{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.057189878625797,
  "eval_steps": 500,
  "global_step": 2500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016457519029006377,
      "grad_norm": 1.7265625,
      "learning_rate": 4e-05,
      "loss": 3.4409,
      "step": 20
    },
    {
      "epoch": 0.032915038058012755,
      "grad_norm": 1.125,
      "learning_rate": 8e-05,
      "loss": 2.834,
      "step": 40
    },
    {
      "epoch": 0.04937255708701913,
      "grad_norm": 2.203125,
      "learning_rate": 0.00012,
      "loss": 2.0422,
      "step": 60
    },
    {
      "epoch": 0.06583007611602551,
      "grad_norm": 1.734375,
      "learning_rate": 0.00016,
      "loss": 1.6617,
      "step": 80
    },
    {
      "epoch": 0.08228759514503188,
      "grad_norm": 1.4765625,
      "learning_rate": 0.0002,
      "loss": 1.5035,
      "step": 100
    },
    {
      "epoch": 0.09874511417403826,
      "grad_norm": 1.6328125,
      "learning_rate": 0.0001988716502115656,
      "loss": 1.4449,
      "step": 120
    },
    {
      "epoch": 0.11520263320304464,
      "grad_norm": 2.015625,
      "learning_rate": 0.00019774330042313118,
      "loss": 1.3653,
      "step": 140
    },
    {
      "epoch": 0.13166015223205102,
      "grad_norm": 1.640625,
      "learning_rate": 0.00019661495063469676,
      "loss": 1.3634,
      "step": 160
    },
    {
      "epoch": 0.1481176712610574,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00019548660084626237,
      "loss": 1.3116,
      "step": 180
    },
    {
      "epoch": 0.16457519029006376,
      "grad_norm": 1.1796875,
      "learning_rate": 0.00019435825105782795,
      "loss": 1.2961,
      "step": 200
    },
    {
      "epoch": 0.18103270931907015,
      "grad_norm": 1.359375,
      "learning_rate": 0.00019322990126939354,
      "loss": 1.2868,
      "step": 220
    },
    {
      "epoch": 0.19749022834807653,
      "grad_norm": 1.2421875,
      "learning_rate": 0.0001921015514809591,
      "loss": 1.2902,
      "step": 240
    },
    {
      "epoch": 0.21394774737708291,
      "grad_norm": 1.5859375,
      "learning_rate": 0.00019097320169252468,
      "loss": 1.209,
      "step": 260
    },
    {
      "epoch": 0.23040526640608927,
      "grad_norm": 1.5859375,
      "learning_rate": 0.00018984485190409026,
      "loss": 1.2912,
      "step": 280
    },
    {
      "epoch": 0.24686278543509566,
      "grad_norm": 1.4296875,
      "learning_rate": 0.00018871650211565587,
      "loss": 1.2733,
      "step": 300
    },
    {
      "epoch": 0.26332030446410204,
      "grad_norm": 1.4140625,
      "learning_rate": 0.00018758815232722145,
      "loss": 1.1895,
      "step": 320
    },
    {
      "epoch": 0.2797778234931084,
      "grad_norm": 1.25,
      "learning_rate": 0.00018645980253878704,
      "loss": 1.2259,
      "step": 340
    },
    {
      "epoch": 0.2962353425221148,
      "grad_norm": 1.4921875,
      "learning_rate": 0.00018533145275035262,
      "loss": 1.2636,
      "step": 360
    },
    {
      "epoch": 0.3126928615511212,
      "grad_norm": 1.796875,
      "learning_rate": 0.0001842031029619182,
      "loss": 1.2748,
      "step": 380
    },
    {
      "epoch": 0.3291503805801275,
      "grad_norm": 1.4296875,
      "learning_rate": 0.0001830747531734838,
      "loss": 1.1335,
      "step": 400
    },
    {
      "epoch": 0.3456078996091339,
      "grad_norm": 1.6640625,
      "learning_rate": 0.00018194640338504937,
