{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.903225806451613,
  "eval_steps": 500,
  "global_step": 190,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.025806451612903226,
      "grad_norm": 891.0758056640625,
      "learning_rate": 5.000000000000001e-07,
      "loss": 12.476,
      "num_input_tokens_seen": 6416,
      "step": 1
    },
    {
      "epoch": 0.05161290322580645,
      "grad_norm": 829.80126953125,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 12.1047,
      "num_input_tokens_seen": 12992,
      "step": 2
    },
    {
      "epoch": 0.07741935483870968,
      "grad_norm": 868.9219360351562,
      "learning_rate": 1.5e-06,
      "loss": 12.0404,
      "num_input_tokens_seen": 19472,
      "step": 3
    },
    {
      "epoch": 0.1032258064516129,
      "grad_norm": 708.6889038085938,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 10.5293,
      "num_input_tokens_seen": 25936,
      "step": 4
    },
    {
      "epoch": 0.12903225806451613,
      "grad_norm": 580.6978759765625,
      "learning_rate": 2.5e-06,
      "loss": 8.3117,
      "num_input_tokens_seen": 32272,
      "step": 5
    },
    {
      "epoch": 0.15483870967741936,
      "grad_norm": 399.11077880859375,
      "learning_rate": 3e-06,
      "loss": 6.0338,
      "num_input_tokens_seen": 38640,
      "step": 6
    },
    {
      "epoch": 0.18064516129032257,
      "grad_norm": 377.40130615234375,
      "learning_rate": 3.5e-06,
      "loss": 4.8226,
      "num_input_tokens_seen": 44992,
      "step": 7
    },
    {
      "epoch": 0.2064516129032258,
      "grad_norm": 494.68267822265625,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.9485,
      "num_input_tokens_seen": 51328,
      "step": 8
    },
    {
      "epoch": 0.23225806451612904,
      "grad_norm": 273.6969909667969,
      "learning_rate": 4.5e-06,
      "loss": 0.9784,
      "num_input_tokens_seen": 57408,
      "step": 9
    },
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 265.04107666015625,
      "learning_rate": 5e-06,
      "loss": 0.5759,
      "num_input_tokens_seen": 63696,
      "step": 10
    },
    {
      "epoch": 0.2838709677419355,
      "grad_norm": 243.1269989013672,
      "learning_rate": 4.9996192378909785e-06,
      "loss": 1.1284,
      "num_input_tokens_seen": 69984,
      "step": 11
    },
    {
      "epoch": 0.3096774193548387,
      "grad_norm": 225.2501678466797,
      "learning_rate": 4.99847706754774e-06,
      "loss": 1.1272,
      "num_input_tokens_seen": 76384,
      "step": 12
    },
    {
      "epoch": 0.33548387096774196,
      "grad_norm": 161.70364379882812,
      "learning_rate": 4.9965738368864345e-06,
      "loss": 0.9501,
      "num_input_tokens_seen": 82704,
      "step": 13
    },
    {
      "epoch": 0.36129032258064514,
      "grad_norm": 70.2842788696289,
      "learning_rate": 4.993910125649561e-06,
      "loss": 0.461,
      "num_input_tokens_seen": 88976,
      "step": 14
    },
    {
      "epoch": 0.3870967741935484,
      "grad_norm": 165.92117309570312,
      "learning_rate": 4.990486745229364e-06,
      "loss": 1.2016,
      "num_input_tokens_seen": 95472,
      "step": 15
    },
    {
      "epoch": 0.4129032258064516,
      "grad_norm": 23.965112686157227,
      "learning_rate": 4.986304738420684e-06,
      "loss": 0.331,
      "num_input_tokens_seen": 101904,
      "step": 16
    },
    {
      "epoch": 0.43870967741935485,
      "grad_norm": 52.11637496948242,
      "learning_rate": 4.981365379103306e-06,
      "loss": 0.3565,
      "num_input_tokens_seen": 108272,
      "step": 17
    },
    {
      "epoch": 0.4645161290322581,
      "grad_norm": 87.24356842041016,
      "learning_rate": 4.975670171853926e-06,
      "loss": 0.6088,
      "num_input_tokens_seen": 114464,
      "step": 18
    },
    {
      "epoch": 0.49032258064516127,
      "grad_norm": 34.48093795776367,
      "learning_rate": 4.9692208514878445e-06,
      "loss": 0.2701,
      "num_input_tokens_seen": 120816,
      "step": 19
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 81.79713439941406,
      "learning_rate": 4.962019382530521e-06,
      "loss": 0.7005,
      "num_input_tokens_seen": 127120,
      "step": 20
    },
    {
      "epoch": 0.5419354838709678,
      "grad_norm": 55.757022857666016,
      "learning_rate": 4.9540679586191605e-06,
      "loss": 0.3424,
      "num_input_tokens_seen": 133712,
      "step": 21
    },
    {
      "epoch": 0.567741935483871,
      "grad_norm": 78.83650970458984,
      "learning_rate": 4.9453690018345144e-06,
      "loss": 0.6274,
      "num_input_tokens_seen": 139904,
      "step": 22
    },
    {
      "epoch": 0.5935483870967742,
      "grad_norm": 125.51705932617188,
      "learning_rate": 4.935925161963089e-06,
      "loss": 0.4183,
      "num_input_tokens_seen": 146256,
      "step": 23
    },
    {
      "epoch": 0.6193548387096774,
      "grad_norm": 13.837501525878906,
      "learning_rate": 4.925739315689991e-06,
      "loss": 0.1517,
      "num_input_tokens_seen": 152784,
      "step": 24
