{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.974910394265233,
  "eval_steps": 500,
  "global_step": 312,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009557945041816009,
      "grad_norm": 4.787891864776611,
      "learning_rate": 0.0,
      "loss": 1.2182,
      "num_tokens": 3087662.0,
      "step": 1
    },
    {
      "epoch": 0.019115890083632018,
      "grad_norm": 4.7660908699035645,
      "learning_rate": 1.5625e-06,
      "loss": 1.2133,
      "num_tokens": 6211852.0,
      "step": 2
    },
    {
      "epoch": 0.02867383512544803,
      "grad_norm": 4.726694107055664,
      "learning_rate": 3.125e-06,
      "loss": 1.2106,
      "num_tokens": 9308149.0,
      "step": 3
    },
    {
      "epoch": 0.038231780167264036,
      "grad_norm": 4.008660793304443,
      "learning_rate": 4.6875000000000004e-06,
      "loss": 1.1473,
      "num_tokens": 12406212.0,
      "step": 4
    },
    {
      "epoch": 0.04778972520908005,
      "grad_norm": 2.9268953800201416,
      "learning_rate": 6.25e-06,
      "loss": 1.0694,
      "num_tokens": 15498886.0,
      "step": 5
    },
    {
      "epoch": 0.05734767025089606,
      "grad_norm": 1.6218466758728027,
      "learning_rate": 7.8125e-06,
      "loss": 0.9229,
      "num_tokens": 18594568.0,
      "step": 6
    },
    {
      "epoch": 0.06690561529271206,
      "grad_norm": 1.232273817062378,
      "learning_rate": 9.375000000000001e-06,
      "loss": 0.8977,
      "num_tokens": 21685747.0,
      "step": 7
    },
    {
      "epoch": 0.07646356033452807,
      "grad_norm": 1.352134346961975,
      "learning_rate": 1.09375e-05,
      "loss": 0.8468,
      "num_tokens": 24802133.0,
      "step": 8
    },
    {
      "epoch": 0.08602150537634409,
      "grad_norm": 1.1753616333007812,
      "learning_rate": 1.25e-05,
      "loss": 0.8356,
      "num_tokens": 27921758.0,
      "step": 9
    },
    {
      "epoch": 0.0955794504181601,
      "grad_norm": 0.841299831867218,
      "learning_rate": 1.4062500000000001e-05,
      "loss": 0.8045,
      "num_tokens": 30982499.0,
      "step": 10
    },
    {
      "epoch": 0.10513739545997611,
      "grad_norm": 0.7823367118835449,
      "learning_rate": 1.5625e-05,
      "loss": 0.7772,
      "num_tokens": 34120523.0,
      "step": 11
    },
    {
      "epoch": 0.11469534050179211,
      "grad_norm": 0.6168179512023926,
      "learning_rate": 1.71875e-05,
      "loss": 0.7493,
      "num_tokens": 37263940.0,
      "step": 12
    },
    {
      "epoch": 0.12425328554360812,
      "grad_norm": 0.4352397918701172,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 0.7391,
      "num_tokens": 40419105.0,
      "step": 13
    },
    {
      "epoch": 0.13381123058542413,
      "grad_norm": 0.4141225516796112,
      "learning_rate": 2.0312500000000002e-05,
      "loss": 0.7168,
      "num_tokens": 43544209.0,
      "step": 14
    },
    {
      "epoch": 0.14336917562724014,
      "grad_norm": 0.3596664071083069,
      "learning_rate": 2.1875e-05,
      "loss": 0.7096,
      "num_tokens": 46640184.0,
      "step": 15
    },
    {
      "epoch": 0.15292712066905614,
      "grad_norm": 0.32062292098999023,
      "learning_rate": 2.34375e-05,
      "loss": 0.6878,
      "num_tokens": 49723879.0,
      "step": 16
    },
    {
      "epoch": 0.16248506571087215,
      "grad_norm": 0.2776451110839844,
      "learning_rate": 2.5e-05,
      "loss": 0.685,
      "num_tokens": 52840221.0,
      "step": 17
    },
    {
      "epoch": 0.17204301075268819,
      "grad_norm": 0.2792057693004608,
      "learning_rate": 2.6562500000000002e-05,
      "loss": 0.6683,
      "num_tokens": 55938115.0,
      "step": 18
    },
    {
      "epoch": 0.1816009557945042,
      "grad_norm": 0.24952948093414307,
      "learning_rate": 2.8125000000000003e-05,
      "loss": 0.6643,
      "num_tokens": 59088421.0,
      "step": 19
    },
    {
      "epoch": 0.1911589008363202,
      "grad_norm": 0.23966556787490845,
      "learning_rate": 2.96875e-05,
      "loss": 0.6568,
      "num_tokens": 62120009.0,
      "step": 20
    },
    {
      "epoch": 0.2007168458781362,
      "grad_norm": 0.29473549127578735,
      "learning_rate": 3.125e-05,
      "loss": 0.6443,
      "num_tokens": 65202270.0,
      "step": 21
    },
    {
      "epoch": 0.21027479091995221,
      "grad_norm": 0.25088849663734436,
      "learning_rate": 3.2812500000000005e-05,
      "loss": 0.64,
      "num_tokens": 68278086.0,
      "step": 22
    },
    {
      "epoch": 0.21983273596176822,
      "grad_norm": 0.26761022210121155,
      "learning_rate": 3.4375e-05,
      "loss": 0.6406,
      "num_tokens": 71423006.0,
      "step": 23
    },
    {
      "epoch": 0.22939068100358423,
      "grad_norm": 0.2646687626838684,
      "learning_rate": 3.59375e-05,
      "loss": 0.6287,
      "num_tokens": 74542778.0,
      "step": 24
    },
    {
      "epoch": 0.23894862604540024,
      "grad_norm": 0.28765901923179626,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.6316,
      "num_tokens": 77676355.0,
      "step": 25
    },
    {
      "epoch": 0.24850657108721624,
      "grad_norm": 0.28572410345077515,
      "learning_rate": 3.90625e-05,
      "loss": 0.6208,
      "num_tokens": 80757397.0,
      "step": 26
    },
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 0.3025137782096863,
      "learning_rate": 4.0625000000000005e-05,
      "loss": 0.6206,
      "num_tokens": 83848581.0,
      "step": 27
    },
    {
      "epoch": 0.26762246117084826,
      "grad_norm": 0.30501461029052734,
      "learning_rate": 4.21875e-05,
      "loss": 0.61,
      "num_tokens": 86949103.0,
      "step": 28
    },
    {
      "epoch": 0.27718040621266427,
      "grad_norm": 0.24303048849105835,
      "learning_rate": 4.375e-05,
      "loss": 0.6062,
      "num_tokens": 90043461.0,
      "step": 29
    },
    {
      "epoch": 0.2867383512544803,
      "grad_norm": 0.4097803235054016,
      "learning_rate": 4.5312500000000004e-05,
      "loss": 0.608,
      "num_tokens": 93175833.0,
      "step": 30
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.22506467998027802,
      "learning_rate": 4.6875e-05,
      "loss": 0.6043,
      "num_tokens": 96298838.0,
      "step": 31
    },
    {
      "epoch": 0.3058542413381123,
      "grad_norm": 0.4554276168346405,
      "learning_rate": 4.8437500000000005e-05,
      "loss": 0.6039,
      "num_tokens": 99387594.0,
      "step": 32
    },
    {
      "epoch": 0.3154121863799283,
      "grad_norm": 0.24191643297672272,
      "learning_rate": 5e-05,
      "loss": 0.5919,
      "num_tokens": 102495943.0,
      "step": 33
    },
    {
      "epoch": 0.3249701314217443,
      "grad_norm": 0.497525155544281,
      "learning_rate": 5e-05,
      "loss": 0.5919,
      "num_tokens": 105605746.0,
      "step": 34
    },
    {
      "epoch": 0.3345280764635603,
      "grad_norm": 0.39946335554122925,
      "learning_rate": 5e-05,
      "loss": 0.5966,
      "num_tokens": 108704371.0,
      "step": 35
    },
    {
      "epoch": 0.34408602150537637,
      "grad_norm": 0.3315200209617615,
      "learning_rate": 5e-05,
      "loss": 0.58,
      "num_tokens": 111803239.0,
      "step": 36
    },
    {
      "epoch": 0.3536439665471924,
      "grad_norm": 0.38535887002944946,
      "learning_rate": 5e-05,
      "loss": 0.5836,
      "num_tokens": 114901473.0,
      "step": 37
    },
    {
      "epoch": 0.3632019115890084,
      "grad_norm": 0.30798089504241943,
      "learning_rate": 5e-05,
      "loss": 0.5821,
