{
  "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": 276.5378112792969,
      "learning_rate": 5.000000000000001e-07,
      "loss": 8.2514,
      "num_input_tokens_seen": 6848,
      "step": 1
    },
    {
      "epoch": 0.05161290322580645,
      "grad_norm": 294.3509521484375,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 8.2793,
      "num_input_tokens_seen": 13776,
      "step": 2
    },
    {
      "epoch": 0.07741935483870968,
      "grad_norm": 283.4303283691406,
      "learning_rate": 1.5e-06,
      "loss": 8.17,
      "num_input_tokens_seen": 20672,
      "step": 3
    },
    {
      "epoch": 0.1032258064516129,
      "grad_norm": 285.55255126953125,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 7.6197,
      "num_input_tokens_seen": 27744,
      "step": 4
    },
    {
      "epoch": 0.12903225806451613,
      "grad_norm": 271.7382507324219,
      "learning_rate": 2.5e-06,
      "loss": 6.9491,
      "num_input_tokens_seen": 34624,
      "step": 5
    },
    {
      "epoch": 0.15483870967741936,
      "grad_norm": 125.66632080078125,
      "learning_rate": 3e-06,
      "loss": 5.2054,
      "num_input_tokens_seen": 41424,
      "step": 6
    },
    {
      "epoch": 0.18064516129032257,
      "grad_norm": 113.50272369384766,
      "learning_rate": 3.5e-06,
      "loss": 4.8642,
      "num_input_tokens_seen": 48304,
      "step": 7
    },
    {
      "epoch": 0.2064516129032258,
      "grad_norm": 113.24736785888672,
      "learning_rate": 4.000000000000001e-06,
      "loss": 3.2874,
      "num_input_tokens_seen": 55152,
      "step": 8
    },
    {
      "epoch": 0.23225806451612904,
      "grad_norm": 117.07583618164062,
      "learning_rate": 4.5e-06,
      "loss": 2.631,
      "num_input_tokens_seen": 61680,
      "step": 9
    },
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 113.77539825439453,
      "learning_rate": 5e-06,
      "loss": 0.6982,
      "num_input_tokens_seen": 68480,
      "step": 10
    },
    {
      "epoch": 0.2838709677419355,
      "grad_norm": 36.774471282958984,
      "learning_rate": 4.9996192378909785e-06,
      "loss": 0.3276,
      "num_input_tokens_seen": 75296,
      "step": 11
    },
    {
      "epoch": 0.3096774193548387,
      "grad_norm": 33.21468734741211,
      "learning_rate": 4.99847706754774e-06,
      "loss": 0.293,
      "num_input_tokens_seen": 82288,
      "step": 12
    },
    {
      "epoch": 0.33548387096774196,
      "grad_norm": 5.65634822845459,
      "learning_rate": 4.9965738368864345e-06,
      "loss": 0.2129,
      "num_input_tokens_seen": 89088,
      "step": 13
    },
    {
      "epoch": 0.36129032258064514,
      "grad_norm": 55.87510299682617,
      "learning_rate": 4.993910125649561e-06,
      "loss": 0.4712,
      "num_input_tokens_seen": 95904,
      "step": 14
    },
    {
      "epoch": 0.3870967741935484,
      "grad_norm": 31.815500259399414,
      "learning_rate": 4.990486745229364e-06,
      "loss": 0.235,
      "num_input_tokens_seen": 102896,
      "step": 15
    },
    {
      "epoch": 0.4129032258064516,
      "grad_norm": 10.451783180236816,
      "learning_rate": 4.986304738420684e-06,
      "loss": 0.202,
      "num_input_tokens_seen": 109792,
      "step": 16
    },
    {
      "epoch": 0.43870967741935485,
      "grad_norm": 21.014144897460938,
      "learning_rate": 4.981365379103306e-06,
      "loss": 0.1981,
      "num_input_tokens_seen": 116528,
      "step": 17
    },
    {
      "epoch": 0.4645161290322581,
      "grad_norm": 4.897561550140381,
      "learning_rate": 4.975670171853926e-06,
      "loss": 0.1517,
      "num_input_tokens_seen": 123200,
      "step": 18
    },
    {
      "epoch": 0.49032258064516127,
      "grad_norm": 37.270225524902344,
      "learning_rate": 4.9692208514878445e-06,
      "loss": 0.4335,
      "num_input_tokens_seen": 130032,
      "step": 19
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 31.595401763916016,
      "learning_rate": 4.962019382530521e-06,
      "loss": 0.3609,
      "num_input_tokens_seen": 136832,
      "step": 20
    },
    {
      "epoch": 0.5419354838709678,
      "grad_norm": 8.859624862670898,
      "learning_rate": 4.9540679586191605e-06,
      "loss": 0.1708,
      "num_input_tokens_seen": 143904,
      "step": 21
    },
    {
      "epoch": 0.567741935483871,
      "grad_norm": 21.666885375976562,
      "learning_rate": 4.9453690018345144e-06,
      "loss": 0.2277,
      "num_input_tokens_seen": 150496,
      "step": 22
    },
    {
      "epoch": 0.5935483870967742,
      "grad_norm": 29.53874969482422,
      "learning_rate": 4.935925161963089e-06,
      "loss": 0.3437,
      "num_input_tokens_seen": 157360,
      "step": 23
    },
    {
      "epoch": 0.6193548387096774,
      "grad_norm": 17.89641761779785,
      "learning_rate": 4.925739315689991e-06,
      "loss": 0.2229,
      "num_input_tokens_seen": 164464,
      "step": 24
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 2.7967522144317627,
      "learning_rate": 4.914814565722671e-06,
      "loss": 0.1242,