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 29.55669403076172,
      "learning_rate": 4.914814565722671e-06,
      "loss": 0.1906,
      "num_input_tokens_seen": 158976,
      "step": 25
    },
    {
      "epoch": 0.6709677419354839,
      "grad_norm": 14.560909271240234,
      "learning_rate": 4.903154239845798e-06,
      "loss": 0.1537,
      "num_input_tokens_seen": 165280,
      "step": 26
    },
    {
      "epoch": 0.6967741935483871,
      "grad_norm": 25.93684196472168,
      "learning_rate": 4.890761889907589e-06,
      "loss": 0.1957,
      "num_input_tokens_seen": 171808,
      "step": 27
    },
    {
      "epoch": 0.7225806451612903,
      "grad_norm": 43.76264572143555,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 0.3026,
      "num_input_tokens_seen": 178112,
      "step": 28
    },
    {
      "epoch": 0.7483870967741936,
      "grad_norm": 35.11921310424805,
      "learning_rate": 4.863796438998293e-06,
      "loss": 0.2031,
      "num_input_tokens_seen": 184448,
      "step": 29
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": 16.956266403198242,
      "learning_rate": 4.849231551964771e-06,
      "loss": 0.1461,
      "num_input_tokens_seen": 190896,
      "step": 30
    },
    {
      "epoch": 0.8,
      "grad_norm": 19.686155319213867,
      "learning_rate": 4.833951066243004e-06,
      "loss": 0.1873,
      "num_input_tokens_seen": 197024,
      "step": 31
    },
    {
      "epoch": 0.8258064516129032,
      "grad_norm": 17.89412498474121,
      "learning_rate": 4.817959636416969e-06,
      "loss": 0.1388,
      "num_input_tokens_seen": 203248,
      "step": 32
    },
    {
      "epoch": 0.8516129032258064,
      "grad_norm": 8.74397087097168,
      "learning_rate": 4.801262133631101e-06,
      "loss": 0.1127,
      "num_input_tokens_seen": 209760,
      "step": 33
    },
    {
      "epoch": 0.8774193548387097,
      "grad_norm": 12.055948257446289,
      "learning_rate": 4.783863644106502e-06,
      "loss": 0.1243,
      "num_input_tokens_seen": 215968,
      "step": 34
    },
    {
      "epoch": 0.9032258064516129,
      "grad_norm": 11.649015426635742,
      "learning_rate": 4.765769467591626e-06,
      "loss": 0.0969,
      "num_input_tokens_seen": 222192,
      "step": 35
    },
    {
      "epoch": 0.9290322580645162,
      "grad_norm": 10.582133293151855,
      "learning_rate": 4.746985115747918e-06,
      "loss": 0.089,
      "num_input_tokens_seen": 228512,
      "step": 36
    },
    {
      "epoch": 0.9548387096774194,
      "grad_norm": 17.14976692199707,
      "learning_rate": 4.72751631047092e-06,
      "loss": 0.1703,
      "num_input_tokens_seen": 235120,
      "step": 37
    },
    {
      "epoch": 0.9806451612903225,
      "grad_norm": 16.854312896728516,
      "learning_rate": 4.707368982147318e-06,
      "loss": 0.1132,
      "num_input_tokens_seen": 241584,
      "step": 38
    },
    {
      "epoch": 1.0064516129032257,
      "grad_norm": 9.631019592285156,
      "learning_rate": 4.68654926784849e-06,
      "loss": 0.1294,
      "num_input_tokens_seen": 248080,
      "step": 39
    },
    {
      "epoch": 1.032258064516129,
      "grad_norm": 9.488115310668945,
      "learning_rate": 4.665063509461098e-06,
      "loss": 0.0881,
      "num_input_tokens_seen": 254416,
      "step": 40
    },
    {
      "epoch": 1.0580645161290323,
      "grad_norm": 8.38987922668457,
      "learning_rate": 4.642918251755281e-06,
      "loss": 0.0504,
      "num_input_tokens_seen": 260640,
      "step": 41
    },
    {
      "epoch": 1.0838709677419356,
      "grad_norm": 6.853363990783691,
      "learning_rate": 4.620120240391065e-06,
      "loss": 0.0723,
      "num_input_tokens_seen": 267072,
      "step": 42
    },
    {
      "epoch": 1.1096774193548387,
      "grad_norm": 5.992878437042236,
      "learning_rate": 4.596676419863561e-06,
      "loss": 0.0726,
      "num_input_tokens_seen": 273392,
      "step": 43
    },
    {
      "epoch": 1.135483870967742,
      "grad_norm": 11.17392349243164,
      "learning_rate": 4.572593931387604e-06,
      "loss": 0.1355,
      "num_input_tokens_seen": 279680,
      "step": 44
    },
    {
      "epoch": 1.1612903225806452,
      "grad_norm": 5.068784236907959,
      "learning_rate": 4.54788011072248e-06,
      "loss": 0.0713,
      "num_input_tokens_seen": 285968,
      "step": 45
    },
    {
      "epoch": 1.1870967741935483,
      "grad_norm": 4.72653865814209,
      "learning_rate": 4.522542485937369e-06,
      "loss": 0.0796,
      "num_input_tokens_seen": 292304,
      "step": 46
    },
    {
      "epoch": 1.2129032258064516,
      "grad_norm": 9.032431602478027,
      "learning_rate": 4.496588775118232e-06,
      "loss": 0.0778,
      "num_input_tokens_seen": 298608,
      "step": 47
    },
    {
      "epoch": 1.238709677419355,
      "grad_norm": 9.944851875305176,
      "learning_rate": 4.470026884016805e-06,
      "loss": 0.0606,
      "num_input_tokens_seen": 304912,
      "step": 48
    },
    {
      "epoch": 1.2645161290322582,
      "grad_norm": 4.149289608001709,