      "num_tokens": 117998143.0,
      "step": 38
    },
    {
      "epoch": 0.3727598566308244,
      "grad_norm": 0.3112103343009949,
      "learning_rate": 5e-05,
      "loss": 0.5789,
      "num_tokens": 121151007.0,
      "step": 39
    },
    {
      "epoch": 0.3823178016726404,
      "grad_norm": 0.28211474418640137,
      "learning_rate": 5e-05,
      "loss": 0.576,
      "num_tokens": 124244420.0,
      "step": 40
    },
    {
      "epoch": 0.3918757467144564,
      "grad_norm": 0.29719066619873047,
      "learning_rate": 5e-05,
      "loss": 0.5776,
      "num_tokens": 127347282.0,
      "step": 41
    },
    {
      "epoch": 0.4014336917562724,
      "grad_norm": 0.28514203429222107,
      "learning_rate": 5e-05,
      "loss": 0.5739,
      "num_tokens": 130425105.0,
      "step": 42
    },
    {
      "epoch": 0.4109916367980884,
      "grad_norm": 0.24759361147880554,
      "learning_rate": 5e-05,
      "loss": 0.5614,
      "num_tokens": 133566882.0,
      "step": 43
    },
    {
      "epoch": 0.42054958183990443,
      "grad_norm": 0.3673174977302551,
      "learning_rate": 5e-05,
      "loss": 0.5755,
      "num_tokens": 136693576.0,
      "step": 44
    },
    {
      "epoch": 0.43010752688172044,
      "grad_norm": 0.2918493151664734,
      "learning_rate": 5e-05,
      "loss": 0.5741,
      "num_tokens": 139836069.0,
      "step": 45
    },
    {
      "epoch": 0.43966547192353644,
      "grad_norm": 0.20241530239582062,
      "learning_rate": 5e-05,
      "loss": 0.5659,
      "num_tokens": 142903826.0,
      "step": 46
    },
    {
      "epoch": 0.44922341696535245,
      "grad_norm": 0.36211881041526794,
      "learning_rate": 5e-05,
      "loss": 0.5652,
      "num_tokens": 146013234.0,
      "step": 47
    },
    {
      "epoch": 0.45878136200716846,
      "grad_norm": 0.27178287506103516,
      "learning_rate": 5e-05,
      "loss": 0.5639,
      "num_tokens": 149106780.0,
      "step": 48
    },
    {
      "epoch": 0.46833930704898447,
      "grad_norm": 0.22404040396213531,
      "learning_rate": 5e-05,
      "loss": 0.5588,
      "num_tokens": 152240290.0,
      "step": 49
    },
    {
      "epoch": 0.4778972520908005,
      "grad_norm": 0.267503023147583,
      "learning_rate": 5e-05,
      "loss": 0.5634,
      "num_tokens": 155343192.0,
      "step": 50
    },
    {
      "epoch": 0.4874551971326165,
      "grad_norm": 0.22685855627059937,
      "learning_rate": 5e-05,
      "loss": 0.5624,
      "num_tokens": 158483136.0,
      "step": 51
    },
    {
      "epoch": 0.4970131421744325,
      "grad_norm": 0.3110021948814392,
      "learning_rate": 5e-05,
      "loss": 0.5543,
      "num_tokens": 161533766.0,
      "step": 52
    },
    {
      "epoch": 0.5065710872162486,
      "grad_norm": 0.23207558691501617,
      "learning_rate": 5e-05,
      "loss": 0.546,
      "num_tokens": 164664119.0,
      "step": 53
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 0.33425262570381165,
      "learning_rate": 5e-05,
      "loss": 0.5544,
      "num_tokens": 167808973.0,
      "step": 54
    },
    {
      "epoch": 0.5256869772998806,
      "grad_norm": 0.2662634253501892,
      "learning_rate": 5e-05,
      "loss": 0.5526,
      "num_tokens": 170887441.0,
      "step": 55
    },
    {
      "epoch": 0.5352449223416965,
      "grad_norm": 0.28920575976371765,
      "learning_rate": 5e-05,
      "loss": 0.5536,
      "num_tokens": 174005920.0,
      "step": 56
    },
    {
      "epoch": 0.5448028673835126,
      "grad_norm": 0.26591673493385315,
      "learning_rate": 5e-05,
      "loss": 0.5481,
      "num_tokens": 177097398.0,
      "step": 57
    },
    {
      "epoch": 0.5543608124253285,
      "grad_norm": 0.2847670614719391,
      "learning_rate": 5e-05,
      "loss": 0.5536,
      "num_tokens": 180221288.0,
      "step": 58
    },
    {
      "epoch": 0.5639187574671446,
      "grad_norm": 0.2541261613368988,
      "learning_rate": 5e-05,
      "loss": 0.542,
      "num_tokens": 183289863.0,
      "step": 59
    },
    {
      "epoch": 0.5734767025089605,
      "grad_norm": 0.275193989276886,
      "learning_rate": 5e-05,
      "loss": 0.5456,
      "num_tokens": 186406120.0,
      "step": 60
    },
    {
      "epoch": 0.5830346475507766,
      "grad_norm": 0.26497912406921387,
      "learning_rate": 5e-05,
      "loss": 0.5425,
      "num_tokens": 189471040.0,
      "step": 61
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.27101513743400574,
      "learning_rate": 5e-05,
      "loss": 0.5386,
      "num_tokens": 192575364.0,
      "step": 62
    },
    {
      "epoch": 0.6021505376344086,
      "grad_norm": 0.26009494066238403,
      "learning_rate": 5e-05,
      "loss": 0.5318,
      "num_tokens": 195684975.0,
      "step": 63
    },
    {
      "epoch": 0.6117084826762246,
      "grad_norm": 0.22097371518611908,
      "learning_rate": 5e-05,
      "loss": 0.5411,
      "num_tokens": 198779716.0,
      "step": 64
    },
    {
      "epoch": 0.6212664277180406,
      "grad_norm": 0.3351891040802002,
      "learning_rate": 5e-05,
      "loss": 0.5458,
      "num_tokens": 201906900.0,
      "step": 65
    },
    {
      "epoch": 0.6308243727598566,
      "grad_norm": 0.23704691231250763,
      "learning_rate": 5e-05,
      "loss": 0.5397,
      "num_tokens": 205031188.0,
      "step": 66
    },
    {
      "epoch": 0.6403823178016727,
      "grad_norm": 0.32154443860054016,
      "learning_rate": 5e-05,
      "loss": 0.5445,
      "num_tokens": 208116939.0,
      "step": 67
    },
    {
      "epoch": 0.6499402628434886,
      "grad_norm": 0.2630949020385742,
      "learning_rate": 5e-05,
      "loss": 0.5322,
      "num_tokens": 211211227.0,
      "step": 68
    },
    {
      "epoch": 0.6594982078853047,
      "grad_norm": 0.31168922781944275,
      "learning_rate": 5e-05,
      "loss": 0.5324,
      "num_tokens": 214301570.0,
      "step": 69
    },
    {
      "epoch": 0.6690561529271206,
      "grad_norm": 0.2585446834564209,
      "learning_rate": 5e-05,
      "loss": 0.5386,
      "num_tokens": 217393704.0,
      "step": 70
    },
    {
      "epoch": 0.6786140979689367,
      "grad_norm": 0.25293031334877014,
      "learning_rate": 5e-05,
      "loss": 0.5223,
      "num_tokens": 220482293.0,
      "step": 71
    },
    {
      "epoch": 0.6881720430107527,
      "grad_norm": 0.3039219379425049,
      "learning_rate": 5e-05,
      "loss": 0.5337,
      "num_tokens": 223590652.0,
      "step": 72
    },
    {
      "epoch": 0.6977299880525687,
      "grad_norm": 0.2043919861316681,
      "learning_rate": 5e-05,
      "loss": 0.5251,
      "num_tokens": 226675856.0,
      "step": 73
    },
    {
      "epoch": 0.7072879330943848,
      "grad_norm": 0.290919691324234,
      "learning_rate": 5e-05,
      "loss": 0.5343,
      "num_tokens": 229778501.0,
      "step": 74
    },
    {
      "epoch": 0.7168458781362007,
      "grad_norm": 0.24795055389404297,
      "learning_rate": 5e-05,
      "loss": 0.5356,
      "num_tokens": 232829595.0,
      "step": 75
    },
    {
      "epoch": 0.7264038231780168,
      "grad_norm": 0.25901439785957336,
      "learning_rate": 5e-05,
      "loss": 0.5258,
      "num_tokens": 235940446.0,
      "step": 76
    },
    {
      "epoch": 0.7359617682198327,
      "grad_norm": 0.30405953526496887,
      "learning_rate": 5e-05,
      "loss": 0.5361,
      "num_tokens": 239028046.0,
      "step": 77
    },
    {
      "epoch": 0.7455197132616488,
      "grad_norm": 0.23060917854309082,