      "loss": 1.1985,
      "step": 420
    },
    {
      "epoch": 0.3620654186381403,
      "grad_norm": 1.5078125,
      "learning_rate": 0.00018081805359661496,
      "loss": 1.2015,
      "step": 440
    },
    {
      "epoch": 0.3785229376671467,
      "grad_norm": 1.53125,
      "learning_rate": 0.00017968970380818057,
      "loss": 1.1548,
      "step": 460
    },
    {
      "epoch": 0.39498045669615306,
      "grad_norm": 1.359375,
      "learning_rate": 0.00017856135401974612,
      "loss": 1.1249,
      "step": 480
    },
    {
      "epoch": 0.41143797572515944,
      "grad_norm": 1.7109375,
      "learning_rate": 0.0001774330042313117,
      "loss": 1.1734,
      "step": 500
    },
    {
      "epoch": 0.42789549475416583,
      "grad_norm": 1.71875,
      "learning_rate": 0.0001763046544428773,
      "loss": 1.1772,
      "step": 520
    },
    {
      "epoch": 0.4443530137831722,
      "grad_norm": 1.2578125,
      "learning_rate": 0.00017517630465444287,
      "loss": 1.1092,
      "step": 540
    },
    {
      "epoch": 0.46081053281217854,
      "grad_norm": 1.234375,
      "learning_rate": 0.00017404795486600846,
      "loss": 1.1306,
      "step": 560
    },
    {
      "epoch": 0.4772680518411849,
      "grad_norm": 1.5234375,
      "learning_rate": 0.00017291960507757407,
      "loss": 1.1457,
      "step": 580
    },
    {
      "epoch": 0.4937255708701913,
      "grad_norm": 1.4375,
      "learning_rate": 0.00017179125528913965,
      "loss": 1.1501,
      "step": 600
    },
    {
      "epoch": 0.5101830898991977,
      "grad_norm": 1.1796875,
      "learning_rate": 0.00017066290550070523,
      "loss": 1.1539,
      "step": 620
    },
    {
      "epoch": 0.5266406089282041,
      "grad_norm": 1.3984375,
      "learning_rate": 0.00016953455571227082,
      "loss": 1.1242,
      "step": 640
    },
    {
      "epoch": 0.5430981279572105,
      "grad_norm": 1.6015625,
      "learning_rate": 0.0001684062059238364,
      "loss": 1.1551,
      "step": 660
    },
    {
      "epoch": 0.5595556469862168,
      "grad_norm": 1.0625,
      "learning_rate": 0.00016727785613540198,
      "loss": 1.1252,
      "step": 680
    },
    {
      "epoch": 0.5760131660152232,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00016614950634696757,
      "loss": 1.1023,
      "step": 700
    },
    {
      "epoch": 0.5924706850442296,
      "grad_norm": 1.28125,
      "learning_rate": 0.00016502115655853315,
      "loss": 1.1136,
      "step": 720
    },
    {
      "epoch": 0.608928204073236,
      "grad_norm": 1.34375,
      "learning_rate": 0.00016389280677009873,
      "loss": 1.1363,
      "step": 740
    },
    {
      "epoch": 0.6253857231022424,
      "grad_norm": 1.3671875,
      "learning_rate": 0.00016276445698166432,
      "loss": 1.0763,
      "step": 760
    },
    {
      "epoch": 0.6418432421312487,
      "grad_norm": 1.34375,
      "learning_rate": 0.0001616361071932299,
      "loss": 1.1558,
      "step": 780
    },
    {
      "epoch": 0.658300761160255,
      "grad_norm": 1.140625,
      "learning_rate": 0.00016050775740479548,
      "loss": 1.0374,
      "step": 800
    },
    {
      "epoch": 0.6747582801892614,
      "grad_norm": 1.40625,
      "learning_rate": 0.00015937940761636107,
      "loss": 1.1492,
      "step": 820
    },
    {
      "epoch": 0.6912157992182678,
      "grad_norm": 1.5234375,
      "learning_rate": 0.00015825105782792665,