      "num_input_tokens_seen": 170960,
      "step": 25
    },
    {
      "epoch": 0.6709677419354839,
      "grad_norm": 15.343024253845215,
      "learning_rate": 4.903154239845798e-06,
      "loss": 0.2117,
      "num_input_tokens_seen": 177808,
      "step": 26
    },
    {
      "epoch": 0.6967741935483871,
      "grad_norm": 20.621328353881836,
      "learning_rate": 4.890761889907589e-06,
      "loss": 0.2706,
      "num_input_tokens_seen": 184848,
      "step": 27
    },
    {
      "epoch": 0.7225806451612903,
      "grad_norm": 14.205361366271973,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 0.2084,
      "num_input_tokens_seen": 191536,
      "step": 28
    },
    {
      "epoch": 0.7483870967741936,
      "grad_norm": 4.756993770599365,
      "learning_rate": 4.863796438998293e-06,
      "loss": 0.0981,
      "num_input_tokens_seen": 198368,
      "step": 29
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": 13.791275024414062,
      "learning_rate": 4.849231551964771e-06,
      "loss": 0.16,
      "num_input_tokens_seen": 205200,
      "step": 30
    },
    {
      "epoch": 0.8,
      "grad_norm": 11.285390853881836,
      "learning_rate": 4.833951066243004e-06,
      "loss": 0.1614,
      "num_input_tokens_seen": 211760,
      "step": 31
    },
    {
      "epoch": 0.8258064516129032,
      "grad_norm": 13.351017951965332,
      "learning_rate": 4.817959636416969e-06,
      "loss": 0.1742,
      "num_input_tokens_seen": 218448,
      "step": 32
    },
    {
      "epoch": 0.8516129032258064,
      "grad_norm": 6.028775691986084,
      "learning_rate": 4.801262133631101e-06,
      "loss": 0.1107,
      "num_input_tokens_seen": 225408,
      "step": 33
    },
    {
      "epoch": 0.8774193548387097,
      "grad_norm": 2.5520031452178955,
      "learning_rate": 4.783863644106502e-06,
      "loss": 0.0822,
      "num_input_tokens_seen": 232032,
      "step": 34
    },
    {
      "epoch": 0.9032258064516129,
      "grad_norm": 13.276092529296875,
      "learning_rate": 4.765769467591626e-06,
      "loss": 0.1873,
      "num_input_tokens_seen": 238672,
      "step": 35
    },
    {
      "epoch": 0.9290322580645162,
      "grad_norm": 15.978204727172852,
      "learning_rate": 4.746985115747918e-06,
      "loss": 0.2375,
      "num_input_tokens_seen": 245456,
      "step": 36
    },
    {
      "epoch": 0.9548387096774194,
      "grad_norm": 16.432758331298828,
      "learning_rate": 4.72751631047092e-06,
      "loss": 0.2667,
      "num_input_tokens_seen": 252576,
      "step": 37
    },
    {
      "epoch": 0.9806451612903225,
      "grad_norm": 12.175621032714844,
      "learning_rate": 4.707368982147318e-06,
      "loss": 0.1547,
      "num_input_tokens_seen": 259536,
      "step": 38
    },
    {
      "epoch": 1.0064516129032257,
      "grad_norm": 9.780308723449707,
      "learning_rate": 4.68654926784849e-06,
      "loss": 0.1662,
      "num_input_tokens_seen": 266560,
      "step": 39
    },
    {
      "epoch": 1.032258064516129,
      "grad_norm": 3.619741678237915,
      "learning_rate": 4.665063509461098e-06,
      "loss": 0.0808,
      "num_input_tokens_seen": 273248,
      "step": 40
    },
    {
      "epoch": 1.0580645161290323,
      "grad_norm": 5.894082546234131,
      "learning_rate": 4.642918251755281e-06,
      "loss": 0.0884,
      "num_input_tokens_seen": 279888,
      "step": 41
    },
    {
      "epoch": 1.0838709677419356,
      "grad_norm": 5.443681240081787,
      "learning_rate": 4.620120240391065e-06,
      "loss": 0.0883,
      "num_input_tokens_seen": 286944,
      "step": 42
    },
    {
      "epoch": 1.1096774193548387,
      "grad_norm": 3.3760452270507812,
      "learning_rate": 4.596676419863561e-06,
      "loss": 0.0562,
      "num_input_tokens_seen": 293792,
      "step": 43
    },
    {
      "epoch": 1.135483870967742,
      "grad_norm": 2.7039427757263184,
      "learning_rate": 4.572593931387604e-06,
      "loss": 0.0856,
      "num_input_tokens_seen": 300512,
      "step": 44
    },
    {
      "epoch": 1.1612903225806452,
      "grad_norm": 4.186523914337158,
      "learning_rate": 4.54788011072248e-06,
      "loss": 0.0612,
      "num_input_tokens_seen": 307264,
      "step": 45
    },
    {
      "epoch": 1.1870967741935483,
      "grad_norm": 4.6027374267578125,
      "learning_rate": 4.522542485937369e-06,
      "loss": 0.0944,
      "num_input_tokens_seen": 314112,
      "step": 46
    },
    {
      "epoch": 1.2129032258064516,
      "grad_norm": 4.636350154876709,
      "learning_rate": 4.496588775118232e-06,
      "loss": 0.0624,
      "num_input_tokens_seen": 320864,
      "step": 47
    },
    {
      "epoch": 1.238709677419355,
      "grad_norm": 3.0458312034606934,
      "learning_rate": 4.470026884016805e-06,
      "loss": 0.0363,
      "num_input_tokens_seen": 327648,
      "step": 48
    },
    {
      "epoch": 1.2645161290322582,
      "grad_norm": 4.572902679443359,
      "learning_rate": 4.442864903642428e-06,
      "loss": 0.1039,
      "num_input_tokens_seen": 334432,
