1.2164,
      "step": 30
    },
    {
      "epoch": 0.2644628099173554,
      "grad_norm": 1.2413148880004883,
      "learning_rate": 0.00019927707194927066,
      "loss": 1.2924,
      "step": 32
    },
    {
      "epoch": 0.2809917355371901,
      "grad_norm": 1.8723937273025513,
      "learning_rate": 0.000199107748815478,
      "loss": 1.2302,
      "step": 34
    },
    {
      "epoch": 0.2975206611570248,
      "grad_norm": 1.393110752105713,
      "learning_rate": 0.00019892071378116376,
      "loss": 1.2276,
      "step": 36
    },
    {
      "epoch": 0.3140495867768595,
      "grad_norm": 1.1459721326828003,
      "learning_rate": 0.0001987160002720283,
      "loss": 1.1504,
      "step": 38
    },
    {
      "epoch": 0.3305785123966942,
      "grad_norm": 1.4680942296981812,
      "learning_rate": 0.00019849364487315558,
      "loss": 1.1623,
      "step": 40
    },
    {
      "epoch": 0.34710743801652894,
      "grad_norm": 1.8715866804122925,
      "learning_rate": 0.0001982536873224748,
      "loss": 1.2155,
      "step": 42
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.871064305305481,
      "learning_rate": 0.0001979961705036587,
      "loss": 1.1594,
      "step": 44
    },
    {
      "epoch": 0.38016528925619836,
      "grad_norm": 0.8239800930023193,
      "learning_rate": 0.00019772114043845965,
      "loss": 1.1501,
      "step": 46
    },
    {
      "epoch": 0.39669421487603307,
      "grad_norm": 0.9587319493293762,
      "learning_rate": 0.0001974286462784851,
      "loss": 1.1195,
      "step": 48
    },
    {
      "epoch": 0.4132231404958678,
      "grad_norm": 1.1645926237106323,
      "learning_rate": 0.0001971187402964132,
      "loss": 1.1417,
      "step": 50
    },
    {
      "epoch": 0.4297520661157025,
      "grad_norm": 0.576813817024231,
      "learning_rate": 0.00019679147787665126,
      "loss": 1.1445,
      "step": 52
    },
    {
      "epoch": 0.4462809917355372,
      "grad_norm": 1.0733133554458618,
      "learning_rate": 0.00019644691750543767,
      "loss": 1.0979,
      "step": 54
    },
    {
      "epoch": 0.4628099173553719,
      "grad_norm": 0.5801639556884766,
      "learning_rate": 0.00019608512076038962,
      "loss": 1.0977,
      "step": 56
    },
    {
      "epoch": 0.4793388429752066,
      "grad_norm": 1.6796538829803467,
      "learning_rate": 0.00019570615229949842,
      "loss": 1.1925,
      "step": 58
    },
    {
      "epoch": 0.49586776859504134,
      "grad_norm": 1.0563887357711792,
      "learning_rate": 0.00019531007984957408,
      "loss": 1.0657,
      "step": 60
    },
    {
      "epoch": 0.512396694214876,
      "grad_norm": 0.9109811186790466,
      "learning_rate": 0.00019489697419414182,
      "loss": 1.1098,
      "step": 62
    },
    {
      "epoch": 0.5289256198347108,
      "grad_norm": 0.7321667671203613,
      "learning_rate": 0.0001944669091607919,
      "loss": 1.0929,
      "step": 64
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.685366690158844,
      "learning_rate": 0.00019401996160798573,
      "loss": 1.1242,
      "step": 66
    },
    {
      "epoch": 0.5619834710743802,
      "grad_norm": 0.8959838151931763,
      "learning_rate": 0.0001935562114113202,
      "loss": 1.181,
      "step": 68
    },
    {
      "epoch": 0.5785123966942148,
      "grad_norm": 0.9717262983322144,
      "learning_rate": 0.00019307574144925287,
      "loss": 1.2295,
      "step": 70
    },
    {
      "epoch": 0.5950413223140496,
      "grad_norm": 1.0358582735061646,
      "learning_rate": 0.00019257863758829035,
      "loss": 1.1431,
      "step": 72
    },
    {
      "epoch": 0.6115702479338843,