      "loss": 1.1261,
      "step": 840
    },
    {
      "epoch": 0.7076733182472742,
      "grad_norm": 1.46875,
      "learning_rate": 0.00015712270803949226,
      "loss": 1.1236,
      "step": 860
    },
    {
      "epoch": 0.7241308372762806,
      "grad_norm": 1.5,
      "learning_rate": 0.00015599435825105785,
      "loss": 1.0795,
      "step": 880
    },
    {
      "epoch": 0.740588356305287,
      "grad_norm": 1.28125,
      "learning_rate": 0.00015486600846262343,
      "loss": 1.0866,
      "step": 900
    },
    {
      "epoch": 0.7570458753342934,
      "grad_norm": 1.640625,
      "learning_rate": 0.000153737658674189,
      "loss": 1.0635,
      "step": 920
    },
    {
      "epoch": 0.7735033943632997,
      "grad_norm": 1.453125,
      "learning_rate": 0.0001526093088857546,
      "loss": 1.1106,
      "step": 940
    },
    {
      "epoch": 0.7899609133923061,
      "grad_norm": 1.0390625,
      "learning_rate": 0.00015148095909732018,
      "loss": 1.1241,
      "step": 960
    },
    {
      "epoch": 0.8064184324213125,
      "grad_norm": 1.296875,
      "learning_rate": 0.00015035260930888576,
      "loss": 1.078,
      "step": 980
    },
    {
      "epoch": 0.8228759514503189,
      "grad_norm": 1.109375,
      "learning_rate": 0.00014922425952045135,
      "loss": 1.1545,
      "step": 1000
    },
    {
      "epoch": 0.8393334704793253,
      "grad_norm": 1.5703125,
      "learning_rate": 0.00014809590973201693,
      "loss": 1.1102,
      "step": 1020
    },
    {
      "epoch": 0.8557909895083317,
      "grad_norm": 1.2265625,
      "learning_rate": 0.0001469675599435825,
      "loss": 1.0258,
      "step": 1040
    },
    {
      "epoch": 0.872248508537338,
      "grad_norm": 1.4609375,
      "learning_rate": 0.0001458392101551481,
      "loss": 1.1205,
      "step": 1060
    },
    {
      "epoch": 0.8887060275663444,
      "grad_norm": 1.40625,
      "learning_rate": 0.00014471086036671368,
      "loss": 1.0562,
      "step": 1080
    },
    {
      "epoch": 0.9051635465953507,
      "grad_norm": 1.203125,
      "learning_rate": 0.00014358251057827926,
      "loss": 1.1234,
      "step": 1100
    },
    {
      "epoch": 0.9216210656243571,
      "grad_norm": 1.3046875,
      "learning_rate": 0.00014245416078984485,
      "loss": 1.0511,
      "step": 1120
    },
    {
      "epoch": 0.9380785846533635,
      "grad_norm": 1.0546875,
      "learning_rate": 0.00014132581100141046,
      "loss": 1.0451,
      "step": 1140
    },
    {
      "epoch": 0.9545361036823699,
      "grad_norm": 1.3046875,
      "learning_rate": 0.00014019746121297604,
      "loss": 1.0539,
      "step": 1160
    },
    {
      "epoch": 0.9709936227113762,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00013906911142454162,
      "loss": 1.0957,
      "step": 1180
    },
    {
      "epoch": 0.9874511417403826,
      "grad_norm": 1.7109375,
      "learning_rate": 0.0001379407616361072,
      "loss": 1.1191,
      "step": 1200
    },
    {
      "epoch": 1.003908660769389,
      "grad_norm": 1.5625,
      "learning_rate": 0.0001368124118476728,
      "loss": 1.0942,
      "step": 1220
    },
    {
      "epoch": 1.0203661797983954,
      "grad_norm": 1.359375,
      "learning_rate": 0.00013568406205923835,
      "loss": 0.9808,
      "step": 1240
    },
    {
      "epoch": 1.0368236988274018,
      "grad_norm": 1.359375,
      "learning_rate": 0.00013455571227080396,
      "loss": 0.9606,