      "learning_rate": 5e-05,
      "loss": 0.5361,
      "num_tokens": 242205870.0,
      "step": 78
    },
    {
      "epoch": 0.7550776583034647,
      "grad_norm": 0.24737045168876648,
      "learning_rate": 5e-05,
      "loss": 0.5204,
      "num_tokens": 245233676.0,
      "step": 79
    },
    {
      "epoch": 0.7646356033452808,
      "grad_norm": 0.22408932447433472,
      "learning_rate": 5e-05,
      "loss": 0.5202,
      "num_tokens": 248356444.0,
      "step": 80
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": 0.328327476978302,
      "learning_rate": 5e-05,
      "loss": 0.5311,
      "num_tokens": 251468079.0,
      "step": 81
    },
    {
      "epoch": 0.7837514934289128,
      "grad_norm": 0.20574553310871124,
      "learning_rate": 5e-05,
      "loss": 0.5231,
      "num_tokens": 254594703.0,
      "step": 82
    },
    {
      "epoch": 0.7933094384707288,
      "grad_norm": 0.305171936750412,
      "learning_rate": 5e-05,
      "loss": 0.5264,
      "num_tokens": 257723496.0,
      "step": 83
    },
    {
      "epoch": 0.8028673835125448,
      "grad_norm": 0.20093268156051636,
      "learning_rate": 5e-05,
      "loss": 0.5274,
      "num_tokens": 260768286.0,
      "step": 84
    },
    {
      "epoch": 0.8124253285543608,
      "grad_norm": 0.3125307559967041,
      "learning_rate": 5e-05,
      "loss": 0.5313,
      "num_tokens": 263875942.0,
      "step": 85
    },
    {
      "epoch": 0.8219832735961768,
      "grad_norm": 0.20460698008537292,
      "learning_rate": 5e-05,
      "loss": 0.5217,
      "num_tokens": 266985727.0,
      "step": 86
    },
    {
      "epoch": 0.8315412186379928,
      "grad_norm": 0.2367510348558426,
      "learning_rate": 5e-05,
      "loss": 0.5163,
      "num_tokens": 270075318.0,
      "step": 87
    },
    {
      "epoch": 0.8410991636798089,
      "grad_norm": 0.2568177580833435,
      "learning_rate": 5e-05,
      "loss": 0.5241,
      "num_tokens": 273156355.0,
      "step": 88
    },
    {
      "epoch": 0.8506571087216248,
      "grad_norm": 0.2784541845321655,
      "learning_rate": 5e-05,
      "loss": 0.5223,
      "num_tokens": 276259662.0,
      "step": 89
    },
    {
      "epoch": 0.8602150537634409,
      "grad_norm": 0.25873690843582153,
      "learning_rate": 5e-05,
      "loss": 0.5256,
      "num_tokens": 279394317.0,
      "step": 90
    },
    {
      "epoch": 0.8697729988052568,
      "grad_norm": 0.2528490126132965,
      "learning_rate": 5e-05,
      "loss": 0.5199,
      "num_tokens": 282498565.0,
      "step": 91
    },
    {
      "epoch": 0.8793309438470729,
      "grad_norm": 0.24740688502788544,
      "learning_rate": 5e-05,
      "loss": 0.5141,
      "num_tokens": 285610462.0,
      "step": 92
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.24610859155654907,
      "learning_rate": 5e-05,
      "loss": 0.5197,
      "num_tokens": 288771247.0,
      "step": 93
    },
    {
      "epoch": 0.8984468339307049,
      "grad_norm": 0.24038155376911163,
      "learning_rate": 5e-05,
      "loss": 0.5191,
      "num_tokens": 291911091.0,
      "step": 94
    },
    {
      "epoch": 0.9080047789725209,
      "grad_norm": 0.2939693033695221,
      "learning_rate": 5e-05,
      "loss": 0.5147,
      "num_tokens": 294998183.0,
      "step": 95
    },
    {
      "epoch": 0.9175627240143369,
      "grad_norm": 0.19252680242061615,
      "learning_rate": 5e-05,
      "loss": 0.5138,
      "num_tokens": 298050683.0,
      "step": 96
    },
    {
      "epoch": 0.927120669056153,
      "grad_norm": 0.23349586129188538,
      "learning_rate": 5e-05,
      "loss": 0.5172,
      "num_tokens": 301164218.0,
      "step": 97
    },
    {
      "epoch": 0.9366786140979689,
      "grad_norm": 0.20470231771469116,
      "learning_rate": 5e-05,
      "loss": 0.5132,
      "num_tokens": 304261920.0,
      "step": 98
    },
    {
      "epoch": 0.946236559139785,
      "grad_norm": 0.27620136737823486,
      "learning_rate": 5e-05,
      "loss": 0.5195,
      "num_tokens": 307412237.0,
      "step": 99
    },
    {
      "epoch": 0.955794504181601,
      "grad_norm": 0.21717092394828796,
      "learning_rate": 5e-05,
      "loss": 0.5172,
      "num_tokens": 310507993.0,
      "step": 100
    },
    {
      "epoch": 0.965352449223417,
      "grad_norm": 0.29017373919487,
      "learning_rate": 5e-05,
      "loss": 0.5107,
      "num_tokens": 313624257.0,
      "step": 101
    },
    {
      "epoch": 0.974910394265233,
      "grad_norm": 0.28068530559539795,
      "learning_rate": 5e-05,
      "loss": 0.5176,
      "num_tokens": 316722666.0,
      "step": 102
    },
    {
      "epoch": 0.984468339307049,
      "grad_norm": 0.2316262573003769,
      "learning_rate": 5e-05,
      "loss": 0.5162,
      "num_tokens": 319820496.0,
      "step": 103
    },
    {
      "epoch": 0.994026284348865,
      "grad_norm": 0.30137985944747925,
      "learning_rate": 5e-05,
      "loss": 0.5102,
      "num_tokens": 322901137.0,
      "step": 104
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.30137985944747925,
      "learning_rate": 5e-05,
      "loss": 0.5069,
      "num_tokens": 324860579.0,
      "step": 105
    },
    {
      "epoch": 1.009557945041816,
      "grad_norm": 0.32997432351112366,
      "learning_rate": 5e-05,
      "loss": 0.4761,
      "num_tokens": 327927654.0,
      "step": 106
    },
    {
      "epoch": 1.0191158900836321,
      "grad_norm": 0.32110321521759033,
      "learning_rate": 5e-05,
      "loss": 0.4785,
      "num_tokens": 331066424.0,
      "step": 107
    },
    {
      "epoch": 1.028673835125448,
      "grad_norm": 0.20342878997325897,
      "learning_rate": 5e-05,
      "loss": 0.4845,
      "num_tokens": 334162426.0,
      "step": 108
    },
    {
      "epoch": 1.038231780167264,
      "grad_norm": 0.3325869143009186,
      "learning_rate": 5e-05,
      "loss": 0.4822,
      "num_tokens": 337302238.0,
      "step": 109
    },
    {
      "epoch": 1.04778972520908,
      "grad_norm": 0.22826018929481506,
      "learning_rate": 5e-05,
      "loss": 0.4824,
      "num_tokens": 340447280.0,
      "step": 110
    },
    {
      "epoch": 1.0573476702508962,
      "grad_norm": 0.3223550021648407,
      "learning_rate": 5e-05,
      "loss": 0.4696,
      "num_tokens": 343568761.0,
      "step": 111
    },
    {
      "epoch": 1.066905615292712,
      "grad_norm": 0.21368011832237244,
      "learning_rate": 5e-05,
      "loss": 0.4756,
      "num_tokens": 346718666.0,
      "step": 112
    },
    {
      "epoch": 1.076463560334528,
      "grad_norm": 0.24224598705768585,
      "learning_rate": 5e-05,
      "loss": 0.4765,
      "num_tokens": 349842177.0,
      "step": 113
    },
    {
      "epoch": 1.086021505376344,
      "grad_norm": 0.2377299815416336,
      "learning_rate": 5e-05,
      "loss": 0.4728,
      "num_tokens": 352932093.0,
      "step": 114
    },
    {
      "epoch": 1.0955794504181602,
      "grad_norm": 0.23792093992233276,
      "learning_rate": 5e-05,
      "loss": 0.4777,
      "num_tokens": 356033224.0,
      "step": 115
    },
    {
      "epoch": 1.1051373954599761,
      "grad_norm": 0.26680827140808105,
      "learning_rate": 5e-05,
      "loss": 0.4778,
      "num_tokens": 359191089.0,
      "step": 116
    },
    {
      "epoch": 1.114695340501792,
      "grad_norm": 0.26498955488204956,
      "learning_rate": 5e-05,
      "loss": 0.4739,
      "num_tokens": 362282504.0,
      "step": 117
    },
    {
      "epoch": 1.124253285543608,