      "step": 49
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": 2.629575252532959,
      "learning_rate": 4.415111107797445e-06,
      "loss": 0.0488,
      "num_input_tokens_seen": 341248,
      "step": 50
    },
    {
      "epoch": 1.3161290322580645,
      "grad_norm": 2.7692055702209473,
      "learning_rate": 4.386773950556931e-06,
      "loss": 0.0613,
      "num_input_tokens_seen": 348192,
      "step": 51
    },
    {
      "epoch": 1.3419354838709676,
      "grad_norm": 2.706336498260498,
      "learning_rate": 4.357862063693486e-06,
      "loss": 0.07,
      "num_input_tokens_seen": 354816,
      "step": 52
    },
    {
      "epoch": 1.367741935483871,
      "grad_norm": 1.679677963256836,
      "learning_rate": 4.328384254047927e-06,
      "loss": 0.0463,
      "num_input_tokens_seen": 361600,
      "step": 53
    },
    {
      "epoch": 1.3935483870967742,
      "grad_norm": 2.623893976211548,
      "learning_rate": 4.2983495008466285e-06,
      "loss": 0.0671,
      "num_input_tokens_seen": 368464,
      "step": 54
    },
    {
      "epoch": 1.4193548387096775,
      "grad_norm": 1.7314574718475342,
      "learning_rate": 4.267766952966369e-06,
      "loss": 0.0428,
      "num_input_tokens_seen": 375440,
      "step": 55
    },
    {
      "epoch": 1.4451612903225808,
      "grad_norm": 5.240540981292725,
      "learning_rate": 4.236645926147493e-06,
      "loss": 0.0678,
      "num_input_tokens_seen": 382240,
      "step": 56
    },
    {
      "epoch": 1.4709677419354839,
      "grad_norm": 1.9007383584976196,
      "learning_rate": 4.204995900156247e-06,
      "loss": 0.0476,
      "num_input_tokens_seen": 389008,
      "step": 57
    },
    {
      "epoch": 1.4967741935483871,
      "grad_norm": 3.100925922393799,
      "learning_rate": 4.172826515897146e-06,
      "loss": 0.0442,
      "num_input_tokens_seen": 396080,
      "step": 58
    },
    {
      "epoch": 1.5225806451612902,
      "grad_norm": 2.798711061477661,
      "learning_rate": 4.140147572476269e-06,
      "loss": 0.0336,
      "num_input_tokens_seen": 403056,
      "step": 59
    },
    {
      "epoch": 1.5483870967741935,
      "grad_norm": 2.20042085647583,
      "learning_rate": 4.106969024216348e-06,
      "loss": 0.046,
      "num_input_tokens_seen": 409664,
      "step": 60
    },
    {
      "epoch": 1.5741935483870968,
      "grad_norm": 4.055737495422363,
      "learning_rate": 4.073300977624594e-06,
      "loss": 0.0416,
      "num_input_tokens_seen": 416272,
      "step": 61
    },
    {
      "epoch": 1.6,
      "grad_norm": 3.15283465385437,
      "learning_rate": 4.039153688314146e-06,
      "loss": 0.0649,
      "num_input_tokens_seen": 423360,
      "step": 62
    },
    {
      "epoch": 1.6258064516129034,
      "grad_norm": 4.418552398681641,
      "learning_rate": 4.0045375578801216e-06,
      "loss": 0.0591,
      "num_input_tokens_seen": 430304,
      "step": 63
    },
    {
      "epoch": 1.6516129032258065,
      "grad_norm": 3.960134506225586,
      "learning_rate": 3.969463130731183e-06,
      "loss": 0.0318,
      "num_input_tokens_seen": 436960,
      "step": 64
    },
    {
      "epoch": 1.6774193548387095,
      "grad_norm": 3.1769161224365234,
      "learning_rate": 3.933941090877615e-06,
      "loss": 0.0462,
      "num_input_tokens_seen": 443792,
      "step": 65
    },
    {
      "epoch": 1.7032258064516128,
      "grad_norm": 4.235939025878906,
      "learning_rate": 3.897982258676867e-06,
      "loss": 0.0465,
      "num_input_tokens_seen": 450672,
      "step": 66
    },
    {
      "epoch": 1.729032258064516,
      "grad_norm": 2.7547543048858643,
      "learning_rate": 3.861597587537568e-06,
      "loss": 0.0316,
      "num_input_tokens_seen": 457616,
      "step": 67
    },
    {
      "epoch": 1.7548387096774194,
      "grad_norm": 4.103342533111572,
      "learning_rate": 3.824798160583012e-06,
      "loss": 0.1,
      "num_input_tokens_seen": 464592,
      "step": 68
    },
    {
      "epoch": 1.7806451612903227,
      "grad_norm": 3.525808811187744,
      "learning_rate": 3.787595187275136e-06,
      "loss": 0.0711,
      "num_input_tokens_seen": 471328,
      "step": 69
    },
    {
      "epoch": 1.8064516129032258,
      "grad_norm": 2.9660446643829346,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.0494,
      "num_input_tokens_seen": 478480,
      "step": 70
    },
    {
      "epoch": 1.832258064516129,
      "grad_norm": 3.661849021911621,
      "learning_rate": 3.7120240506158433e-06,
      "loss": 0.0618,
      "num_input_tokens_seen": 485264,
      "step": 71
    },
    {
      "epoch": 1.8580645161290321,
      "grad_norm": 1.8227900266647339,
      "learning_rate": 3.6736789069647273e-06,
      "loss": 0.0511,
      "num_input_tokens_seen": 492064,
      "step": 72
    },
    {
      "epoch": 1.8838709677419354,
      "grad_norm": 2.1322553157806396,
      "learning_rate": 3.634976249348867e-06,
      "loss": 0.0464,
      "num_input_tokens_seen": 498896,
      "step": 73
    },