      "step": 1260
    },
    {
      "epoch": 1.0532812178564082,
      "grad_norm": 1.40625,
      "learning_rate": 0.00013342736248236954,
      "loss": 0.9658,
      "step": 1280
    },
    {
      "epoch": 1.0697387368854145,
      "grad_norm": 1.3828125,
      "learning_rate": 0.00013229901269393512,
      "loss": 0.8955,
      "step": 1300
    },
    {
      "epoch": 1.086196255914421,
      "grad_norm": 1.34375,
      "learning_rate": 0.0001311706629055007,
      "loss": 0.9449,
      "step": 1320
    },
    {
      "epoch": 1.1026537749434273,
      "grad_norm": 1.4296875,
      "learning_rate": 0.0001300423131170663,
      "loss": 0.936,
      "step": 1340
    },
    {
      "epoch": 1.1191112939724337,
      "grad_norm": 1.6015625,
      "learning_rate": 0.00012891396332863187,
      "loss": 0.8886,
      "step": 1360
    },
    {
      "epoch": 1.13556881300144,
      "grad_norm": 1.8125,
      "learning_rate": 0.00012778561354019746,
      "loss": 0.9193,
      "step": 1380
    },
    {
      "epoch": 1.1520263320304465,
      "grad_norm": 2.09375,
      "learning_rate": 0.00012665726375176307,
      "loss": 0.8895,
      "step": 1400
    },
    {
      "epoch": 1.1684838510594528,
      "grad_norm": 1.5703125,
      "learning_rate": 0.00012552891396332865,
      "loss": 0.9278,
      "step": 1420
    },
    {
      "epoch": 1.1849413700884592,
      "grad_norm": 1.5546875,
      "learning_rate": 0.00012440056417489424,
      "loss": 0.9096,
      "step": 1440
    },
    {
      "epoch": 1.2013988891174656,
      "grad_norm": 1.703125,
      "learning_rate": 0.00012327221438645982,
      "loss": 0.9084,
      "step": 1460
    },
    {
      "epoch": 1.217856408146472,
      "grad_norm": 1.1640625,
      "learning_rate": 0.0001221438645980254,
      "loss": 0.971,
      "step": 1480
    },
    {
      "epoch": 1.2343139271754784,
      "grad_norm": 1.4375,
      "learning_rate": 0.00012101551480959097,
      "loss": 0.9663,
      "step": 1500
    },
    {
      "epoch": 1.2507714462044848,
      "grad_norm": 1.2578125,
      "learning_rate": 0.00011988716502115656,
      "loss": 0.8331,
      "step": 1520
    },
    {
      "epoch": 1.2672289652334912,
      "grad_norm": 1.65625,
      "learning_rate": 0.00011875881523272214,
      "loss": 0.9695,
      "step": 1540
    },
    {
      "epoch": 1.2836864842624975,
      "grad_norm": 1.609375,
      "learning_rate": 0.00011763046544428774,
      "loss": 0.9584,
      "step": 1560
    },
    {
      "epoch": 1.300144003291504,
      "grad_norm": 1.546875,
      "learning_rate": 0.00011650211565585332,
      "loss": 0.975,
      "step": 1580
    },
    {
      "epoch": 1.3166015223205103,
      "grad_norm": 1.5234375,
      "learning_rate": 0.0001153737658674189,
      "loss": 0.9561,
      "step": 1600
    },
    {
      "epoch": 1.3330590413495167,
      "grad_norm": 1.609375,
      "learning_rate": 0.00011424541607898449,
      "loss": 0.9068,
      "step": 1620
    },
    {
      "epoch": 1.3495165603785229,
      "grad_norm": 1.375,
      "learning_rate": 0.00011311706629055008,
      "loss": 0.9088,
      "step": 1640
    },
    {
      "epoch": 1.3659740794075292,
      "grad_norm": 1.7734375,
      "learning_rate": 0.00011198871650211567,
      "loss": 0.8766,
      "step": 1660
    },
    {
      "epoch": 1.3824315984365356,
      "grad_norm": 1.5234375,
      "learning_rate": 0.00011086036671368125,
      "loss": 0.9034,