      "learning_rate": 4.442864903642428e-06,
      "loss": 0.0411,
      "num_input_tokens_seen": 311328,
      "step": 49
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": 9.92379093170166,
      "learning_rate": 4.415111107797445e-06,
      "loss": 0.0773,
      "num_input_tokens_seen": 317664,
      "step": 50
    },
    {
      "epoch": 1.3161290322580645,
      "grad_norm": 7.274410247802734,
      "learning_rate": 4.386773950556931e-06,
      "loss": 0.0355,
      "num_input_tokens_seen": 324128,
      "step": 51
    },
    {
      "epoch": 1.3419354838709676,
      "grad_norm": 8.456096649169922,
      "learning_rate": 4.357862063693486e-06,
      "loss": 0.0607,
      "num_input_tokens_seen": 330304,
      "step": 52
    },
    {
      "epoch": 1.367741935483871,
      "grad_norm": 6.24631404876709,
      "learning_rate": 4.328384254047927e-06,
      "loss": 0.0542,
      "num_input_tokens_seen": 336608,
      "step": 53
    },
    {
      "epoch": 1.3935483870967742,
      "grad_norm": 8.23633098602295,
      "learning_rate": 4.2983495008466285e-06,
      "loss": 0.0629,
      "num_input_tokens_seen": 342944,
      "step": 54
    },
    {
      "epoch": 1.4193548387096775,
      "grad_norm": 7.366152763366699,
      "learning_rate": 4.267766952966369e-06,
      "loss": 0.0519,
      "num_input_tokens_seen": 349504,
      "step": 55
    },
    {
      "epoch": 1.4451612903225808,
      "grad_norm": 4.767688751220703,
      "learning_rate": 4.236645926147493e-06,
      "loss": 0.0481,
      "num_input_tokens_seen": 355808,
      "step": 56
    },
    {
      "epoch": 1.4709677419354839,
      "grad_norm": 6.601537227630615,
      "learning_rate": 4.204995900156247e-06,
      "loss": 0.0659,
      "num_input_tokens_seen": 362144,
      "step": 57
    },
    {
      "epoch": 1.4967741935483871,
      "grad_norm": 12.549847602844238,
      "learning_rate": 4.172826515897146e-06,
      "loss": 0.098,
      "num_input_tokens_seen": 368800,
      "step": 58
    },
    {
      "epoch": 1.5225806451612902,
      "grad_norm": 4.087855339050293,
      "learning_rate": 4.140147572476269e-06,
      "loss": 0.0411,
      "num_input_tokens_seen": 375264,
      "step": 59
    },
    {
      "epoch": 1.5483870967741935,
      "grad_norm": 5.732005596160889,
      "learning_rate": 4.106969024216348e-06,
      "loss": 0.0396,
      "num_input_tokens_seen": 381408,
      "step": 60
    },
    {
      "epoch": 1.5741935483870968,
      "grad_norm": 4.3451361656188965,
      "learning_rate": 4.073300977624594e-06,
      "loss": 0.0413,
      "num_input_tokens_seen": 387552,
      "step": 61
    },
    {
      "epoch": 1.6,
      "grad_norm": 10.537796974182129,
      "learning_rate": 4.039153688314146e-06,
      "loss": 0.1195,
      "num_input_tokens_seen": 394128,
      "step": 62
    },
    {
      "epoch": 1.6258064516129034,
      "grad_norm": 5.795935153961182,
      "learning_rate": 4.0045375578801216e-06,
      "loss": 0.0534,
      "num_input_tokens_seen": 400512,
      "step": 63
    },
    {
      "epoch": 1.6516129032258065,
      "grad_norm": 3.5450239181518555,
      "learning_rate": 3.969463130731183e-06,
      "loss": 0.0662,
      "num_input_tokens_seen": 406752,
      "step": 64
    },
    {
      "epoch": 1.6774193548387095,
      "grad_norm": 3.7263312339782715,
      "learning_rate": 3.933941090877615e-06,
      "loss": 0.0462,
      "num_input_tokens_seen": 413040,
      "step": 65
    },
    {
      "epoch": 1.7032258064516128,
      "grad_norm": 14.24105453491211,
      "learning_rate": 3.897982258676867e-06,
      "loss": 0.0899,
      "num_input_tokens_seen": 419408,
      "step": 66
    },
    {
      "epoch": 1.729032258064516,
      "grad_norm": 11.823075294494629,
      "learning_rate": 3.861597587537568e-06,
      "loss": 0.0691,
      "num_input_tokens_seen": 425920,
      "step": 67
    },
    {
      "epoch": 1.7548387096774194,
      "grad_norm": 8.369593620300293,
      "learning_rate": 3.824798160583012e-06,
      "loss": 0.1022,
      "num_input_tokens_seen": 432400,
      "step": 68
    },
    {
      "epoch": 1.7806451612903227,
      "grad_norm": 11.862183570861816,
      "learning_rate": 3.787595187275136e-06,
      "loss": 0.1062,
      "num_input_tokens_seen": 438688,
      "step": 69
    },
    {
      "epoch": 1.8064516129032258,
      "grad_norm": 6.197830677032471,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.0491,
      "num_input_tokens_seen": 445280,
      "step": 70
    },
    {
      "epoch": 1.832258064516129,
      "grad_norm": 12.781743049621582,
      "learning_rate": 3.7120240506158433e-06,
      "loss": 0.1507,
      "num_input_tokens_seen": 451616,
      "step": 71
    },
    {
      "epoch": 1.8580645161290321,
      "grad_norm": 8.9237699508667,
      "learning_rate": 3.6736789069647273e-06,
      "loss": 0.1234,
      "num_input_tokens_seen": 457856,
      "step": 72
    },
    {
      "epoch": 1.8838709677419354,
      "grad_norm": 4.439033031463623,
      "learning_rate": 3.634976249348867e-06,