    {
      "epoch": 1.9096774193548387,
      "grad_norm": 1.8635531663894653,
      "learning_rate": 3.595927866972694e-06,
      "loss": 0.0331,
      "num_input_tokens_seen": 506016,
      "step": 74
    },
    {
      "epoch": 1.935483870967742,
      "grad_norm": 2.9526419639587402,
      "learning_rate": 3.556545654351749e-06,
      "loss": 0.0706,
      "num_input_tokens_seen": 512848,
      "step": 75
    },
    {
      "epoch": 1.9612903225806453,
      "grad_norm": 2.8351802825927734,
      "learning_rate": 3.516841607689501e-06,
      "loss": 0.0442,
      "num_input_tokens_seen": 519744,
      "step": 76
    },
    {
      "epoch": 1.9870967741935484,
      "grad_norm": 3.1449944972991943,
      "learning_rate": 3.476827821223184e-06,
      "loss": 0.042,
      "num_input_tokens_seen": 526352,
      "step": 77
    },
    {
      "epoch": 2.0129032258064514,
      "grad_norm": 1.6314219236373901,
      "learning_rate": 3.436516483539781e-06,
      "loss": 0.021,
      "num_input_tokens_seen": 533136,
      "step": 78
    },
    {
      "epoch": 2.0387096774193547,
      "grad_norm": 1.6224279403686523,
      "learning_rate": 3.39591987386325e-06,
      "loss": 0.0094,
      "num_input_tokens_seen": 540016,
      "step": 79
    },
    {
      "epoch": 2.064516129032258,
      "grad_norm": 0.3502344787120819,
      "learning_rate": 3.3550503583141726e-06,
      "loss": 0.0021,
      "num_input_tokens_seen": 547152,
      "step": 80
    },
    {
      "epoch": 2.0903225806451613,
      "grad_norm": 1.7473047971725464,
      "learning_rate": 3.313920386142892e-06,
      "loss": 0.0146,
      "num_input_tokens_seen": 553888,
      "step": 81
    },
    {
      "epoch": 2.1161290322580646,
      "grad_norm": 2.363898277282715,
      "learning_rate": 3.272542485937369e-06,
      "loss": 0.0237,
      "num_input_tokens_seen": 561024,
      "step": 82
    },
    {
      "epoch": 2.141935483870968,
      "grad_norm": 1.377082109451294,
      "learning_rate": 3.230929261806842e-06,
      "loss": 0.0031,
      "num_input_tokens_seen": 567936,
      "step": 83
    },
    {
      "epoch": 2.167741935483871,
      "grad_norm": 0.6467981934547424,
      "learning_rate": 3.189093389542498e-06,
      "loss": 0.0034,
      "num_input_tokens_seen": 574736,
      "step": 84
    },
    {
      "epoch": 2.193548387096774,
      "grad_norm": 0.9653486609458923,
      "learning_rate": 3.147047612756302e-06,
      "loss": 0.0045,
      "num_input_tokens_seen": 581680,
      "step": 85
    },
    {
      "epoch": 2.2193548387096773,
      "grad_norm": 0.7019590735435486,
      "learning_rate": 3.1048047389991693e-06,
      "loss": 0.0031,
      "num_input_tokens_seen": 588464,
      "step": 86
    },
    {
      "epoch": 2.2451612903225806,
      "grad_norm": 2.078730821609497,
      "learning_rate": 3.062377635859663e-06,
      "loss": 0.0341,
      "num_input_tokens_seen": 595312,
      "step": 87
    },
    {
      "epoch": 2.270967741935484,
      "grad_norm": 4.608306407928467,
      "learning_rate": 3.019779227044398e-06,
      "loss": 0.0095,
      "num_input_tokens_seen": 602080,
      "step": 88
    },
    {
      "epoch": 2.296774193548387,
      "grad_norm": 3.8219709396362305,
      "learning_rate": 2.9770224884413625e-06,
      "loss": 0.0459,
      "num_input_tokens_seen": 609168,
      "step": 89
    },
    {
      "epoch": 2.3225806451612905,
      "grad_norm": 2.868053674697876,
      "learning_rate": 2.9341204441673267e-06,
      "loss": 0.0104,
      "num_input_tokens_seen": 616000,
      "step": 90
    },
    {
      "epoch": 2.3483870967741938,
      "grad_norm": 2.516240119934082,
      "learning_rate": 2.8910861626005774e-06,
      "loss": 0.0201,
      "num_input_tokens_seen": 622544,
      "step": 91
    },
    {
      "epoch": 2.3741935483870966,
      "grad_norm": 0.5750585794448853,
      "learning_rate": 2.847932752400164e-06,
      "loss": 0.0021,
      "num_input_tokens_seen": 629600,
      "step": 92
    },
    {
      "epoch": 2.4,
      "grad_norm": 2.9817891120910645,
      "learning_rate": 2.804673358512869e-06,
      "loss": 0.043,
      "num_input_tokens_seen": 636320,
      "step": 93
    },
    {
      "epoch": 2.425806451612903,
      "grad_norm": 1.8277342319488525,
      "learning_rate": 2.761321158169134e-06,
      "loss": 0.0207,
      "num_input_tokens_seen": 643136,
      "step": 94
    },
    {
      "epoch": 2.4516129032258065,
      "grad_norm": 4.615224361419678,
      "learning_rate": 2.717889356869146e-06,
      "loss": 0.0148,
      "num_input_tokens_seen": 650048,
      "step": 95
    },
    {
      "epoch": 2.47741935483871,
      "grad_norm": 0.9854787588119507,
      "learning_rate": 2.6743911843603134e-06,
      "loss": 0.004,
      "num_input_tokens_seen": 656736,
      "step": 96
    },
    {
      "epoch": 2.5032258064516126,
      "grad_norm": 1.4292289018630981,
      "learning_rate": 2.6308398906073603e-06,
      "loss": 0.0131,
      "num_input_tokens_seen": 663552,
      "step": 97
    },
    {