      "step": 1680
    },
    {
      "epoch": 1.398889117465542,
      "grad_norm": 1.921875,
      "learning_rate": 0.00010973201692524683,
      "loss": 0.9532,
      "step": 1700
    },
    {
      "epoch": 1.4153466364945484,
      "grad_norm": 1.765625,
      "learning_rate": 0.00010860366713681243,
      "loss": 0.8913,
      "step": 1720
    },
    {
      "epoch": 1.4318041555235548,
      "grad_norm": 1.578125,
      "learning_rate": 0.00010747531734837801,
      "loss": 0.886,
      "step": 1740
    },
    {
      "epoch": 1.4482616745525612,
      "grad_norm": 2.015625,
      "learning_rate": 0.00010634696755994358,
      "loss": 0.9405,
      "step": 1760
    },
    {
      "epoch": 1.4647191935815675,
      "grad_norm": 1.5859375,
      "learning_rate": 0.00010521861777150917,
      "loss": 0.9094,
      "step": 1780
    },
    {
      "epoch": 1.481176712610574,
      "grad_norm": 1.8984375,
      "learning_rate": 0.00010409026798307475,
      "loss": 0.9985,
      "step": 1800
    },
    {
      "epoch": 1.4976342316395803,
      "grad_norm": 1.5546875,
      "learning_rate": 0.00010296191819464033,
      "loss": 0.9577,
      "step": 1820
    },
    {
      "epoch": 1.5140917506685867,
      "grad_norm": 1.671875,
      "learning_rate": 0.00010183356840620593,
      "loss": 0.9125,
      "step": 1840
    },
    {
      "epoch": 1.530549269697593,
      "grad_norm": 1.390625,
      "learning_rate": 0.00010070521861777152,
      "loss": 0.9305,
      "step": 1860
    },
    {
      "epoch": 1.5470067887265995,
      "grad_norm": 1.1953125,
      "learning_rate": 9.95768688293371e-05,
      "loss": 0.9372,
      "step": 1880
    },
    {
      "epoch": 1.5634643077556059,
      "grad_norm": 1.15625,
      "learning_rate": 9.844851904090268e-05,
      "loss": 0.9658,
      "step": 1900
    },
    {
      "epoch": 1.5799218267846122,
      "grad_norm": 1.78125,
      "learning_rate": 9.732016925246828e-05,
      "loss": 0.8637,
      "step": 1920
    },
    {
      "epoch": 1.5963793458136186,
      "grad_norm": 1.515625,
      "learning_rate": 9.619181946403385e-05,
      "loss": 0.8523,
      "step": 1940
    },
    {
      "epoch": 1.612836864842625,
      "grad_norm": 1.28125,
      "learning_rate": 9.506346967559943e-05,
      "loss": 0.8689,
      "step": 1960
    },
    {
      "epoch": 1.6292943838716314,
      "grad_norm": 1.09375,
      "learning_rate": 9.393511988716503e-05,
      "loss": 0.8898,
      "step": 1980
    },
    {
      "epoch": 1.6457519029006378,
      "grad_norm": 1.7421875,
      "learning_rate": 9.280677009873061e-05,
      "loss": 0.9299,
      "step": 2000
    },
    {
      "epoch": 1.6622094219296442,
      "grad_norm": 1.84375,
      "learning_rate": 9.16784203102962e-05,
      "loss": 0.9165,
      "step": 2020
    },
    {
      "epoch": 1.6786669409586503,
      "grad_norm": 1.6875,
      "learning_rate": 9.055007052186178e-05,
      "loss": 0.897,
      "step": 2040
    },
    {
      "epoch": 1.6951244599876567,
      "grad_norm": 1.734375,
      "learning_rate": 8.942172073342738e-05,
      "loss": 0.9132,
      "step": 2060
    },
    {
      "epoch": 1.711581979016663,
      "grad_norm": 1.6875,
      "learning_rate": 8.829337094499295e-05,
      "loss": 0.8897,
      "step": 2080
    },
    {
      "epoch": 1.7280394980456695,
      "grad_norm": 1.6640625,
      "learning_rate": 8.716502115655853e-05,
      "loss": 0.9079,
      "step": 2100