      "grad_norm": 0.7998526096343994,
      "learning_rate": 0.00019206498866764288,
      "loss": 1.1032,
      "step": 74
    },
    {
      "epoch": 0.628099173553719,
      "grad_norm": 1.1496188640594482,
      "learning_rate": 0.0001915348864833476,
      "loss": 1.057,
      "step": 76
    },
    {
      "epoch": 0.6446280991735537,
      "grad_norm": 0.652406632900238,
      "learning_rate": 0.00019098842577186314,
      "loss": 1.146,
      "step": 78
    },
    {
      "epoch": 0.6611570247933884,
      "grad_norm": 0.9454944729804993,
      "learning_rate": 0.00019042570419313925,
      "loss": 1.1543,
      "step": 80
    },
    {
      "epoch": 0.6776859504132231,
      "grad_norm": 0.7456652522087097,
      "learning_rate": 0.00018984682231316333,
      "loss": 1.1189,
      "step": 82
    },
    {
      "epoch": 0.6942148760330579,
      "grad_norm": 0.7312512397766113,
      "learning_rate": 0.00018925188358598813,
      "loss": 1.0873,
      "step": 84
    },
    {
      "epoch": 0.7107438016528925,
      "grad_norm": 0.8474765419960022,
      "learning_rate": 0.000188640994335243,
      "loss": 1.1698,
      "step": 86
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.6979633569717407,
      "learning_rate": 0.0001880142637351325,
      "loss": 1.1417,
      "step": 88
    },
    {
      "epoch": 0.743801652892562,
      "grad_norm": 0.5989161133766174,
      "learning_rate": 0.00018737180379092537,
      "loss": 1.0479,
      "step": 90
    },
    {
      "epoch": 0.7603305785123967,
      "grad_norm": 0.5765272378921509,
      "learning_rate": 0.00018671372931893773,
      "loss": 1.1336,
      "step": 92
    },
    {
      "epoch": 0.7768595041322314,
      "grad_norm": 0.6709849834442139,
      "learning_rate": 0.00018604015792601396,
      "loss": 1.1157,
      "step": 94
    },
    {
      "epoch": 0.7933884297520661,
      "grad_norm": 0.8181343674659729,
      "learning_rate": 0.00018535120998850848,
      "loss": 1.0927,
      "step": 96
    },
    {
      "epoch": 0.8099173553719008,
      "grad_norm": 0.6146332621574402,
      "learning_rate": 0.00018464700863077312,
      "loss": 1.0739,
      "step": 98
    },
    {
      "epoch": 0.8264462809917356,
      "grad_norm": 0.9904415011405945,
      "learning_rate": 0.00018392767970315313,
      "loss": 1.0331,
      "step": 100
    },
    {
      "epoch": 0.8429752066115702,
      "grad_norm": 0.6186695694923401,
      "learning_rate": 0.0001831933517594957,
      "loss": 1.0513,
      "step": 102
    },
    {
      "epoch": 0.859504132231405,
      "grad_norm": 1.1912785768508911,
      "learning_rate": 0.00018244415603417603,
      "loss": 1.1567,
      "step": 104
    },
    {
      "epoch": 0.8760330578512396,
      "grad_norm": 1.3681318759918213,
      "learning_rate": 0.00018168022641864377,
      "loss": 1.1497,
      "step": 106
    },
    {
      "epoch": 0.8925619834710744,
      "grad_norm": 0.619476318359375,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.1546,
      "step": 108
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.7421219348907471,
      "learning_rate": 0.00018010871422407236,
      "loss": 1.1458,
      "step": 110
    },
    {
      "epoch": 0.9256198347107438,
      "grad_norm": 0.6569286584854126,
      "learning_rate": 0.00017930141249560233,
      "loss": 1.12,
      "step": 112
    },
    {
      "epoch": 0.9421487603305785,
      "grad_norm": 0.4168110191822052,
      "learning_rate": 0.0001784799385278661,
      "loss": 1.1682,
      "step": 114
    },
    {
      "epoch": 0.9586776859504132,
      "grad_norm": 0.5620162487030029,
      "learning_rate": 0.00017764443912941672,
      "loss": 1.1828,