      "loss": 0.045,
      "num_input_tokens_seen": 464144,
      "step": 73
    },
    {
      "epoch": 1.9096774193548387,
      "grad_norm": 6.061345100402832,
      "learning_rate": 3.595927866972694e-06,
      "loss": 0.0615,
      "num_input_tokens_seen": 470736,
      "step": 74
    },
    {
      "epoch": 1.935483870967742,
      "grad_norm": 20.429502487182617,
      "learning_rate": 3.556545654351749e-06,
      "loss": 0.1961,
      "num_input_tokens_seen": 477168,
      "step": 75
    },
    {
      "epoch": 1.9612903225806453,
      "grad_norm": 21.598663330078125,
      "learning_rate": 3.516841607689501e-06,
      "loss": 0.2311,
      "num_input_tokens_seen": 483536,
      "step": 76
    },
    {
      "epoch": 1.9870967741935484,
      "grad_norm": 19.673458099365234,
      "learning_rate": 3.476827821223184e-06,
      "loss": 0.1556,
      "num_input_tokens_seen": 489760,
      "step": 77
    },
    {
      "epoch": 2.0129032258064514,
      "grad_norm": 10.228775978088379,
      "learning_rate": 3.436516483539781e-06,
      "loss": 0.0626,
      "num_input_tokens_seen": 496000,
      "step": 78
    },
    {
      "epoch": 2.0387096774193547,
      "grad_norm": 2.8426713943481445,
      "learning_rate": 3.39591987386325e-06,
      "loss": 0.0197,
      "num_input_tokens_seen": 502384,
      "step": 79
    },
    {
      "epoch": 2.064516129032258,
      "grad_norm": 1.3634212017059326,
      "learning_rate": 3.3550503583141726e-06,
      "loss": 0.0057,
      "num_input_tokens_seen": 508992,
      "step": 80
    },
    {
      "epoch": 2.0903225806451613,
      "grad_norm": 4.306141376495361,
      "learning_rate": 3.313920386142892e-06,
      "loss": 0.029,
      "num_input_tokens_seen": 515216,
      "step": 81
    },
    {
      "epoch": 2.1161290322580646,
      "grad_norm": 6.760740756988525,
      "learning_rate": 3.272542485937369e-06,
      "loss": 0.0593,
      "num_input_tokens_seen": 521792,
      "step": 82
    },
    {
      "epoch": 2.141935483870968,
      "grad_norm": 6.014277935028076,
      "learning_rate": 3.230929261806842e-06,
      "loss": 0.0455,
      "num_input_tokens_seen": 528176,
      "step": 83
    },
    {
      "epoch": 2.167741935483871,
      "grad_norm": 4.916089057922363,
      "learning_rate": 3.189093389542498e-06,
      "loss": 0.0325,
      "num_input_tokens_seen": 534496,
      "step": 84
    },
    {
      "epoch": 2.193548387096774,
      "grad_norm": 3.420660972595215,
      "learning_rate": 3.147047612756302e-06,
      "loss": 0.0071,
      "num_input_tokens_seen": 541024,
      "step": 85
    },
    {
      "epoch": 2.2193548387096773,
      "grad_norm": 9.941604614257812,
      "learning_rate": 3.1048047389991693e-06,
      "loss": 0.0336,
      "num_input_tokens_seen": 547328,
      "step": 86
    },
    {
      "epoch": 2.2451612903225806,
      "grad_norm": 3.6986887454986572,
      "learning_rate": 3.062377635859663e-06,
      "loss": 0.0389,
      "num_input_tokens_seen": 553760,
      "step": 87
    },
    {
      "epoch": 2.270967741935484,
      "grad_norm": 0.8903897404670715,
      "learning_rate": 3.019779227044398e-06,
      "loss": 0.0016,
      "num_input_tokens_seen": 560048,
      "step": 88
    },
    {
      "epoch": 2.296774193548387,
      "grad_norm": 3.993572473526001,
      "learning_rate": 2.9770224884413625e-06,
      "loss": 0.0625,
      "num_input_tokens_seen": 566624,
      "step": 89
    },
    {
      "epoch": 2.3225806451612905,
      "grad_norm": 5.582505702972412,
      "learning_rate": 2.9341204441673267e-06,
      "loss": 0.0201,
      "num_input_tokens_seen": 572864,
      "step": 90
    },
    {
      "epoch": 2.3483870967741938,
      "grad_norm": 3.705141305923462,
      "learning_rate": 2.8910861626005774e-06,
      "loss": 0.0126,
      "num_input_tokens_seen": 579024,
      "step": 91
    },
    {
      "epoch": 2.3741935483870966,
      "grad_norm": 2.028670072555542,
      "learning_rate": 2.847932752400164e-06,
      "loss": 0.0148,
      "num_input_tokens_seen": 585536,
      "step": 92
    },
    {
      "epoch": 2.4,
      "grad_norm": 3.1567721366882324,
      "learning_rate": 2.804673358512869e-06,
      "loss": 0.014,
      "num_input_tokens_seen": 591792,
      "step": 93
    },
    {
      "epoch": 2.425806451612903,
      "grad_norm": 2.679948329925537,
      "learning_rate": 2.761321158169134e-06,
      "loss": 0.0096,
      "num_input_tokens_seen": 598144,
      "step": 94
    },
    {
      "epoch": 2.4516129032258065,
      "grad_norm": 4.910022258758545,
      "learning_rate": 2.717889356869146e-06,
      "loss": 0.0249,
      "num_input_tokens_seen": 604496,
      "step": 95
    },
    {
      "epoch": 2.47741935483871,
      "grad_norm": 3.3921937942504883,
      "learning_rate": 2.6743911843603134e-06,
      "loss": 0.0358,
      "num_input_tokens_seen": 610784,
      "step": 96
    },
    {
      "epoch": 2.5032258064516126,
      "grad_norm": 7.016202926635742,
      "learning_rate": 2.6308398906073603e-06,
      "loss": 0.0494,