    },
    {
      "epoch": 1.7444970170746759,
      "grad_norm": 1.234375,
      "learning_rate": 8.603667136812413e-05,
      "loss": 0.8468,
      "step": 2120
    },
    {
      "epoch": 1.7609545361036822,
      "grad_norm": 1.46875,
      "learning_rate": 8.490832157968971e-05,
      "loss": 0.862,
      "step": 2140
    },
    {
      "epoch": 1.7774120551326886,
      "grad_norm": 1.671875,
      "learning_rate": 8.37799717912553e-05,
      "loss": 0.901,
      "step": 2160
    },
    {
      "epoch": 1.793869574161695,
      "grad_norm": 1.5546875,
      "learning_rate": 8.265162200282088e-05,
      "loss": 0.864,
      "step": 2180
    },
    {
      "epoch": 1.8103270931907014,
      "grad_norm": 1.953125,
      "learning_rate": 8.152327221438646e-05,
      "loss": 0.8773,
      "step": 2200
    },
    {
      "epoch": 1.8267846122197078,
      "grad_norm": 1.421875,
      "learning_rate": 8.039492242595204e-05,
      "loss": 0.8714,
      "step": 2220
    },
    {
      "epoch": 1.8432421312487142,
      "grad_norm": 1.9375,
      "learning_rate": 7.926657263751763e-05,
      "loss": 0.9346,
      "step": 2240
    },
    {
      "epoch": 1.8596996502777206,
      "grad_norm": 1.5546875,
      "learning_rate": 7.813822284908322e-05,
      "loss": 0.877,
      "step": 2260
    },
    {
      "epoch": 1.876157169306727,
      "grad_norm": 1.4140625,
      "learning_rate": 7.700987306064881e-05,
      "loss": 0.9007,
      "step": 2280
    },
    {
      "epoch": 1.8926146883357333,
      "grad_norm": 1.734375,
      "learning_rate": 7.588152327221439e-05,
      "loss": 0.9481,
      "step": 2300
    },
    {
      "epoch": 1.9090722073647397,
      "grad_norm": 1.7109375,
      "learning_rate": 7.475317348377997e-05,
      "loss": 0.8854,
      "step": 2320
    },
    {
      "epoch": 1.925529726393746,
      "grad_norm": 1.6484375,
      "learning_rate": 7.362482369534556e-05,
      "loss": 0.9206,
      "step": 2340
    },
    {
      "epoch": 1.9419872454227525,
      "grad_norm": 1.8046875,
      "learning_rate": 7.249647390691114e-05,
      "loss": 0.8936,
      "step": 2360
    },
    {
      "epoch": 1.9584447644517589,
      "grad_norm": 1.6484375,
      "learning_rate": 7.136812411847673e-05,
      "loss": 0.8942,
      "step": 2380
    },
    {
      "epoch": 1.9749022834807652,
      "grad_norm": 1.390625,
      "learning_rate": 7.023977433004232e-05,
      "loss": 0.881,
      "step": 2400
    },
    {
      "epoch": 1.9913598025097716,
      "grad_norm": 1.5625,
      "learning_rate": 6.91114245416079e-05,
      "loss": 0.9034,
      "step": 2420
    },
    {
      "epoch": 2.007817321538778,
      "grad_norm": 1.515625,
      "learning_rate": 6.798307475317349e-05,
      "loss": 0.8102,
      "step": 2440
    },
    {
      "epoch": 2.0242748405677844,
      "grad_norm": 1.5078125,
      "learning_rate": 6.685472496473907e-05,
      "loss": 0.7575,
      "step": 2460
    },
    {
      "epoch": 2.040732359596791,
      "grad_norm": 1.671875,
      "learning_rate": 6.572637517630466e-05,
      "loss": 0.7636,
      "step": 2480
    },
    {
      "epoch": 2.057189878625797,
      "grad_norm": 1.5859375,
      "learning_rate": 6.459802538787024e-05,
      "loss": 0.8552,
      "step": 2500
    }
  ],
  "logging_steps": 20,
  "max_steps": 3645,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 3.33909657102336e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}