      "epoch": 2.5290322580645164,
      "grad_norm": 4.594967842102051,
      "learning_rate": 2.587248741756253e-06,
      "loss": 0.0455,
      "num_input_tokens_seen": 670224,
      "step": 98
    },
    {
      "epoch": 2.554838709677419,
      "grad_norm": 0.8579672574996948,
      "learning_rate": 2.543631016093209e-06,
      "loss": 0.0031,
      "num_input_tokens_seen": 676960,
      "step": 99
    },
    {
      "epoch": 2.5806451612903225,
      "grad_norm": 2.075626850128174,
      "learning_rate": 2.5e-06,
      "loss": 0.0099,
      "num_input_tokens_seen": 684016,
      "step": 100
    },
    {
      "epoch": 2.606451612903226,
      "grad_norm": 3.9176177978515625,
      "learning_rate": 2.4563689839067913e-06,
      "loss": 0.0797,
      "num_input_tokens_seen": 690832,
      "step": 101
    },
    {
      "epoch": 2.632258064516129,
      "grad_norm": 1.6330746412277222,
      "learning_rate": 2.4127512582437486e-06,
      "loss": 0.0059,
      "num_input_tokens_seen": 697808,
      "step": 102
    },
    {
      "epoch": 2.6580645161290324,
      "grad_norm": 2.173410177230835,
      "learning_rate": 2.3691601093926406e-06,
      "loss": 0.0438,
      "num_input_tokens_seen": 704352,
      "step": 103
    },
    {
      "epoch": 2.6838709677419352,
      "grad_norm": 1.6522724628448486,
      "learning_rate": 2.325608815639687e-06,
      "loss": 0.0149,
      "num_input_tokens_seen": 711456,
      "step": 104
    },
    {
      "epoch": 2.709677419354839,
      "grad_norm": 0.7776157855987549,
      "learning_rate": 2.2821106431308546e-06,
      "loss": 0.0126,
      "num_input_tokens_seen": 718224,
      "step": 105
    },
    {
      "epoch": 2.735483870967742,
      "grad_norm": 2.2912323474884033,
      "learning_rate": 2.238678841830867e-06,
      "loss": 0.0255,
      "num_input_tokens_seen": 724928,
      "step": 106
    },
    {
      "epoch": 2.761290322580645,
      "grad_norm": 0.5118953585624695,
      "learning_rate": 2.195326641487132e-06,
      "loss": 0.0048,
      "num_input_tokens_seen": 731616,
      "step": 107
    },
    {
      "epoch": 2.7870967741935484,
      "grad_norm": 0.9067234396934509,
      "learning_rate": 2.1520672475998374e-06,
      "loss": 0.0142,
      "num_input_tokens_seen": 738272,
      "step": 108
    },
    {
      "epoch": 2.8129032258064517,
      "grad_norm": 1.6885769367218018,
      "learning_rate": 2.1089138373994226e-06,
      "loss": 0.0193,
      "num_input_tokens_seen": 745104,
      "step": 109
    },
    {
      "epoch": 2.838709677419355,
      "grad_norm": 0.6433587074279785,
      "learning_rate": 2.0658795558326745e-06,
      "loss": 0.0055,
      "num_input_tokens_seen": 752016,
      "step": 110
    },
    {
      "epoch": 2.864516129032258,
      "grad_norm": 1.0263943672180176,
      "learning_rate": 2.022977511558638e-06,
      "loss": 0.0144,
      "num_input_tokens_seen": 758720,
      "step": 111
    },
    {
      "epoch": 2.8903225806451616,
      "grad_norm": 1.3137305974960327,
      "learning_rate": 1.9802207729556023e-06,
      "loss": 0.0272,
      "num_input_tokens_seen": 765520,
      "step": 112
    },
    {
      "epoch": 2.9161290322580644,
      "grad_norm": 2.692868947982788,
      "learning_rate": 1.937622364140338e-06,
      "loss": 0.0101,
      "num_input_tokens_seen": 772288,
      "step": 113
    },
    {
      "epoch": 2.9419354838709677,
      "grad_norm": 2.19588565826416,
      "learning_rate": 1.895195261000831e-06,
      "loss": 0.0109,
      "num_input_tokens_seen": 779520,
      "step": 114
    },
    {
      "epoch": 2.967741935483871,
      "grad_norm": 2.681143283843994,
      "learning_rate": 1.852952387243698e-06,
      "loss": 0.018,
      "num_input_tokens_seen": 786400,
      "step": 115
    },
    {
      "epoch": 2.9935483870967743,
      "grad_norm": 1.9662718772888184,
      "learning_rate": 1.8109066104575023e-06,
      "loss": 0.0141,
      "num_input_tokens_seen": 793008,
      "step": 116
    },
    {
      "epoch": 3.0193548387096776,
      "grad_norm": 1.1327028274536133,
      "learning_rate": 1.7690707381931585e-06,
      "loss": 0.0057,
      "num_input_tokens_seen": 799808,
      "step": 117
    },
    {
      "epoch": 3.0451612903225804,
      "grad_norm": 0.593132495880127,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 0.0063,
      "num_input_tokens_seen": 806576,
      "step": 118
    },
    {
      "epoch": 3.0709677419354837,
      "grad_norm": 1.123922348022461,
      "learning_rate": 1.686079613857109e-06,
      "loss": 0.0138,
      "num_input_tokens_seen": 813312,
      "step": 119
    },
    {
      "epoch": 3.096774193548387,
      "grad_norm": 0.14445500075817108,
      "learning_rate": 1.6449496416858285e-06,
      "loss": 0.0011,
      "num_input_tokens_seen": 819728,
      "step": 120
    },
    {
      "epoch": 3.1225806451612903,
      "grad_norm": 0.09276027232408524,
      "learning_rate": 1.6040801261367494e-06,
      "loss": 0.0006,
      "num_input_tokens_seen": 826496,
      "step": 121
    },