      "num_input_tokens_seen": 617024,
      "step": 97
    },
    {
      "epoch": 2.5290322580645164,
      "grad_norm": 2.0283963680267334,
      "learning_rate": 2.587248741756253e-06,
      "loss": 0.0092,
      "num_input_tokens_seen": 623312,
      "step": 98
    },
    {
      "epoch": 2.554838709677419,
      "grad_norm": 3.0168426036834717,
      "learning_rate": 2.543631016093209e-06,
      "loss": 0.0215,
      "num_input_tokens_seen": 629616,
      "step": 99
    },
    {
      "epoch": 2.5806451612903225,
      "grad_norm": 1.7446969747543335,
      "learning_rate": 2.5e-06,
      "loss": 0.0122,
      "num_input_tokens_seen": 636144,
      "step": 100
    },
    {
      "epoch": 2.606451612903226,
      "grad_norm": 5.639215469360352,
      "learning_rate": 2.4563689839067913e-06,
      "loss": 0.0296,
      "num_input_tokens_seen": 642496,
      "step": 101
    },
    {
      "epoch": 2.632258064516129,
      "grad_norm": 2.9085285663604736,
      "learning_rate": 2.4127512582437486e-06,
      "loss": 0.0089,
      "num_input_tokens_seen": 648912,
      "step": 102
    },
    {
      "epoch": 2.6580645161290324,
      "grad_norm": 5.7294182777404785,
      "learning_rate": 2.3691601093926406e-06,
      "loss": 0.0406,
      "num_input_tokens_seen": 655088,
      "step": 103
    },
    {
      "epoch": 2.6838709677419352,
      "grad_norm": 2.689070463180542,
      "learning_rate": 2.325608815639687e-06,
      "loss": 0.0114,
      "num_input_tokens_seen": 661680,
      "step": 104
    },
    {
      "epoch": 2.709677419354839,
      "grad_norm": 6.133366584777832,
      "learning_rate": 2.2821106431308546e-06,
      "loss": 0.0396,
      "num_input_tokens_seen": 668016,
      "step": 105
    },
    {
      "epoch": 2.735483870967742,
      "grad_norm": 2.75050687789917,
      "learning_rate": 2.238678841830867e-06,
      "loss": 0.0077,
      "num_input_tokens_seen": 674176,
      "step": 106
    },
    {
      "epoch": 2.761290322580645,
      "grad_norm": 1.4048194885253906,
      "learning_rate": 2.195326641487132e-06,
      "loss": 0.0044,
      "num_input_tokens_seen": 680464,
      "step": 107
    },
    {
      "epoch": 2.7870967741935484,
      "grad_norm": 1.6331162452697754,
      "learning_rate": 2.1520672475998374e-06,
      "loss": 0.0045,
      "num_input_tokens_seen": 686688,
      "step": 108
    },
    {
      "epoch": 2.8129032258064517,
      "grad_norm": 7.9665045738220215,
      "learning_rate": 2.1089138373994226e-06,
      "loss": 0.0405,
      "num_input_tokens_seen": 692992,
      "step": 109
    },
    {
      "epoch": 2.838709677419355,
      "grad_norm": 1.685049295425415,
      "learning_rate": 2.0658795558326745e-06,
      "loss": 0.0225,
      "num_input_tokens_seen": 699392,
      "step": 110
    },
    {
      "epoch": 2.864516129032258,
      "grad_norm": 7.692150115966797,
      "learning_rate": 2.022977511558638e-06,
      "loss": 0.0415,
      "num_input_tokens_seen": 705680,
      "step": 111
    },
    {
      "epoch": 2.8903225806451616,
      "grad_norm": 3.878633499145508,
      "learning_rate": 1.9802207729556023e-06,
      "loss": 0.0173,
      "num_input_tokens_seen": 711952,
      "step": 112
    },
    {
      "epoch": 2.9161290322580644,
      "grad_norm": 0.16839256882667542,
      "learning_rate": 1.937622364140338e-06,
      "loss": 0.0005,
      "num_input_tokens_seen": 718192,
      "step": 113
    },
    {
      "epoch": 2.9419354838709677,
      "grad_norm": 11.416730880737305,
      "learning_rate": 1.895195261000831e-06,
      "loss": 0.0306,
      "num_input_tokens_seen": 724832,
      "step": 114
    },
    {
      "epoch": 2.967741935483871,
      "grad_norm": 7.409735679626465,
      "learning_rate": 1.852952387243698e-06,
      "loss": 0.0422,
      "num_input_tokens_seen": 731312,
      "step": 115
    },
    {
      "epoch": 2.9935483870967743,
      "grad_norm": 10.997987747192383,
      "learning_rate": 1.8109066104575023e-06,
      "loss": 0.0472,
      "num_input_tokens_seen": 737488,
      "step": 116
    },
    {
      "epoch": 3.0193548387096776,
      "grad_norm": 3.9862027168273926,
      "learning_rate": 1.7690707381931585e-06,
      "loss": 0.0259,
      "num_input_tokens_seen": 743760,
      "step": 117
    },
    {
      "epoch": 3.0451612903225804,
      "grad_norm": 1.2078546285629272,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 0.0029,
      "num_input_tokens_seen": 750048,
      "step": 118
    },
    {
      "epoch": 3.0709677419354837,
      "grad_norm": 2.100956916809082,
      "learning_rate": 1.686079613857109e-06,
      "loss": 0.035,
      "num_input_tokens_seen": 756400,
      "step": 119
    },
    {
      "epoch": 3.096774193548387,
      "grad_norm": 0.5347418785095215,
      "learning_rate": 1.6449496416858285e-06,
      "loss": 0.0015,
      "num_input_tokens_seen": 762432,
      "step": 120
    },
    {
      "epoch": 3.1225806451612903,
      "grad_norm": 0.09030436724424362,
      "learning_rate": 1.6040801261367494e-06,
      "loss": 0.0006,