      "grad_norm": 0.2889910936355591,
      "learning_rate": 5e-05,
      "loss": 0.4751,
      "num_tokens": 365375038.0,
      "step": 118
    },
    {
      "epoch": 1.1338112305854242,
      "grad_norm": 0.2168579399585724,
      "learning_rate": 5e-05,
      "loss": 0.4615,
      "num_tokens": 368405060.0,
      "step": 119
    },
    {
      "epoch": 1.1433691756272402,
      "grad_norm": 0.2727675437927246,
      "learning_rate": 5e-05,
      "loss": 0.4738,
      "num_tokens": 371483975.0,
      "step": 120
    },
    {
      "epoch": 1.1529271206690561,
      "grad_norm": 0.36416906118392944,
      "learning_rate": 5e-05,
      "loss": 0.4791,
      "num_tokens": 374634435.0,
      "step": 121
    },
    {
      "epoch": 1.162485065710872,
      "grad_norm": 0.18200910091400146,
      "learning_rate": 5e-05,
      "loss": 0.4731,
      "num_tokens": 377757663.0,
      "step": 122
    },
    {
      "epoch": 1.1720430107526882,
      "grad_norm": 0.386223167181015,
      "learning_rate": 5e-05,
      "loss": 0.4777,
      "num_tokens": 380874183.0,
      "step": 123
    },
    {
      "epoch": 1.1816009557945042,
      "grad_norm": 0.25184914469718933,
      "learning_rate": 5e-05,
      "loss": 0.4793,
      "num_tokens": 383990561.0,
      "step": 124
    },
    {
      "epoch": 1.1911589008363201,
      "grad_norm": 0.37080973386764526,
      "learning_rate": 5e-05,
      "loss": 0.4764,
      "num_tokens": 387086225.0,
      "step": 125
    },
    {
      "epoch": 1.2007168458781363,
      "grad_norm": 0.27940818667411804,
      "learning_rate": 5e-05,
      "loss": 0.4718,
      "num_tokens": 390204819.0,
      "step": 126
    },
    {
      "epoch": 1.2102747909199523,
      "grad_norm": 0.28235924243927,
      "learning_rate": 5e-05,
      "loss": 0.4713,
      "num_tokens": 393287937.0,
      "step": 127
    },
    {
      "epoch": 1.2198327359617682,
      "grad_norm": 0.28537049889564514,
      "learning_rate": 5e-05,
      "loss": 0.4746,
      "num_tokens": 396363663.0,
      "step": 128
    },
    {
      "epoch": 1.2293906810035842,
      "grad_norm": 0.3287442922592163,
      "learning_rate": 5e-05,
      "loss": 0.4796,
      "num_tokens": 399462801.0,
      "step": 129
    },
    {
      "epoch": 1.2389486260454001,
      "grad_norm": 0.23722870647907257,
      "learning_rate": 5e-05,
      "loss": 0.4674,
      "num_tokens": 402561690.0,
      "step": 130
    },
    {
      "epoch": 1.2485065710872163,
      "grad_norm": 0.26579034328460693,
      "learning_rate": 5e-05,
      "loss": 0.46,
      "num_tokens": 405671986.0,
      "step": 131
    },
    {
      "epoch": 1.2580645161290323,
      "grad_norm": 0.21499669551849365,
      "learning_rate": 5e-05,
      "loss": 0.4633,
      "num_tokens": 408745166.0,
      "step": 132
    },
    {
      "epoch": 1.2676224611708482,
      "grad_norm": 0.26388466358184814,
      "learning_rate": 5e-05,
      "loss": 0.4736,
      "num_tokens": 411848560.0,
      "step": 133
    },
    {
      "epoch": 1.2771804062126644,
      "grad_norm": 0.22143350541591644,
      "learning_rate": 5e-05,
      "loss": 0.4624,
      "num_tokens": 414961042.0,
      "step": 134
    },
    {
      "epoch": 1.2867383512544803,
      "grad_norm": 0.27563315629959106,
      "learning_rate": 5e-05,
      "loss": 0.4645,
      "num_tokens": 418038833.0,
      "step": 135
    },
    {
      "epoch": 1.2962962962962963,
      "grad_norm": 0.2135905772447586,
      "learning_rate": 5e-05,
      "loss": 0.4732,
      "num_tokens": 421176052.0,
      "step": 136
    },
    {
      "epoch": 1.3058542413381122,
      "grad_norm": 0.24489735066890717,
      "learning_rate": 5e-05,
      "loss": 0.472,
      "num_tokens": 424278020.0,
      "step": 137
    },
    {
      "epoch": 1.3154121863799282,
      "grad_norm": 0.22754637897014618,
      "learning_rate": 5e-05,
      "loss": 0.4691,
      "num_tokens": 427397110.0,
      "step": 138
    },
    {
      "epoch": 1.3249701314217444,
      "grad_norm": 0.24249699711799622,
      "learning_rate": 5e-05,
      "loss": 0.4757,
      "num_tokens": 430504573.0,
      "step": 139
    },
    {
      "epoch": 1.3345280764635603,
      "grad_norm": 0.23354573547840118,
      "learning_rate": 5e-05,
      "loss": 0.4605,
      "num_tokens": 433626191.0,
      "step": 140
    },
    {
      "epoch": 1.3440860215053765,
      "grad_norm": 0.2180928736925125,
      "learning_rate": 5e-05,
      "loss": 0.4679,
      "num_tokens": 436727625.0,
      "step": 141
    },
    {
      "epoch": 1.3536439665471924,
      "grad_norm": 0.2624548077583313,
      "learning_rate": 5e-05,
      "loss": 0.4704,
      "num_tokens": 439824215.0,
      "step": 142
    },
    {
      "epoch": 1.3632019115890084,
      "grad_norm": 0.22936105728149414,
      "learning_rate": 5e-05,
      "loss": 0.4638,
      "num_tokens": 442903885.0,
      "step": 143
    },
    {
      "epoch": 1.3727598566308243,
      "grad_norm": 0.2361782044172287,
      "learning_rate": 5e-05,
      "loss": 0.4722,
      "num_tokens": 446049216.0,
      "step": 144
    },
    {
      "epoch": 1.3823178016726403,
      "grad_norm": 0.22354678809642792,
      "learning_rate": 5e-05,
      "loss": 0.4702,
      "num_tokens": 449164822.0,
      "step": 145
    },
    {
      "epoch": 1.3918757467144565,
      "grad_norm": 0.2597694396972656,
      "learning_rate": 5e-05,
      "loss": 0.4659,
      "num_tokens": 452296016.0,
      "step": 146
    },
    {
      "epoch": 1.4014336917562724,
      "grad_norm": 0.18445123732089996,
      "learning_rate": 5e-05,
      "loss": 0.4675,
      "num_tokens": 455409198.0,
      "step": 147
    },
    {
      "epoch": 1.4109916367980884,
      "grad_norm": 0.24752481281757355,
      "learning_rate": 5e-05,
      "loss": 0.4665,
      "num_tokens": 458552498.0,
      "step": 148
    },
    {
      "epoch": 1.4205495818399045,
      "grad_norm": 0.23295103013515472,
      "learning_rate": 5e-05,
      "loss": 0.4642,
      "num_tokens": 461598172.0,
      "step": 149
    },
    {
      "epoch": 1.4301075268817205,
      "grad_norm": 0.26925209164619446,
      "learning_rate": 5e-05,
      "loss": 0.4618,
      "num_tokens": 464763731.0,
      "step": 150
    },
    {
      "epoch": 1.4396654719235364,
      "grad_norm": 0.1971091479063034,
      "learning_rate": 5e-05,
      "loss": 0.4639,
      "num_tokens": 467905236.0,
      "step": 151
    },
    {
      "epoch": 1.4492234169653524,
      "grad_norm": 0.2771715819835663,
      "learning_rate": 5e-05,
      "loss": 0.4645,
      "num_tokens": 471038706.0,
      "step": 152
    },
    {
      "epoch": 1.4587813620071683,
      "grad_norm": 0.2006852775812149,
      "learning_rate": 5e-05,
      "loss": 0.4664,
      "num_tokens": 474170594.0,
      "step": 153
    },
    {
      "epoch": 1.4683393070489845,
      "grad_norm": 0.27502164244651794,
      "learning_rate": 5e-05,
      "loss": 0.4581,
      "num_tokens": 477293327.0,
      "step": 154
    },
    {
      "epoch": 1.4778972520908005,
      "grad_norm": 0.19383655488491058,
      "learning_rate": 5e-05,
      "loss": 0.4641,
      "num_tokens": 480356338.0,
      "step": 155
    },
    {
      "epoch": 1.4874551971326164,
      "grad_norm": 0.29519346356391907,
      "learning_rate": 5e-05,
      "loss": 0.4636,
      "num_tokens": 483466822.0,
      "step": 156
    },
    {
      "epoch": 1.4970131421744326,
      "grad_norm": 0.24049213528633118,
      "learning_rate": 5e-05,