    {
      "epoch": 3.1483870967741936,
      "grad_norm": 0.6197965741157532,
      "learning_rate": 1.56348351646022e-06,
      "loss": 0.0055,
      "num_input_tokens_seen": 833360,
      "step": 122
    },
    {
      "epoch": 3.174193548387097,
      "grad_norm": 0.1872132420539856,
      "learning_rate": 1.5231721787768162e-06,
      "loss": 0.0011,
      "num_input_tokens_seen": 840080,
      "step": 123
    },
    {
      "epoch": 3.2,
      "grad_norm": 2.89666748046875,
      "learning_rate": 1.4831583923105e-06,
      "loss": 0.0173,
      "num_input_tokens_seen": 847104,
      "step": 124
    },
    {
      "epoch": 3.225806451612903,
      "grad_norm": 0.8067394495010376,
      "learning_rate": 1.443454345648252e-06,
      "loss": 0.0027,
      "num_input_tokens_seen": 853712,
      "step": 125
    },
    {
      "epoch": 3.2516129032258063,
      "grad_norm": 0.5419718623161316,
      "learning_rate": 1.4040721330273063e-06,
      "loss": 0.0029,
      "num_input_tokens_seen": 860400,
      "step": 126
    },
    {
      "epoch": 3.2774193548387096,
      "grad_norm": 0.05267687141895294,
      "learning_rate": 1.3650237506511333e-06,
      "loss": 0.0003,
      "num_input_tokens_seen": 867440,
      "step": 127
    },
    {
      "epoch": 3.303225806451613,
      "grad_norm": 0.11772596091032028,
      "learning_rate": 1.3263210930352737e-06,
      "loss": 0.0007,
      "num_input_tokens_seen": 874256,
      "step": 128
    },
    {
      "epoch": 3.329032258064516,
      "grad_norm": 0.9182859063148499,
      "learning_rate": 1.2879759493841577e-06,
      "loss": 0.008,
      "num_input_tokens_seen": 881168,
      "step": 129
    },
    {
      "epoch": 3.3548387096774195,
      "grad_norm": 0.07012775540351868,
      "learning_rate": 1.2500000000000007e-06,
      "loss": 0.0004,
      "num_input_tokens_seen": 888128,
      "step": 130
    },
    {
      "epoch": 3.3806451612903228,
      "grad_norm": 0.979766309261322,
      "learning_rate": 1.2124048127248644e-06,
      "loss": 0.0049,
      "num_input_tokens_seen": 895296,
      "step": 131
    },
    {
      "epoch": 3.4064516129032256,
      "grad_norm": 0.25211745500564575,
      "learning_rate": 1.1752018394169882e-06,
      "loss": 0.0012,
      "num_input_tokens_seen": 901984,
      "step": 132
    },
    {
      "epoch": 3.432258064516129,
      "grad_norm": 0.7576802968978882,
      "learning_rate": 1.1384024124624324e-06,
      "loss": 0.0044,
      "num_input_tokens_seen": 909104,
      "step": 133
    },
    {
      "epoch": 3.458064516129032,
      "grad_norm": 0.6242833733558655,
      "learning_rate": 1.1020177413231334e-06,
      "loss": 0.0017,
      "num_input_tokens_seen": 916032,
      "step": 134
    },
    {
      "epoch": 3.4838709677419355,
      "grad_norm": 0.06409750878810883,
      "learning_rate": 1.0660589091223854e-06,
      "loss": 0.0003,
      "num_input_tokens_seen": 922736,
      "step": 135
    },
    {
      "epoch": 3.509677419354839,
      "grad_norm": 0.7863635420799255,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 0.0099,
      "num_input_tokens_seen": 929472,
      "step": 136
    },
    {
      "epoch": 3.535483870967742,
      "grad_norm": 0.7082129716873169,
      "learning_rate": 9.95462442119879e-07,
      "loss": 0.0068,
      "num_input_tokens_seen": 936112,
      "step": 137
    },
    {
      "epoch": 3.5612903225806454,
      "grad_norm": 0.5010254383087158,
      "learning_rate": 9.608463116858544e-07,
      "loss": 0.0025,
      "num_input_tokens_seen": 942912,
      "step": 138
    },
    {
      "epoch": 3.587096774193548,
      "grad_norm": 0.1011819988489151,
      "learning_rate": 9.266990223754069e-07,
      "loss": 0.0004,
      "num_input_tokens_seen": 949984,
      "step": 139
    },
    {
      "epoch": 3.6129032258064515,
      "grad_norm": 4.317319869995117,
      "learning_rate": 8.930309757836517e-07,
      "loss": 0.0101,
      "num_input_tokens_seen": 956608,
      "step": 140
    },
    {
      "epoch": 3.638709677419355,
      "grad_norm": 0.7055479288101196,
      "learning_rate": 8.598524275237321e-07,
      "loss": 0.0068,
      "num_input_tokens_seen": 963488,
      "step": 141
    },
    {
      "epoch": 3.664516129032258,
      "grad_norm": 0.10063151270151138,
      "learning_rate": 8.271734841028553e-07,
      "loss": 0.0007,
      "num_input_tokens_seen": 970128,
      "step": 142
    },
    {
      "epoch": 3.6903225806451614,
      "grad_norm": 3.3077032566070557,
      "learning_rate": 7.950040998437541e-07,
      "loss": 0.0161,
      "num_input_tokens_seen": 976800,
      "step": 143
    },
    {
      "epoch": 3.7161290322580647,
      "grad_norm": 1.0670413970947266,
      "learning_rate": 7.633540738525066e-07,
      "loss": 0.0115,
      "num_input_tokens_seen": 984000,
      "step": 144
    },
    {
      "epoch": 3.741935483870968,
      "grad_norm": 1.591837763786316,
      "learning_rate": 7.322330470336314e-07,
      "loss": 0.0052,
      "num_input_tokens_seen": 990896,