      "step": 116
    },
    {
      "epoch": 0.9752066115702479,
      "grad_norm": 0.8095484375953674,
      "learning_rate": 0.00017679506361534215,
      "loss": 1.1953,
      "step": 118
    },
    {
      "epoch": 0.9917355371900827,
      "grad_norm": 0.7646257281303406,
      "learning_rate": 0.0001759319637805806,
      "loss": 1.2148,
      "step": 120
    },
    {
      "epoch": 1.0082644628099173,
      "grad_norm": 0.5254501104354858,
      "learning_rate": 0.00017505529387279277,
      "loss": 1.1359,
      "step": 122
    },
    {
      "epoch": 1.024793388429752,
      "grad_norm": 0.6001765727996826,
      "learning_rate": 0.00017416521056479577,
      "loss": 1.1336,
      "step": 124
    },
    {
      "epoch": 1.0413223140495869,
      "grad_norm": 0.35407504439353943,
      "learning_rate": 0.00017326187292656333,
      "loss": 1.1833,
      "step": 126
    },
    {
      "epoch": 1.0578512396694215,
      "grad_norm": 0.414528489112854,
      "learning_rate": 0.00017234544239679806,
      "loss": 1.1301,
      "step": 128
    },
    {
      "epoch": 1.0743801652892562,
      "grad_norm": 0.46355852484703064,
      "learning_rate": 0.00017141608275408006,
      "loss": 1.213,
      "step": 130
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.5040593147277832,
      "learning_rate": 0.00017047396008759754,
      "loss": 1.132,
      "step": 132
    },
    {
      "epoch": 1.1074380165289257,
      "grad_norm": 0.4813704192638397,
      "learning_rate": 0.00016951924276746425,
      "loss": 1.0831,
      "step": 134
    },
    {
      "epoch": 1.1239669421487604,
      "grad_norm": 0.5174686312675476,
      "learning_rate": 0.00016855210141462963,
      "loss": 1.0514,
      "step": 136
    },
    {
      "epoch": 1.140495867768595,
      "grad_norm": 0.4712466299533844,
      "learning_rate": 0.00016757270887038654,
      "loss": 1.1334,
      "step": 138
    },
    {
      "epoch": 1.1570247933884297,
      "grad_norm": 0.5912173390388489,
      "learning_rate": 0.00016658124016548197,
      "loss": 1.1011,
      "step": 140
    },
    {
      "epoch": 1.1735537190082646,
      "grad_norm": 0.6392802000045776,
      "learning_rate": 0.00016557787248883696,
      "loss": 1.1361,
      "step": 142
    },
    {
      "epoch": 1.1900826446280992,
      "grad_norm": 0.7376368045806885,
      "learning_rate": 0.00016456278515588024,
      "loss": 1.109,
      "step": 144
    },
    {
      "epoch": 1.2066115702479339,
      "grad_norm": 0.5020875930786133,
      "learning_rate": 0.00016353615957650236,
      "loss": 1.0925,
      "step": 146
    },
    {
      "epoch": 1.2231404958677685,
      "grad_norm": 0.8081740736961365,
      "learning_rate": 0.00016249817922263517,
      "loss": 1.047,
      "step": 148
    },
    {
      "epoch": 1.2396694214876034,
      "grad_norm": 0.6371219754219055,
      "learning_rate": 0.00016144902959546286,
      "loss": 1.113,
      "step": 150
    },
    {
      "epoch": 1.256198347107438,
      "grad_norm": 0.7588189840316772,
      "learning_rate": 0.00016038889819227045,
      "loss": 1.1179,
      "step": 152
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 0.6286205053329468,
      "learning_rate": 0.00015931797447293552,
      "loss": 1.1209,
      "step": 154
    },
    {
      "epoch": 1.2892561983471074,
      "grad_norm": 0.797656238079071,
      "learning_rate": 0.00015823644982606905,
      "loss": 1.1698,
      "step": 156
    },
    {
      "epoch": 1.3057851239669422,
      "grad_norm": 0.5368632078170776,
      "learning_rate": 0.00015714451753481168,
      "loss": 1.1973,
      "step": 158
    },
    {
      "epoch": 1.322314049586777,