      "loss": 0.4708,
      "num_tokens": 486598025.0,
      "step": 157
    },
    {
      "epoch": 1.5065710872162486,
      "grad_norm": 0.23467357456684113,
      "learning_rate": 5e-05,
      "loss": 0.4629,
      "num_tokens": 489710268.0,
      "step": 158
    },
    {
      "epoch": 1.5161290322580645,
      "grad_norm": 0.23279620707035065,
      "learning_rate": 5e-05,
      "loss": 0.4642,
      "num_tokens": 492749301.0,
      "step": 159
    },
    {
      "epoch": 1.5256869772998805,
      "grad_norm": 0.21989446878433228,
      "learning_rate": 5e-05,
      "loss": 0.4609,
      "num_tokens": 495858425.0,
      "step": 160
    },
    {
      "epoch": 1.5352449223416964,
      "grad_norm": 0.20997576415538788,
      "learning_rate": 5e-05,
      "loss": 0.4615,
      "num_tokens": 499002124.0,
      "step": 161
    },
    {
      "epoch": 1.5448028673835126,
      "grad_norm": 0.2443646341562271,
      "learning_rate": 5e-05,
      "loss": 0.4599,
      "num_tokens": 502158127.0,
      "step": 162
    },
    {
      "epoch": 1.5543608124253285,
      "grad_norm": 0.2202104926109314,
      "learning_rate": 5e-05,
      "loss": 0.4685,
      "num_tokens": 505273653.0,
      "step": 163
    },
    {
      "epoch": 1.5639187574671447,
      "grad_norm": 0.2284436672925949,
      "learning_rate": 5e-05,
      "loss": 0.4666,
      "num_tokens": 508383175.0,
      "step": 164
    },
    {
      "epoch": 1.5734767025089607,
      "grad_norm": 0.21461881697177887,
      "learning_rate": 5e-05,
      "loss": 0.4649,
      "num_tokens": 511456188.0,
      "step": 165
    },
    {
      "epoch": 1.5830346475507766,
      "grad_norm": 0.24341613054275513,
      "learning_rate": 5e-05,
      "loss": 0.4726,
      "num_tokens": 514504919.0,
      "step": 166
    },
    {
      "epoch": 1.5925925925925926,
      "grad_norm": 0.2432275414466858,
      "learning_rate": 5e-05,
      "loss": 0.462,
      "num_tokens": 517638097.0,
      "step": 167
    },
    {
      "epoch": 1.6021505376344085,
      "grad_norm": 0.1924099624156952,
      "learning_rate": 5e-05,
      "loss": 0.4574,
      "num_tokens": 520744764.0,
      "step": 168
    },
    {
      "epoch": 1.6117084826762245,
      "grad_norm": 0.2210276573896408,
      "learning_rate": 5e-05,
      "loss": 0.4652,
      "num_tokens": 523847555.0,
      "step": 169
    },
    {
      "epoch": 1.6212664277180406,
      "grad_norm": 0.24831326305866241,
      "learning_rate": 5e-05,
      "loss": 0.4622,
      "num_tokens": 526938439.0,
      "step": 170
    },
    {
      "epoch": 1.6308243727598566,
      "grad_norm": 0.20027406513690948,
      "learning_rate": 5e-05,
      "loss": 0.4625,
      "num_tokens": 530100826.0,
      "step": 171
    },
    {
      "epoch": 1.6403823178016728,
      "grad_norm": 0.2210628092288971,
      "learning_rate": 5e-05,
      "loss": 0.4543,
      "num_tokens": 533217368.0,
      "step": 172
    },
    {
      "epoch": 1.6499402628434887,
      "grad_norm": 0.21531818807125092,
      "learning_rate": 5e-05,
      "loss": 0.464,
      "num_tokens": 536266028.0,
      "step": 173
    },
    {
      "epoch": 1.6594982078853047,
      "grad_norm": 0.24346983432769775,
      "learning_rate": 5e-05,
      "loss": 0.4582,
      "num_tokens": 539353780.0,
      "step": 174
    },
    {
      "epoch": 1.6690561529271206,
      "grad_norm": 0.18500176072120667,
      "learning_rate": 5e-05,
      "loss": 0.4611,
      "num_tokens": 542436030.0,
      "step": 175
    },
    {
      "epoch": 1.6786140979689366,
      "grad_norm": 0.21900725364685059,
      "learning_rate": 5e-05,
      "loss": 0.4567,
      "num_tokens": 545556259.0,
      "step": 176
    },
    {
      "epoch": 1.6881720430107527,
      "grad_norm": 0.26041945815086365,
      "learning_rate": 5e-05,
      "loss": 0.4609,
      "num_tokens": 548651036.0,
      "step": 177
    },
    {
      "epoch": 1.6977299880525687,
      "grad_norm": 0.1868957281112671,
      "learning_rate": 5e-05,
      "loss": 0.4578,
      "num_tokens": 551763960.0,
      "step": 178
    },
    {
      "epoch": 1.7072879330943849,
      "grad_norm": 0.30002743005752563,
      "learning_rate": 5e-05,
      "loss": 0.4621,
      "num_tokens": 554859971.0,
      "step": 179
    },
    {
      "epoch": 1.7168458781362008,
      "grad_norm": 0.15785135328769684,
      "learning_rate": 5e-05,
      "loss": 0.4531,
      "num_tokens": 557960344.0,
      "step": 180
    },
    {
      "epoch": 1.7264038231780168,
      "grad_norm": 0.21860018372535706,
      "learning_rate": 5e-05,
      "loss": 0.456,
      "num_tokens": 561070346.0,
      "step": 181
    },
    {
      "epoch": 1.7359617682198327,
      "grad_norm": 0.21262319386005402,
      "learning_rate": 5e-05,
      "loss": 0.4548,
      "num_tokens": 564124513.0,
      "step": 182
    },
    {
      "epoch": 1.7455197132616487,
      "grad_norm": 0.208367258310318,
      "learning_rate": 5e-05,
      "loss": 0.4597,
      "num_tokens": 567229917.0,
      "step": 183
    },
    {
      "epoch": 1.7550776583034646,
      "grad_norm": 0.23050186038017273,
      "learning_rate": 5e-05,
      "loss": 0.4609,
      "num_tokens": 570377549.0,
      "step": 184
    },
    {
      "epoch": 1.7646356033452808,
      "grad_norm": 0.19711245596408844,
      "learning_rate": 5e-05,
      "loss": 0.4596,
      "num_tokens": 573423384.0,
      "step": 185
    },
    {
      "epoch": 1.7741935483870968,
      "grad_norm": 0.25033050775527954,
      "learning_rate": 5e-05,
      "loss": 0.4536,
      "num_tokens": 576529785.0,
      "step": 186
    },
    {
      "epoch": 1.783751493428913,
      "grad_norm": 0.23019000887870789,
      "learning_rate": 5e-05,
      "loss": 0.457,
      "num_tokens": 579611243.0,
      "step": 187
    },
    {
      "epoch": 1.7933094384707289,
      "grad_norm": 0.24459266662597656,
      "learning_rate": 5e-05,
      "loss": 0.4563,
      "num_tokens": 582684585.0,
      "step": 188
    },
    {
      "epoch": 1.8028673835125448,
      "grad_norm": 0.2335624098777771,
      "learning_rate": 5e-05,
      "loss": 0.456,
      "num_tokens": 585749574.0,
      "step": 189
    },
    {
      "epoch": 1.8124253285543608,
      "grad_norm": 0.21826566755771637,
      "learning_rate": 5e-05,
      "loss": 0.4545,
      "num_tokens": 588793971.0,
      "step": 190
    },
    {
      "epoch": 1.8219832735961767,
      "grad_norm": 0.2118789553642273,
      "learning_rate": 5e-05,
      "loss": 0.4561,
      "num_tokens": 591863271.0,
      "step": 191
    },
    {
      "epoch": 1.8315412186379927,
      "grad_norm": 0.25364288687705994,
      "learning_rate": 5e-05,
      "loss": 0.4582,
      "num_tokens": 594955013.0,
      "step": 192
    },
    {
      "epoch": 1.8410991636798089,
      "grad_norm": 0.18223045766353607,
      "learning_rate": 5e-05,
      "loss": 0.4586,
      "num_tokens": 598054762.0,
      "step": 193
    },
    {
      "epoch": 1.8506571087216248,
      "grad_norm": 0.19568181037902832,
      "learning_rate": 5e-05,
      "loss": 0.4542,
      "num_tokens": 601156311.0,
      "step": 194
    },
    {
      "epoch": 1.860215053763441,
      "grad_norm": 0.21927742660045624,
      "learning_rate": 5e-05,
      "loss": 0.4593,
      "num_tokens": 604264490.0,
      "step": 195
    },
    {
      "epoch": 1.869772998805257,
      "grad_norm": 0.22864626348018646,
      "learning_rate": 5e-05,
      "loss": 0.4582,
      "num_tokens": 607369801.0,
      "step": 196
    },