      "step": 145
    },
    {
      "epoch": 3.767741935483871,
      "grad_norm": 3.105447769165039,
      "learning_rate": 7.016504991533727e-07,
      "loss": 0.0098,
      "num_input_tokens_seen": 997824,
      "step": 146
    },
    {
      "epoch": 3.793548387096774,
      "grad_norm": 0.0832144096493721,
      "learning_rate": 6.716157459520739e-07,
      "loss": 0.0005,
      "num_input_tokens_seen": 1004928,
      "step": 147
    },
    {
      "epoch": 3.8193548387096774,
      "grad_norm": 0.2546854317188263,
      "learning_rate": 6.421379363065142e-07,
      "loss": 0.0012,
      "num_input_tokens_seen": 1011696,
      "step": 148
    },
    {
      "epoch": 3.8451612903225807,
      "grad_norm": 0.40274935960769653,
      "learning_rate": 6.1322604944307e-07,
      "loss": 0.0013,
      "num_input_tokens_seen": 1018368,
      "step": 149
    },
    {
      "epoch": 3.870967741935484,
      "grad_norm": 0.04935682937502861,
      "learning_rate": 5.848888922025553e-07,
      "loss": 0.0003,
      "num_input_tokens_seen": 1025424,
      "step": 150
    },
    {
      "epoch": 3.896774193548387,
      "grad_norm": 0.8725687265396118,
      "learning_rate": 5.571350963575728e-07,
      "loss": 0.0026,
      "num_input_tokens_seen": 1032016,
      "step": 151
    },
    {
      "epoch": 3.9225806451612906,
      "grad_norm": 0.9522215127944946,
      "learning_rate": 5.299731159831953e-07,
      "loss": 0.0097,
      "num_input_tokens_seen": 1038928,
      "step": 152
    },
    {
      "epoch": 3.9483870967741934,
      "grad_norm": 2.608211040496826,
      "learning_rate": 5.034112248817685e-07,
      "loss": 0.0047,
      "num_input_tokens_seen": 1045664,
      "step": 153
    },
    {
      "epoch": 3.9741935483870967,
      "grad_norm": 0.913472592830658,
      "learning_rate": 4.774575140626317e-07,
      "loss": 0.0081,
      "num_input_tokens_seen": 1052640,
      "step": 154
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.5549633502960205,
      "learning_rate": 4.5211988927752026e-07,
      "loss": 0.0018,
      "num_input_tokens_seen": 1059840,
      "step": 155
    },
    {
      "epoch": 4.025806451612903,
      "grad_norm": 0.6482688784599304,
      "learning_rate": 4.27406068612396e-07,
      "loss": 0.0053,
      "num_input_tokens_seen": 1066704,
      "step": 156
    },
    {
      "epoch": 4.051612903225807,
      "grad_norm": 0.11119811981916428,
      "learning_rate": 4.033235801364402e-07,
      "loss": 0.0005,
      "num_input_tokens_seen": 1073600,
      "step": 157
    },
    {
      "epoch": 4.077419354838709,
      "grad_norm": 0.009617508389055729,
      "learning_rate": 3.798797596089351e-07,
      "loss": 0.0001,
      "num_input_tokens_seen": 1080208,
      "step": 158
    },
    {
      "epoch": 4.103225806451613,
      "grad_norm": 0.18060296773910522,
      "learning_rate": 3.5708174824471947e-07,
      "loss": 0.0018,
      "num_input_tokens_seen": 1086880,
      "step": 159
    },
    {
      "epoch": 4.129032258064516,
      "grad_norm": 0.3545215427875519,
      "learning_rate": 3.3493649053890325e-07,
      "loss": 0.001,
      "num_input_tokens_seen": 1093520,
      "step": 160
    },
    {
      "epoch": 4.15483870967742,
      "grad_norm": 0.03870348632335663,
      "learning_rate": 3.134507321515107e-07,
      "loss": 0.0001,
      "num_input_tokens_seen": 1100528,
      "step": 161
    },
    {
      "epoch": 4.180645161290323,
      "grad_norm": 0.20078836381435394,
      "learning_rate": 2.9263101785268253e-07,
      "loss": 0.0012,
      "num_input_tokens_seen": 1107520,
      "step": 162
    },
    {
      "epoch": 4.2064516129032254,
      "grad_norm": 0.00893727969378233,
      "learning_rate": 2.7248368952908055e-07,
      "loss": 0.0001,
      "num_input_tokens_seen": 1114208,
      "step": 163
    },
    {
      "epoch": 4.232258064516129,
      "grad_norm": 0.027001328766345978,
      "learning_rate": 2.53014884252083e-07,
      "loss": 0.0002,
      "num_input_tokens_seen": 1120912,
      "step": 164
    },
    {
      "epoch": 4.258064516129032,
      "grad_norm": 0.01514577865600586,
      "learning_rate": 2.3423053240837518e-07,
      "loss": 0.0001,
      "num_input_tokens_seen": 1127872,
      "step": 165
    },
    {
      "epoch": 4.283870967741936,
      "grad_norm": 0.0690593495965004,
      "learning_rate": 2.1613635589349756e-07,
      "loss": 0.0003,
      "num_input_tokens_seen": 1134352,
      "step": 166
    },
    {
      "epoch": 4.309677419354839,
      "grad_norm": 0.021051278337836266,
      "learning_rate": 1.9873786636889908e-07,
      "loss": 0.0001,
      "num_input_tokens_seen": 1141440,
      "step": 167
    },
    {
      "epoch": 4.335483870967742,
      "grad_norm": 0.3527485132217407,
      "learning_rate": 1.8204036358303173e-07,
      "loss": 0.0007,
      "num_input_tokens_seen": 1148096,
      "step": 168
    },
    {
      "epoch": 4.361290322580645,
      "grad_norm": 0.09119685739278793,
      "learning_rate": 1.6604893375699594e-07,
      "loss": 0.0003,