      "grad_norm": 0.4135212302207947,
      "learning_rate": 0.00015604237274229147,
      "loss": 1.1452,
      "step": 160
    },
    {
      "epoch": 1.3388429752066116,
      "grad_norm": 0.5289668440818787,
      "learning_rate": 0.00015493021241674918,
      "loss": 1.1954,
      "step": 162
    },
    {
      "epoch": 1.3553719008264462,
      "grad_norm": 0.4092061221599579,
      "learning_rate": 0.00015380823531633729,
      "loss": 1.1226,
      "step": 164
    },
    {
      "epoch": 1.3719008264462809,
      "grad_norm": 0.7049645781517029,
      "learning_rate": 0.00015267664195359917,
      "loss": 1.0948,
      "step": 166
    },
    {
      "epoch": 1.3884297520661157,
      "grad_norm": 0.47164198756217957,
      "learning_rate": 0.00015153563455963499,
      "loss": 1.0977,
      "step": 168
    },
    {
      "epoch": 1.4049586776859504,
      "grad_norm": 0.7871695160865784,
      "learning_rate": 0.00015038541704796003,
      "loss": 1.1674,
      "step": 170
    },
    {
      "epoch": 1.421487603305785,
      "grad_norm": 0.5381121635437012,
      "learning_rate": 0.00014922619497806277,
      "loss": 1.1415,
      "step": 172
    },
    {
      "epoch": 1.43801652892562,
      "grad_norm": 0.39419299364089966,
      "learning_rate": 0.00014805817551866838,
      "loss": 1.0747,
      "step": 174
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.38382914662361145,
      "learning_rate": 0.00014688156741071514,
      "loss": 1.1278,
      "step": 176
    },
    {
      "epoch": 1.4710743801652892,
      "grad_norm": 0.32674962282180786,
      "learning_rate": 0.00014569658093004935,
      "loss": 0.9774,
      "step": 178
    },
    {
      "epoch": 1.487603305785124,
      "grad_norm": 0.5443088412284851,
      "learning_rate": 0.00014450342784984633,
      "loss": 1.034,
      "step": 180
    },
    {
      "epoch": 1.5041322314049586,
      "grad_norm": 0.6682401895523071,
      "learning_rate": 0.00014330232140276366,
      "loss": 1.1732,
      "step": 182
    },
    {
      "epoch": 1.5206611570247934,
      "grad_norm": 0.5696044564247131,
      "learning_rate": 0.0001420934762428335,
      "loss": 1.0384,
      "step": 184
    },
    {
      "epoch": 1.537190082644628,
      "grad_norm": 0.6782551407814026,
      "learning_rate": 0.0001408771084071012,
      "loss": 1.1107,
      "step": 186
    },
    {
      "epoch": 1.553719008264463,
      "grad_norm": 0.8336123824119568,
      "learning_rate": 0.00013965343527701628,
      "loss": 1.0737,
      "step": 188
    },
    {
      "epoch": 1.5702479338842976,
      "grad_norm": 0.539226233959198,
      "learning_rate": 0.00013842267553958371,
      "loss": 1.1665,
      "step": 190
    },
    {
      "epoch": 1.5867768595041323,
      "grad_norm": 0.566620409488678,
      "learning_rate": 0.00013718504914828135,
      "loss": 1.1333,
      "step": 192
    },
    {
      "epoch": 1.603305785123967,
      "grad_norm": 0.4735005795955658,
      "learning_rate": 0.00013594077728375128,
      "loss": 1.1709,
      "step": 194
    },
    {
      "epoch": 1.6198347107438016,
      "grad_norm": 0.534383237361908,
      "learning_rate": 0.00013469008231427207,
      "loss": 1.0783,
      "step": 196
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 0.8410363793373108,
      "learning_rate": 0.0001334331877560182,
      "loss": 1.0708,
      "step": 198
    },
    {
      "epoch": 1.6528925619834711,
      "grad_norm": 0.6392219662666321,
      "learning_rate": 0.00013217031823311488,
      "loss": 1.0329,
      "step": 200
    },
    {
      "epoch": 1.6694214876033058,
      "grad_norm": 0.5770404934883118,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.0404,