    {
      "epoch": 1.8793309438470729,
      "grad_norm": 0.2220122367143631,
      "learning_rate": 5e-05,
      "loss": 0.4586,
      "num_tokens": 610464157.0,
      "step": 197
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 0.20654238760471344,
      "learning_rate": 5e-05,
      "loss": 0.4572,
      "num_tokens": 613600074.0,
      "step": 198
    },
    {
      "epoch": 1.8984468339307048,
      "grad_norm": 0.24055001139640808,
      "learning_rate": 5e-05,
      "loss": 0.447,
      "num_tokens": 616692135.0,
      "step": 199
    },
    {
      "epoch": 1.9080047789725207,
      "grad_norm": 0.2102368324995041,
      "learning_rate": 5e-05,
      "loss": 0.4616,
      "num_tokens": 619865728.0,
      "step": 200
    },
    {
      "epoch": 1.917562724014337,
      "grad_norm": 0.1804041713476181,
      "learning_rate": 5e-05,
      "loss": 0.456,
      "num_tokens": 622937270.0,
      "step": 201
    },
    {
      "epoch": 1.927120669056153,
      "grad_norm": 0.20141775906085968,
      "learning_rate": 5e-05,
      "loss": 0.4573,
      "num_tokens": 626025595.0,
      "step": 202
    },
    {
      "epoch": 1.936678614097969,
      "grad_norm": 0.23730237782001495,
      "learning_rate": 5e-05,
      "loss": 0.4588,
      "num_tokens": 629102565.0,
      "step": 203
    },
    {
      "epoch": 1.946236559139785,
      "grad_norm": 0.20814980566501617,
      "learning_rate": 5e-05,
      "loss": 0.4596,
      "num_tokens": 632248389.0,
      "step": 204
    },
    {
      "epoch": 1.955794504181601,
      "grad_norm": 0.23954477906227112,
      "learning_rate": 5e-05,
      "loss": 0.4608,
      "num_tokens": 635381252.0,
      "step": 205
    },
    {
      "epoch": 1.965352449223417,
      "grad_norm": 0.2159876823425293,
      "learning_rate": 5e-05,
      "loss": 0.4568,
      "num_tokens": 638503290.0,
      "step": 206
    },
    {
      "epoch": 1.9749103942652328,
      "grad_norm": 0.2248695194721222,
      "learning_rate": 5e-05,
      "loss": 0.4494,
      "num_tokens": 641566168.0,
      "step": 207
    },
    {
      "epoch": 1.984468339307049,
      "grad_norm": 0.18469811975955963,
      "learning_rate": 5e-05,
      "loss": 0.4553,
      "num_tokens": 644664768.0,
      "step": 208
    },
    {
      "epoch": 1.994026284348865,
      "grad_norm": 0.2029660940170288,
      "learning_rate": 5e-05,
      "loss": 0.458,
      "num_tokens": 647777196.0,
      "step": 209
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2680661678314209,
      "learning_rate": 5e-05,
      "loss": 0.4472,
      "num_tokens": 649717884.0,
      "step": 210
    },
    {
      "epoch": 2.009557945041816,
      "grad_norm": 0.2700228691101074,
      "learning_rate": 5e-05,
      "loss": 0.4049,
      "num_tokens": 652835514.0,
      "step": 211
    },
    {
      "epoch": 2.019115890083632,
      "grad_norm": 0.21437576413154602,
      "learning_rate": 5e-05,
      "loss": 0.4077,
      "num_tokens": 655939553.0,
      "step": 212
    },
    {
      "epoch": 2.028673835125448,
      "grad_norm": 0.2812529504299164,
      "learning_rate": 5e-05,
      "loss": 0.4043,
      "num_tokens": 659052255.0,
      "step": 213
    },
    {
      "epoch": 2.0382317801672643,
      "grad_norm": 0.19706906378269196,
      "learning_rate": 5e-05,
      "loss": 0.4069,
      "num_tokens": 662144062.0,
      "step": 214
    },
    {
      "epoch": 2.04778972520908,
      "grad_norm": 0.23425546288490295,
      "learning_rate": 5e-05,
      "loss": 0.3947,
      "num_tokens": 665243818.0,
      "step": 215
    },
    {
      "epoch": 2.057347670250896,
      "grad_norm": 0.2341323047876358,
      "learning_rate": 5e-05,
      "loss": 0.4005,
      "num_tokens": 668343069.0,
      "step": 216
    },
    {
      "epoch": 2.066905615292712,
      "grad_norm": 0.26267462968826294,
      "learning_rate": 5e-05,
      "loss": 0.4076,
      "num_tokens": 671491544.0,
      "step": 217
    },
    {
      "epoch": 2.076463560334528,
      "grad_norm": 0.22123785316944122,
      "learning_rate": 5e-05,
      "loss": 0.3994,
      "num_tokens": 674603425.0,
      "step": 218
    },
    {
      "epoch": 2.086021505376344,
      "grad_norm": 0.22117979824543,
      "learning_rate": 5e-05,
      "loss": 0.3999,
      "num_tokens": 677683109.0,
      "step": 219
    },
    {
      "epoch": 2.09557945041816,
      "grad_norm": 0.25451090931892395,
      "learning_rate": 5e-05,
      "loss": 0.4035,
      "num_tokens": 680765161.0,
      "step": 220
    },
    {
      "epoch": 2.105137395459976,
      "grad_norm": 0.21930952370166779,
      "learning_rate": 5e-05,
      "loss": 0.4027,
      "num_tokens": 683877744.0,
      "step": 221
    },
    {
      "epoch": 2.1146953405017923,
      "grad_norm": 0.2268250733613968,
      "learning_rate": 5e-05,
      "loss": 0.4017,
      "num_tokens": 687007762.0,
      "step": 222
    },
    {
      "epoch": 2.1242532855436083,
      "grad_norm": 0.21051234006881714,
      "learning_rate": 5e-05,
      "loss": 0.4083,
      "num_tokens": 690110389.0,
      "step": 223
    },
    {
      "epoch": 2.133811230585424,
      "grad_norm": 0.22137832641601562,
      "learning_rate": 5e-05,
      "loss": 0.3908,
      "num_tokens": 693193272.0,
      "step": 224
    },
    {
      "epoch": 2.14336917562724,
      "grad_norm": 0.24819853901863098,
      "learning_rate": 5e-05,
      "loss": 0.4037,
      "num_tokens": 696332399.0,
      "step": 225
    },
    {
      "epoch": 2.152927120669056,
      "grad_norm": 0.2136155366897583,
      "learning_rate": 5e-05,
      "loss": 0.3972,
      "num_tokens": 699449474.0,
      "step": 226
    },
    {
      "epoch": 2.162485065710872,
      "grad_norm": 0.21676744520664215,
      "learning_rate": 5e-05,
      "loss": 0.4009,
      "num_tokens": 702535376.0,
      "step": 227
    },
    {
      "epoch": 2.172043010752688,
      "grad_norm": 0.21379505097866058,
      "learning_rate": 5e-05,
      "loss": 0.4048,
      "num_tokens": 705594342.0,
      "step": 228
    },
    {
      "epoch": 2.1816009557945044,
      "grad_norm": 0.24907568097114563,
      "learning_rate": 5e-05,
      "loss": 0.4016,
      "num_tokens": 708681631.0,
      "step": 229
    },
    {
      "epoch": 2.1911589008363204,
      "grad_norm": 0.23827004432678223,
      "learning_rate": 5e-05,
      "loss": 0.3897,
      "num_tokens": 711768161.0,
      "step": 230
    },
    {
      "epoch": 2.2007168458781363,
      "grad_norm": 0.19475553929805756,
      "learning_rate": 5e-05,
      "loss": 0.3984,
      "num_tokens": 714866856.0,
      "step": 231
    },
    {
      "epoch": 2.2102747909199523,
      "grad_norm": 0.22524000704288483,
      "learning_rate": 5e-05,
      "loss": 0.3997,
      "num_tokens": 717989725.0,
      "step": 232
    },
    {
      "epoch": 2.219832735961768,
      "grad_norm": 0.22430852055549622,
      "learning_rate": 5e-05,
      "loss": 0.3981,
      "num_tokens": 721080176.0,
      "step": 233
    },
    {
      "epoch": 2.229390681003584,
      "grad_norm": 0.2231917530298233,
      "learning_rate": 5e-05,
      "loss": 0.4044,
      "num_tokens": 724211432.0,
      "step": 234
    },
    {
      "epoch": 2.2389486260454,
      "grad_norm": 0.24612534046173096,
      "learning_rate": 5e-05,
      "loss": 0.3955,
      "num_tokens": 727270220.0,
      "step": 235
    },
    {
      "epoch": 2.248506571087216,
      "grad_norm": 0.2350219190120697,
      "learning_rate": 5e-05,
      "loss": 0.4062,