      "num_input_tokens_seen": 768688,
      "step": 121
    },
    {
      "epoch": 3.1483870967741936,
      "grad_norm": 1.5785781145095825,
      "learning_rate": 1.56348351646022e-06,
      "loss": 0.0143,
      "num_input_tokens_seen": 775024,
      "step": 122
    },
    {
      "epoch": 3.174193548387097,
      "grad_norm": 3.521341562271118,
      "learning_rate": 1.5231721787768162e-06,
      "loss": 0.0219,
      "num_input_tokens_seen": 781360,
      "step": 123
    },
    {
      "epoch": 3.2,
      "grad_norm": 1.1369749307632446,
      "learning_rate": 1.4831583923105e-06,
      "loss": 0.0074,
      "num_input_tokens_seen": 787888,
      "step": 124
    },
    {
      "epoch": 3.225806451612903,
      "grad_norm": 1.8700661659240723,
      "learning_rate": 1.443454345648252e-06,
      "loss": 0.0052,
      "num_input_tokens_seen": 794112,
      "step": 125
    },
    {
      "epoch": 3.2516129032258063,
      "grad_norm": 0.2537897527217865,
      "learning_rate": 1.4040721330273063e-06,
      "loss": 0.0013,
      "num_input_tokens_seen": 800384,
      "step": 126
    },
    {
      "epoch": 3.2774193548387096,
      "grad_norm": 0.5774049162864685,
      "learning_rate": 1.3650237506511333e-06,
      "loss": 0.0018,
      "num_input_tokens_seen": 806848,
      "step": 127
    },
    {
      "epoch": 3.303225806451613,
      "grad_norm": 3.956850528717041,
      "learning_rate": 1.3263210930352737e-06,
      "loss": 0.0077,
      "num_input_tokens_seen": 813136,
      "step": 128
    },
    {
      "epoch": 3.329032258064516,
      "grad_norm": 1.5908522605895996,
      "learning_rate": 1.2879759493841577e-06,
      "loss": 0.0138,
      "num_input_tokens_seen": 819504,
      "step": 129
    },
    {
      "epoch": 3.3548387096774195,
      "grad_norm": 2.6174991130828857,
      "learning_rate": 1.2500000000000007e-06,
      "loss": 0.0102,
      "num_input_tokens_seen": 825936,
      "step": 130
    },
    {
      "epoch": 3.3806451612903228,
      "grad_norm": 0.6057196259498596,
      "learning_rate": 1.2124048127248644e-06,
      "loss": 0.0067,
      "num_input_tokens_seen": 832496,
      "step": 131
    },
    {
      "epoch": 3.4064516129032256,
      "grad_norm": 0.7317366003990173,
      "learning_rate": 1.1752018394169882e-06,
      "loss": 0.0056,
      "num_input_tokens_seen": 838864,
      "step": 132
    },
    {
      "epoch": 3.432258064516129,
      "grad_norm": 0.7846810817718506,
      "learning_rate": 1.1384024124624324e-06,
      "loss": 0.0066,
      "num_input_tokens_seen": 845504,
      "step": 133
    },
    {
      "epoch": 3.458064516129032,
      "grad_norm": 1.7466976642608643,
      "learning_rate": 1.1020177413231334e-06,
      "loss": 0.0033,
      "num_input_tokens_seen": 851888,
      "step": 134
    },
    {
      "epoch": 3.4838709677419355,
      "grad_norm": 0.22806118428707123,
      "learning_rate": 1.0660589091223854e-06,
      "loss": 0.0008,
      "num_input_tokens_seen": 858144,
      "step": 135
    },
    {
      "epoch": 3.509677419354839,
      "grad_norm": 1.3712356090545654,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 0.0027,
      "num_input_tokens_seen": 864496,
      "step": 136
    },
    {
      "epoch": 3.535483870967742,
      "grad_norm": 1.6921025514602661,
      "learning_rate": 9.95462442119879e-07,
      "loss": 0.0021,
      "num_input_tokens_seen": 870672,
      "step": 137
    },
    {
      "epoch": 3.5612903225806454,
      "grad_norm": 0.22363713383674622,
      "learning_rate": 9.608463116858544e-07,
      "loss": 0.0008,
      "num_input_tokens_seen": 876944,
      "step": 138
    },
    {
      "epoch": 3.587096774193548,
      "grad_norm": 0.9099496603012085,
      "learning_rate": 9.266990223754069e-07,
      "loss": 0.0051,
      "num_input_tokens_seen": 883488,
      "step": 139
    },
    {
      "epoch": 3.6129032258064515,
      "grad_norm": 1.2267215251922607,
      "learning_rate": 8.930309757836517e-07,
      "loss": 0.0026,
      "num_input_tokens_seen": 889824,
      "step": 140
    },
    {
      "epoch": 3.638709677419355,
      "grad_norm": 1.089577317237854,
      "learning_rate": 8.598524275237321e-07,
      "loss": 0.0041,
      "num_input_tokens_seen": 896176,
      "step": 141
    },
    {
      "epoch": 3.664516129032258,
      "grad_norm": 4.791709899902344,
      "learning_rate": 8.271734841028553e-07,
      "loss": 0.023,
      "num_input_tokens_seen": 902272,
      "step": 142
    },
    {
      "epoch": 3.6903225806451614,
      "grad_norm": 1.1492427587509155,
      "learning_rate": 7.950040998437541e-07,
      "loss": 0.0106,
      "num_input_tokens_seen": 908512,
      "step": 143
    },
    {
      "epoch": 3.7161290322580647,
      "grad_norm": 1.7846548557281494,
      "learning_rate": 7.633540738525066e-07,
      "loss": 0.0238,
      "num_input_tokens_seen": 915152,
      "step": 144
    },
    {
      "epoch": 3.741935483870968,
      "grad_norm": 1.1331474781036377,
      "learning_rate": 7.322330470336314e-07,
      "loss": 0.0088,