      "step": 202
    },
    {
      "epoch": 1.6859504132231407,
      "grad_norm": 0.6814575791358948,
      "learning_rate": 0.00012962755808856342,
      "loss": 1.0702,
      "step": 204
    },
    {
      "epoch": 1.7024793388429753,
      "grad_norm": 0.673312783241272,
      "learning_rate": 0.0001283481218926818,
      "loss": 1.0529,
      "step": 206
    },
    {
      "epoch": 1.71900826446281,
      "grad_norm": 0.6180073618888855,
      "learning_rate": 0.0001270636195024719,
      "loss": 1.0257,
      "step": 208
    },
    {
      "epoch": 1.7355371900826446,
      "grad_norm": 0.5565724968910217,
      "learning_rate": 0.00012577428047595344,
      "loss": 1.1102,
      "step": 210
    },
    {
      "epoch": 1.7520661157024793,
      "grad_norm": 0.5586270689964294,
      "learning_rate": 0.00012448033523551865,
      "loss": 1.0277,
      "step": 212
    },
    {
      "epoch": 1.768595041322314,
      "grad_norm": 0.542448878288269,
      "learning_rate": 0.00012318201502675285,
      "loss": 1.0988,
      "step": 214
    },
    {
      "epoch": 1.7851239669421488,
      "grad_norm": 0.513042151927948,
      "learning_rate": 0.0001218795518771075,
      "loss": 1.0828,
      "step": 216
    },
    {
      "epoch": 1.8016528925619835,
      "grad_norm": 0.7613060474395752,
      "learning_rate": 0.00012057317855443395,
      "loss": 1.1962,
      "step": 218
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.7522129416465759,
      "learning_rate": 0.00011926312852538455,
      "loss": 1.1339,
      "step": 220
    },
    {
      "epoch": 1.834710743801653,
      "grad_norm": 0.4655594825744629,
      "learning_rate": 0.00011794963591368893,
      "loss": 1.0967,
      "step": 222
    },
    {
      "epoch": 1.8512396694214877,
      "grad_norm": 0.5036570429801941,
      "learning_rate": 0.00011663293545831302,
      "loss": 1.0361,
      "step": 224
    },
    {
      "epoch": 1.8677685950413223,
      "grad_norm": 0.43016380071640015,
      "learning_rate": 0.00011531326247150803,
      "loss": 1.1281,
      "step": 226
    },
    {
      "epoch": 1.884297520661157,
      "grad_norm": 0.5184316635131836,
      "learning_rate": 0.00011399085279675687,
      "loss": 1.2083,
      "step": 228
    },
    {
      "epoch": 1.9008264462809916,
      "grad_norm": 0.6556355357170105,
      "learning_rate": 0.0001126659427666257,
      "loss": 1.0266,
      "step": 230
    },
    {
      "epoch": 1.9173553719008265,
      "grad_norm": 0.515681803226471,
      "learning_rate": 0.00011133876916052821,
      "loss": 1.0472,
      "step": 232
    },
    {
      "epoch": 1.9338842975206612,
      "grad_norm": 0.4592064321041107,
      "learning_rate": 0.00011000956916240985,
      "loss": 1.054,
      "step": 234
    },
    {
      "epoch": 1.950413223140496,
      "grad_norm": 0.5623230338096619,
      "learning_rate": 0.00010867858031835975,
      "loss": 1.1571,
      "step": 236
    },
    {
      "epoch": 1.9669421487603307,
      "grad_norm": 0.5241667032241821,
      "learning_rate": 0.00010734604049415822,
      "loss": 1.0985,
      "step": 238
    },
    {
      "epoch": 1.9834710743801653,
      "grad_norm": 0.54905104637146,
      "learning_rate": 0.00010601218783276672,
      "loss": 1.1088,
      "step": 240
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.8823345303535461,
      "learning_rate": 0.00010467726071176853,
      "loss": 1.0991,
      "step": 242
    }
  ],
  "logging_steps": 2,
  "max_steps": 484,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4578676410679296.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}