      "num_input_tokens_seen": 1154672,
      "step": 169
    },
    {
      "epoch": 4.387096774193548,
      "grad_norm": 0.014869263395667076,
      "learning_rate": 1.507684480352292e-07,
      "loss": 0.0001,
      "num_input_tokens_seen": 1161744,
      "step": 170
    },
    {
      "epoch": 4.412903225806452,
      "grad_norm": 0.16110821068286896,
      "learning_rate": 1.362035610017079e-07,
      "loss": 0.0008,
      "num_input_tokens_seen": 1168944,
      "step": 171
    },
    {
      "epoch": 4.438709677419355,
      "grad_norm": 0.05959083512425423,
      "learning_rate": 1.223587092621162e-07,
      "loss": 0.0001,
      "num_input_tokens_seen": 1175792,
      "step": 172
    },
    {
      "epoch": 4.464516129032258,
      "grad_norm": 0.15646237134933472,
      "learning_rate": 1.0923811009241142e-07,
      "loss": 0.0004,
      "num_input_tokens_seen": 1182800,
      "step": 173
    },
    {
      "epoch": 4.490322580645161,
      "grad_norm": 0.024713285267353058,
      "learning_rate": 9.684576015420277e-08,
      "loss": 0.0001,
      "num_input_tokens_seen": 1189568,
      "step": 174
    },
    {
      "epoch": 4.516129032258064,
      "grad_norm": 0.0995955690741539,
      "learning_rate": 8.518543427732951e-08,
      "loss": 0.0005,
      "num_input_tokens_seen": 1196480,
      "step": 175
    },
    {
      "epoch": 4.541935483870968,
      "grad_norm": 0.5925021767616272,
      "learning_rate": 7.426068431000883e-08,
      "loss": 0.0076,
      "num_input_tokens_seen": 1203728,
      "step": 176
    },
    {
      "epoch": 4.567741935483871,
      "grad_norm": 0.07701185345649719,
      "learning_rate": 6.407483803691216e-08,
      "loss": 0.0004,
      "num_input_tokens_seen": 1210320,
      "step": 177
    },
    {
      "epoch": 4.593548387096774,
      "grad_norm": 0.5693293213844299,
      "learning_rate": 5.463099816548578e-08,
      "loss": 0.004,
      "num_input_tokens_seen": 1217248,
      "step": 178
    },
    {
      "epoch": 4.619354838709677,
      "grad_norm": 0.025556327775120735,
      "learning_rate": 4.593204138084006e-08,
      "loss": 0.0001,
      "num_input_tokens_seen": 1224192,
      "step": 179
    },
    {
      "epoch": 4.645161290322581,
      "grad_norm": 0.14782366156578064,
      "learning_rate": 3.798061746947995e-08,
      "loss": 0.0005,
      "num_input_tokens_seen": 1230896,
      "step": 180
    },
    {
      "epoch": 4.670967741935484,
      "grad_norm": 0.06809692084789276,
      "learning_rate": 3.077914851215585e-08,
      "loss": 0.0002,
      "num_input_tokens_seen": 1237840,
      "step": 181
    },
    {
      "epoch": 4.6967741935483875,
      "grad_norm": 0.01677132397890091,
      "learning_rate": 2.4329828146074096e-08,
      "loss": 0.0001,
      "num_input_tokens_seen": 1244688,
      "step": 182
    },
    {
      "epoch": 4.72258064516129,
      "grad_norm": 0.019206374883651733,
      "learning_rate": 1.8634620896695044e-08,
      "loss": 0.0001,
      "num_input_tokens_seen": 1251584,
      "step": 183
    },
    {
      "epoch": 4.748387096774193,
      "grad_norm": 0.02283065766096115,
      "learning_rate": 1.3695261579316776e-08,
      "loss": 0.0001,
      "num_input_tokens_seen": 1258448,
      "step": 184
    },
    {
      "epoch": 4.774193548387097,
      "grad_norm": 1.8589617013931274,
      "learning_rate": 9.513254770636138e-09,
      "loss": 0.0167,
      "num_input_tokens_seen": 1265440,
      "step": 185
    },
    {
      "epoch": 4.8,
      "grad_norm": 0.03213285654783249,
      "learning_rate": 6.089874350439507e-09,
      "loss": 0.0002,
      "num_input_tokens_seen": 1272080,
      "step": 186
    },
    {
      "epoch": 4.825806451612904,
      "grad_norm": 0.11905555427074432,
      "learning_rate": 3.4261631135654174e-09,
      "loss": 0.0003,
      "num_input_tokens_seen": 1278976,
      "step": 187
    },
    {
      "epoch": 4.851612903225806,
      "grad_norm": 0.384997695684433,
      "learning_rate": 1.5229324522605949e-09,
      "loss": 0.0024,
      "num_input_tokens_seen": 1285760,
      "step": 188
    },
    {
      "epoch": 4.877419354838709,
      "grad_norm": 0.08503298461437225,
      "learning_rate": 3.8076210902182607e-10,
      "loss": 0.0005,
      "num_input_tokens_seen": 1292368,
      "step": 189
    },
    {
      "epoch": 4.903225806451613,
      "grad_norm": 0.4136364758014679,
      "learning_rate": 0.0,
      "loss": 0.0017,
      "num_input_tokens_seen": 1299120,
      "step": 190
    },
    {
      "epoch": 4.903225806451613,
      "num_input_tokens_seen": 1299120,
      "step": 190,
      "total_flos": 5.150239379108659e+16,
      "train_loss": 0.3450760219912857,
      "train_runtime": 2142.6975,
      "train_samples_per_second": 11.57,
      "train_steps_per_second": 0.089
    }
  ],
  "logging_steps": 1,
  "max_steps": 190,
  "num_input_tokens_seen": 1299120,
  "num_train_epochs": 5,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.150239379108659e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}