      "num_tokens": 730444444.0,
      "step": 236
    },
    {
      "epoch": 2.258064516129032,
      "grad_norm": 0.24301743507385254,
      "learning_rate": 5e-05,
      "loss": 0.4025,
      "num_tokens": 733557450.0,
      "step": 237
    },
    {
      "epoch": 2.2676224611708484,
      "grad_norm": 0.20786051452159882,
      "learning_rate": 5e-05,
      "loss": 0.4005,
      "num_tokens": 736681750.0,
      "step": 238
    },
    {
      "epoch": 2.2771804062126644,
      "grad_norm": 0.33719518780708313,
      "learning_rate": 5e-05,
      "loss": 0.393,
      "num_tokens": 739789232.0,
      "step": 239
    },
    {
      "epoch": 2.2867383512544803,
      "grad_norm": 0.17687377333641052,
      "learning_rate": 5e-05,
      "loss": 0.4038,
      "num_tokens": 742891601.0,
      "step": 240
    },
    {
      "epoch": 2.2962962962962963,
      "grad_norm": 0.342306524515152,
      "learning_rate": 5e-05,
      "loss": 0.4019,
      "num_tokens": 746006954.0,
      "step": 241
    },
    {
      "epoch": 2.3058542413381122,
      "grad_norm": 0.16845592856407166,
      "learning_rate": 5e-05,
      "loss": 0.403,
      "num_tokens": 749147037.0,
      "step": 242
    },
    {
      "epoch": 2.315412186379928,
      "grad_norm": 0.32256966829299927,
      "learning_rate": 5e-05,
      "loss": 0.4034,
      "num_tokens": 752229629.0,
      "step": 243
    },
    {
      "epoch": 2.324970131421744,
      "grad_norm": 0.20878097414970398,
      "learning_rate": 5e-05,
      "loss": 0.4026,
      "num_tokens": 755278777.0,
      "step": 244
    },
    {
      "epoch": 2.3345280764635605,
      "grad_norm": 0.2807317078113556,
      "learning_rate": 5e-05,
      "loss": 0.406,
      "num_tokens": 758363222.0,
      "step": 245
    },
    {
      "epoch": 2.3440860215053765,
      "grad_norm": 0.2278064638376236,
      "learning_rate": 5e-05,
      "loss": 0.401,
      "num_tokens": 761474147.0,
      "step": 246
    },
    {
      "epoch": 2.3536439665471924,
      "grad_norm": 0.2612324357032776,
      "learning_rate": 5e-05,
      "loss": 0.395,
      "num_tokens": 764551769.0,
      "step": 247
    },
    {
      "epoch": 2.3632019115890084,
      "grad_norm": 0.23537400364875793,
      "learning_rate": 5e-05,
      "loss": 0.3948,
      "num_tokens": 767614488.0,
      "step": 248
    },
    {
      "epoch": 2.3727598566308243,
      "grad_norm": 0.21469944715499878,
      "learning_rate": 5e-05,
      "loss": 0.403,
      "num_tokens": 770735177.0,
      "step": 249
    },
    {
      "epoch": 2.3823178016726403,
      "grad_norm": 0.2674992084503174,
      "learning_rate": 5e-05,
      "loss": 0.3933,
      "num_tokens": 773851787.0,
      "step": 250
    },
    {
      "epoch": 2.3918757467144562,
      "grad_norm": 0.18953253328800201,
      "learning_rate": 5e-05,
      "loss": 0.3994,
      "num_tokens": 776935088.0,
      "step": 251
    },
    {
      "epoch": 2.4014336917562726,
      "grad_norm": 0.2478407323360443,
      "learning_rate": 5e-05,
      "loss": 0.4052,
      "num_tokens": 780049122.0,
      "step": 252
    },
    {
      "epoch": 2.4109916367980886,
      "grad_norm": 0.195692777633667,
      "learning_rate": 5e-05,
      "loss": 0.4084,
      "num_tokens": 783178312.0,
      "step": 253
    },
    {
      "epoch": 2.4205495818399045,
      "grad_norm": 0.20106397569179535,
      "learning_rate": 5e-05,
      "loss": 0.4022,
      "num_tokens": 786281027.0,
      "step": 254
    },
    {
      "epoch": 2.4301075268817205,
      "grad_norm": 0.19922764599323273,
      "learning_rate": 5e-05,
      "loss": 0.4039,
      "num_tokens": 789414028.0,
      "step": 255
    },
    {
      "epoch": 2.4396654719235364,
      "grad_norm": 0.2001892626285553,
      "learning_rate": 5e-05,
      "loss": 0.4024,
      "num_tokens": 792520500.0,
      "step": 256
    },
    {
      "epoch": 2.4492234169653524,
      "grad_norm": 0.22683829069137573,
      "learning_rate": 5e-05,
      "loss": 0.4022,
      "num_tokens": 795635985.0,
      "step": 257
    },
    {
      "epoch": 2.4587813620071683,
      "grad_norm": 0.20693090558052063,
      "learning_rate": 5e-05,
      "loss": 0.3995,
      "num_tokens": 798748918.0,
      "step": 258
    },
    {
      "epoch": 2.4683393070489843,
      "grad_norm": 0.22366446256637573,
      "learning_rate": 5e-05,
      "loss": 0.3988,
      "num_tokens": 801831194.0,
      "step": 259
    },
    {
      "epoch": 2.4778972520908003,
      "grad_norm": 0.21484145522117615,
      "learning_rate": 5e-05,
      "loss": 0.3991,
      "num_tokens": 804928214.0,
      "step": 260
    },
    {
      "epoch": 2.4874551971326166,
      "grad_norm": 0.22603361308574677,
      "learning_rate": 5e-05,
      "loss": 0.4033,
      "num_tokens": 807987120.0,
      "step": 261
    },
    {
      "epoch": 2.4970131421744326,
      "grad_norm": 0.23147359490394592,
      "learning_rate": 5e-05,
      "loss": 0.4022,
      "num_tokens": 811098180.0,
      "step": 262
    },
    {
      "epoch": 2.5065710872162486,
      "grad_norm": 0.1985515058040619,
      "learning_rate": 5e-05,
      "loss": 0.4022,
      "num_tokens": 814198566.0,
      "step": 263
    },
    {
      "epoch": 2.5161290322580645,
      "grad_norm": 0.20071357488632202,
      "learning_rate": 5e-05,
      "loss": 0.4034,
      "num_tokens": 817257072.0,
      "step": 264
    },
    {
      "epoch": 2.5256869772998805,
      "grad_norm": 0.25529035925865173,
      "learning_rate": 5e-05,
      "loss": 0.4067,
      "num_tokens": 820406825.0,
      "step": 265
    },
    {
      "epoch": 2.5352449223416964,
      "grad_norm": 0.20370543003082275,
      "learning_rate": 5e-05,
      "loss": 0.4008,
      "num_tokens": 823512817.0,
      "step": 266
    },
    {
      "epoch": 2.5448028673835124,
      "grad_norm": 0.20760004222393036,
      "learning_rate": 5e-05,
      "loss": 0.4034,
      "num_tokens": 826610050.0,
      "step": 267
    },
    {
      "epoch": 2.5543608124253288,
      "grad_norm": 0.20357725024223328,
      "learning_rate": 5e-05,
      "loss": 0.398,
      "num_tokens": 829753903.0,
      "step": 268
    },
    {
      "epoch": 2.5639187574671447,
      "grad_norm": 0.22291164100170135,
      "learning_rate": 5e-05,
      "loss": 0.3995,
      "num_tokens": 832868477.0,
      "step": 269
    },
    {
      "epoch": 2.5734767025089607,
      "grad_norm": 0.1923750936985016,
      "learning_rate": 5e-05,
      "loss": 0.402,
      "num_tokens": 835937080.0,
      "step": 270
    },
    {
      "epoch": 2.5830346475507766,
      "grad_norm": 0.22883036732673645,
      "learning_rate": 5e-05,
      "loss": 0.3997,
      "num_tokens": 839073075.0,
      "step": 271
    },
    {
      "epoch": 2.5925925925925926,
      "grad_norm": 0.21349798142910004,
      "learning_rate": 5e-05,
      "loss": 0.403,
      "num_tokens": 842191197.0,
      "step": 272
    },
    {
      "epoch": 2.6021505376344085,
      "grad_norm": 0.22202804684638977,
      "learning_rate": 5e-05,
      "loss": 0.4026,
      "num_tokens": 845276551.0,
      "step": 273
    },
    {
      "epoch": 2.6117084826762245,
      "grad_norm": 0.20453181862831116,
      "learning_rate": 5e-05,
      "loss": 0.3986,
      "num_tokens": 848352451.0,
      "step": 274
    },
    {
      "epoch": 2.621266427718041,
      "grad_norm": 0.21245239675045013,
      "learning_rate": 5e-05,
      "loss": 0.3993,
      "num_tokens": 851459757.0,
      "step": 275
    },
    {
      "epoch": 2.6308243727598564,