      "num_input_tokens_seen": 921552,
      "step": 145
    },
    {
      "epoch": 3.767741935483871,
      "grad_norm": 3.830028772354126,
      "learning_rate": 7.016504991533727e-07,
      "loss": 0.0391,
      "num_input_tokens_seen": 928048,
      "step": 146
    },
    {
      "epoch": 3.793548387096774,
      "grad_norm": 0.4352247714996338,
      "learning_rate": 6.716157459520739e-07,
      "loss": 0.0008,
      "num_input_tokens_seen": 934512,
      "step": 147
    },
    {
      "epoch": 3.8193548387096774,
      "grad_norm": 2.370004892349243,
      "learning_rate": 6.421379363065142e-07,
      "loss": 0.0177,
      "num_input_tokens_seen": 940816,
      "step": 148
    },
    {
      "epoch": 3.8451612903225807,
      "grad_norm": 0.025743747130036354,
      "learning_rate": 6.1322604944307e-07,
      "loss": 0.0001,
      "num_input_tokens_seen": 946992,
      "step": 149
    },
    {
      "epoch": 3.870967741935484,
      "grad_norm": 0.05237932130694389,
      "learning_rate": 5.848888922025553e-07,
      "loss": 0.0002,
      "num_input_tokens_seen": 953424,
      "step": 150
    },
    {
      "epoch": 3.896774193548387,
      "grad_norm": 1.3190343379974365,
      "learning_rate": 5.571350963575728e-07,
      "loss": 0.0044,
      "num_input_tokens_seen": 959616,
      "step": 151
    },
    {
      "epoch": 3.9225806451612906,
      "grad_norm": 0.6631452441215515,
      "learning_rate": 5.299731159831953e-07,
      "loss": 0.0015,
      "num_input_tokens_seen": 966096,
      "step": 152
    },
    {
      "epoch": 3.9483870967741934,
      "grad_norm": 0.0852465108036995,
      "learning_rate": 5.034112248817685e-07,
      "loss": 0.0003,
      "num_input_tokens_seen": 972368,
      "step": 153
    },
    {
      "epoch": 3.9741935483870967,
      "grad_norm": 3.415978193283081,
      "learning_rate": 4.774575140626317e-07,
      "loss": 0.0361,
      "num_input_tokens_seen": 978848,
      "step": 154
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.18466639518737793,
      "learning_rate": 4.5211988927752026e-07,
      "loss": 0.0005,
      "num_input_tokens_seen": 985520,
      "step": 155
    },
    {
      "epoch": 4.025806451612903,
      "grad_norm": 0.411256343126297,
      "learning_rate": 4.27406068612396e-07,
      "loss": 0.0022,
      "num_input_tokens_seen": 991904,
      "step": 156
    },
    {
      "epoch": 4.051612903225807,
      "grad_norm": 4.388174533843994,
      "learning_rate": 4.033235801364402e-07,
      "loss": 0.0212,
      "num_input_tokens_seen": 998288,
      "step": 157
    },
    {
      "epoch": 4.077419354838709,
      "grad_norm": 0.09413906931877136,
      "learning_rate": 3.798797596089351e-07,
      "loss": 0.0003,
      "num_input_tokens_seen": 1004432,
      "step": 158
    },
    {
      "epoch": 4.103225806451613,
      "grad_norm": 0.31842732429504395,
      "learning_rate": 3.5708174824471947e-07,
      "loss": 0.0047,
      "num_input_tokens_seen": 1010608,
      "step": 159
    },
    {
      "epoch": 4.129032258064516,
      "grad_norm": 0.2919209599494934,
      "learning_rate": 3.3493649053890325e-07,
      "loss": 0.0014,
      "num_input_tokens_seen": 1016848,
      "step": 160
    },
    {
      "epoch": 4.15483870967742,
      "grad_norm": 0.2236456423997879,
      "learning_rate": 3.134507321515107e-07,
      "loss": 0.0006,
      "num_input_tokens_seen": 1023360,
      "step": 161
    },
    {
      "epoch": 4.180645161290323,
      "grad_norm": 0.10099940747022629,
      "learning_rate": 2.9263101785268253e-07,
      "loss": 0.0003,
      "num_input_tokens_seen": 1029808,
      "step": 162
    },
    {
      "epoch": 4.2064516129032254,
      "grad_norm": 0.7959046363830566,
      "learning_rate": 2.7248368952908055e-07,
      "loss": 0.0021,
      "num_input_tokens_seen": 1036080,
      "step": 163
    },
    {
      "epoch": 4.232258064516129,
      "grad_norm": 0.027844589203596115,
      "learning_rate": 2.53014884252083e-07,
      "loss": 0.0001,
      "num_input_tokens_seen": 1042240,
      "step": 164
    },
    {
      "epoch": 4.258064516129032,
      "grad_norm": 0.1852904111146927,
      "learning_rate": 2.3423053240837518e-07,
      "loss": 0.0007,
      "num_input_tokens_seen": 1048672,
      "step": 165
    },
    {
      "epoch": 4.283870967741936,
      "grad_norm": 0.30857357382774353,
      "learning_rate": 2.1613635589349756e-07,
      "loss": 0.0013,
      "num_input_tokens_seen": 1054832,
      "step": 166
    },
    {
      "epoch": 4.309677419354839,
      "grad_norm": 0.06834129244089127,
      "learning_rate": 1.9873786636889908e-07,
      "loss": 0.0002,
      "num_input_tokens_seen": 1061312,
      "step": 167
    },
    {
      "epoch": 4.335483870967742,
      "grad_norm": 0.2285776287317276,
      "learning_rate": 1.8204036358303173e-07,
      "loss": 0.0011,
      "num_input_tokens_seen": 1067488,
      "step": 168
    },
    {
      "epoch": 4.361290322580645,
      "grad_norm": 0.0340169332921505,
      "learning_rate": 1.6604893375699594e-07,