      "grad_norm": 0.20784446597099304,
      "learning_rate": 5e-05,
      "loss": 0.4029,
      "num_tokens": 854632749.0,
      "step": 276
    },
    {
      "epoch": 2.6403823178016728,
      "grad_norm": 0.20124511420726776,
      "learning_rate": 5e-05,
      "loss": 0.4018,
      "num_tokens": 857704440.0,
      "step": 277
    },
    {
      "epoch": 2.6499402628434887,
      "grad_norm": 0.19951878488063812,
      "learning_rate": 5e-05,
      "loss": 0.4096,
      "num_tokens": 860825716.0,
      "step": 278
    },
    {
      "epoch": 2.6594982078853047,
      "grad_norm": 0.19267506897449493,
      "learning_rate": 5e-05,
      "loss": 0.3974,
      "num_tokens": 863922145.0,
      "step": 279
    },
    {
      "epoch": 2.6690561529271206,
      "grad_norm": 0.21417343616485596,
      "learning_rate": 5e-05,
      "loss": 0.4002,
      "num_tokens": 866991544.0,
      "step": 280
    },
    {
      "epoch": 2.6786140979689366,
      "grad_norm": 0.21816791594028473,
      "learning_rate": 5e-05,
      "loss": 0.3997,
      "num_tokens": 870069694.0,
      "step": 281
    },
    {
      "epoch": 2.688172043010753,
      "grad_norm": 0.21573670208454132,
      "learning_rate": 5e-05,
      "loss": 0.4064,
      "num_tokens": 873180617.0,
      "step": 282
    },
    {
      "epoch": 2.6977299880525685,
      "grad_norm": 0.18886543810367584,
      "learning_rate": 5e-05,
      "loss": 0.3971,
      "num_tokens": 876262507.0,
      "step": 283
    },
    {
      "epoch": 2.707287933094385,
      "grad_norm": 0.18656791746616364,
      "learning_rate": 5e-05,
      "loss": 0.4038,
      "num_tokens": 879380128.0,
      "step": 284
    },
    {
      "epoch": 2.716845878136201,
      "grad_norm": 0.197296142578125,
      "learning_rate": 5e-05,
      "loss": 0.3986,
      "num_tokens": 882473178.0,
      "step": 285
    },
    {
      "epoch": 2.7264038231780168,
      "grad_norm": 0.23007364571094513,
      "learning_rate": 5e-05,
      "loss": 0.4036,
      "num_tokens": 885565233.0,
      "step": 286
    },
    {
      "epoch": 2.7359617682198327,
      "grad_norm": 0.19327418506145477,
      "learning_rate": 5e-05,
      "loss": 0.4134,
      "num_tokens": 888688634.0,
      "step": 287
    },
    {
      "epoch": 2.7455197132616487,
      "grad_norm": 0.1903911530971527,
      "learning_rate": 5e-05,
      "loss": 0.3996,
      "num_tokens": 891794908.0,
      "step": 288
    },
    {
      "epoch": 2.7550776583034646,
      "grad_norm": 0.18659088015556335,
      "learning_rate": 5e-05,
      "loss": 0.4044,
      "num_tokens": 894950413.0,
      "step": 289
    },
    {
      "epoch": 2.7646356033452806,
      "grad_norm": 0.22853848338127136,
      "learning_rate": 5e-05,
      "loss": 0.4085,
      "num_tokens": 898028493.0,
      "step": 290
    },
    {
      "epoch": 2.774193548387097,
      "grad_norm": 0.2249801754951477,
      "learning_rate": 5e-05,
      "loss": 0.4063,
      "num_tokens": 901215396.0,
      "step": 291
    },
    {
      "epoch": 2.783751493428913,
      "grad_norm": 0.2070578783750534,
      "learning_rate": 5e-05,
      "loss": 0.3988,
      "num_tokens": 904344510.0,
      "step": 292
    },
    {
      "epoch": 2.793309438470729,
      "grad_norm": 0.1973543018102646,
      "learning_rate": 5e-05,
      "loss": 0.4042,
      "num_tokens": 907446044.0,
      "step": 293
    },
    {
      "epoch": 2.802867383512545,
      "grad_norm": 0.18739643692970276,
      "learning_rate": 5e-05,
      "loss": 0.4118,
      "num_tokens": 910525112.0,
      "step": 294
    },
    {
      "epoch": 2.812425328554361,
      "grad_norm": 0.18655946850776672,
      "learning_rate": 5e-05,
      "loss": 0.3976,
      "num_tokens": 913646064.0,
      "step": 295
    },
    {
      "epoch": 2.8219832735961767,
      "grad_norm": 0.19254498183727264,
      "learning_rate": 5e-05,
      "loss": 0.4044,
      "num_tokens": 916750615.0,
      "step": 296
    },
    {
      "epoch": 2.8315412186379927,
      "grad_norm": 0.20286458730697632,
      "learning_rate": 5e-05,
      "loss": 0.4026,
      "num_tokens": 919815959.0,
      "step": 297
    },
    {
      "epoch": 2.841099163679809,
      "grad_norm": 0.2116730809211731,
      "learning_rate": 5e-05,
      "loss": 0.3999,
      "num_tokens": 922854402.0,
      "step": 298
    },
    {
      "epoch": 2.8506571087216246,
      "grad_norm": 0.22266528010368347,
      "learning_rate": 5e-05,
      "loss": 0.4038,
      "num_tokens": 925926441.0,
      "step": 299
    },
    {
      "epoch": 2.860215053763441,
      "grad_norm": 0.18784675002098083,
      "learning_rate": 5e-05,
      "loss": 0.4046,
      "num_tokens": 929091816.0,
      "step": 300
    },
    {
      "epoch": 2.869772998805257,
      "grad_norm": 0.18861991167068481,
      "learning_rate": 5e-05,
      "loss": 0.4058,
      "num_tokens": 932245034.0,
      "step": 301
    },
    {
      "epoch": 2.879330943847073,
      "grad_norm": 0.18745040893554688,
      "learning_rate": 5e-05,
      "loss": 0.4053,
      "num_tokens": 935337789.0,
      "step": 302
    },
    {
      "epoch": 2.888888888888889,
      "grad_norm": 0.21158824861049652,
      "learning_rate": 5e-05,
      "loss": 0.398,
      "num_tokens": 938469999.0,
      "step": 303
    },
    {
      "epoch": 2.898446833930705,
      "grad_norm": 0.21590955555438995,
      "learning_rate": 5e-05,
      "loss": 0.4024,
      "num_tokens": 941548793.0,
      "step": 304
    },
    {
      "epoch": 2.9080047789725207,
      "grad_norm": 0.206715390086174,
      "learning_rate": 5e-05,
      "loss": 0.4048,
      "num_tokens": 944687830.0,
      "step": 305
    },
    {
      "epoch": 2.9175627240143367,
      "grad_norm": 0.2118476778268814,
      "learning_rate": 5e-05,
      "loss": 0.4093,
      "num_tokens": 947789759.0,
      "step": 306
    },
    {
      "epoch": 2.927120669056153,
      "grad_norm": 0.18484579026699066,
      "learning_rate": 5e-05,
      "loss": 0.3981,
      "num_tokens": 950899733.0,
      "step": 307
    },
    {
      "epoch": 2.936678614097969,
      "grad_norm": 0.17388074100017548,
      "learning_rate": 5e-05,
      "loss": 0.4065,
      "num_tokens": 954039453.0,
      "step": 308
    },
    {
      "epoch": 2.946236559139785,
      "grad_norm": 0.16568942368030548,
      "learning_rate": 5e-05,
      "loss": 0.3993,
      "num_tokens": 957164986.0,
      "step": 309
    },
    {
      "epoch": 2.955794504181601,
      "grad_norm": 0.17550726234912872,
      "learning_rate": 5e-05,
      "loss": 0.4014,
      "num_tokens": 960246209.0,
      "step": 310
    },
    {
      "epoch": 2.965352449223417,
      "grad_norm": 0.1897525042295456,
      "learning_rate": 5e-05,
      "loss": 0.3993,
      "num_tokens": 963312993.0,
      "step": 311
    },
    {
      "epoch": 2.974910394265233,
      "grad_norm": 0.1897035390138626,
      "learning_rate": 5e-05,
      "loss": 0.3997,
      "num_tokens": 966396496.0,
      "step": 312
    },
    {
      "epoch": 2.974910394265233,
      "step": 312,
      "total_flos": 3.993677328755458e+19,
      "train_loss": 0.4935996499963296,
      "train_runtime": 22258.2821,
      "train_samples_per_second": 12.633,
      "train_steps_per_second": 0.014
    }
  ],
  "logging_steps": 1,
  "max_steps": 312,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 16,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.993677328755458e+19,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}