      "loss": 0.0001,
      "num_input_tokens_seen": 1073648,
      "step": 169
    },
    {
      "epoch": 4.387096774193548,
      "grad_norm": 0.19227157533168793,
      "learning_rate": 1.507684480352292e-07,
      "loss": 0.0006,
      "num_input_tokens_seen": 1080160,
      "step": 170
    },
    {
      "epoch": 4.412903225806452,
      "grad_norm": 0.071542888879776,
      "learning_rate": 1.362035610017079e-07,
      "loss": 0.0003,
      "num_input_tokens_seen": 1086832,
      "step": 171
    },
    {
      "epoch": 4.438709677419355,
      "grad_norm": 0.03672094643115997,
      "learning_rate": 1.223587092621162e-07,
      "loss": 0.0002,
      "num_input_tokens_seen": 1093184,
      "step": 172
    },
    {
      "epoch": 4.464516129032258,
      "grad_norm": 0.5119577646255493,
      "learning_rate": 1.0923811009241142e-07,
      "loss": 0.0027,
      "num_input_tokens_seen": 1099728,
      "step": 173
    },
    {
      "epoch": 4.490322580645161,
      "grad_norm": 0.04045412689447403,
      "learning_rate": 9.684576015420277e-08,
      "loss": 0.0002,
      "num_input_tokens_seen": 1106032,
      "step": 174
    },
    {
      "epoch": 4.516129032258064,
      "grad_norm": 0.02040756493806839,
      "learning_rate": 8.518543427732951e-08,
      "loss": 0.0001,
      "num_input_tokens_seen": 1112496,
      "step": 175
    },
    {
      "epoch": 4.541935483870968,
      "grad_norm": 1.3152027130126953,
      "learning_rate": 7.426068431000883e-08,
      "loss": 0.0109,
      "num_input_tokens_seen": 1119152,
      "step": 176
    },
    {
      "epoch": 4.567741935483871,
      "grad_norm": 0.6810739636421204,
      "learning_rate": 6.407483803691216e-08,
      "loss": 0.0039,
      "num_input_tokens_seen": 1125360,
      "step": 177
    },
    {
      "epoch": 4.593548387096774,
      "grad_norm": 0.567620575428009,
      "learning_rate": 5.463099816548578e-08,
      "loss": 0.0026,
      "num_input_tokens_seen": 1131824,
      "step": 178
    },
    {
      "epoch": 4.619354838709677,
      "grad_norm": 0.04240654036402702,
      "learning_rate": 4.593204138084006e-08,
      "loss": 0.0002,
      "num_input_tokens_seen": 1138224,
      "step": 179
    },
    {
      "epoch": 4.645161290322581,
      "grad_norm": 0.46607980132102966,
      "learning_rate": 3.798061746947995e-08,
      "loss": 0.0044,
      "num_input_tokens_seen": 1144528,
      "step": 180
    },
    {
      "epoch": 4.670967741935484,
      "grad_norm": 0.053230661898851395,
      "learning_rate": 3.077914851215585e-08,
      "loss": 0.0001,
      "num_input_tokens_seen": 1150880,
      "step": 181
    },
    {
      "epoch": 4.6967741935483875,
      "grad_norm": 5.332281112670898,
      "learning_rate": 2.4329828146074096e-08,
      "loss": 0.0103,
      "num_input_tokens_seen": 1157184,
      "step": 182
    },
    {
      "epoch": 4.72258064516129,
      "grad_norm": 0.3008340001106262,
      "learning_rate": 1.8634620896695044e-08,
      "loss": 0.0002,
      "num_input_tokens_seen": 1163536,
      "step": 183
    },
    {
      "epoch": 4.748387096774193,
      "grad_norm": 0.7082801461219788,
      "learning_rate": 1.3695261579316776e-08,
      "loss": 0.0038,
      "num_input_tokens_seen": 1169888,
      "step": 184
    },
    {
      "epoch": 4.774193548387097,
      "grad_norm": 0.7764519453048706,
      "learning_rate": 9.513254770636138e-09,
      "loss": 0.0039,
      "num_input_tokens_seen": 1176400,
      "step": 185
    },
    {
      "epoch": 4.8,
      "grad_norm": 0.19201423227787018,
      "learning_rate": 6.089874350439507e-09,
      "loss": 0.0005,
      "num_input_tokens_seen": 1182608,
      "step": 186
    },
    {
      "epoch": 4.825806451612904,
      "grad_norm": 0.03770337998867035,
      "learning_rate": 3.4261631135654174e-09,
      "loss": 0.0002,
      "num_input_tokens_seen": 1189008,
      "step": 187
    },
    {
      "epoch": 4.851612903225806,
      "grad_norm": 0.26141980290412903,
      "learning_rate": 1.5229324522605949e-09,
      "loss": 0.0011,
      "num_input_tokens_seen": 1195280,
      "step": 188
    },
    {
      "epoch": 4.877419354838709,
      "grad_norm": 0.19117940962314606,
      "learning_rate": 3.8076210902182607e-10,
      "loss": 0.0007,
      "num_input_tokens_seen": 1201456,
      "step": 189
    },
    {
      "epoch": 4.903225806451613,
      "grad_norm": 0.11188680678606033,
      "learning_rate": 0.0,
      "loss": 0.0002,
      "num_input_tokens_seen": 1207760,
      "step": 190
    },
    {
      "epoch": 4.903225806451613,
      "num_input_tokens_seen": 1207760,
      "step": 190,
      "total_flos": 5.438488809413018e+16,
      "train_loss": 0.4546951471592796,
      "train_runtime": 2562.7617,
      "train_samples_per_second": 9.673,
      "train_steps_per_second": 0.074
    }
  ],
  "logging_steps": 1,
  "max_steps": 190,
  "num_input_tokens_seen": 1207760,
  "num_train_epochs": 5,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.438488809413018e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}