{
  "best_metric": 0.8318732976913452,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 3.0,
  "eval_steps": 50,
  "global_step": 114,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02631578947368421,
      "grad_norm": 35.45204162597656,
      "learning_rate": 1e-05,
      "loss": 5.5742,
      "step": 1
    },
    {
      "epoch": 0.02631578947368421,
      "eval_loss": 1.6754724979400635,
      "eval_runtime": 4.6261,
      "eval_samples_per_second": 13.835,
      "eval_steps_per_second": 3.459,
      "step": 1
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 44.67980194091797,
      "learning_rate": 2e-05,
      "loss": 6.0369,
      "step": 2
    },
    {
      "epoch": 0.07894736842105263,
      "grad_norm": 46.14945602416992,
      "learning_rate": 3e-05,
      "loss": 6.071,
      "step": 3
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 52.658287048339844,
      "learning_rate": 4e-05,
      "loss": 5.5399,
      "step": 4
    },
    {
      "epoch": 0.13157894736842105,
      "grad_norm": 39.682334899902344,
      "learning_rate": 5e-05,
      "loss": 5.1847,
      "step": 5
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 39.48842239379883,
      "learning_rate": 6e-05,
      "loss": 4.777,
      "step": 6
    },
    {
      "epoch": 0.18421052631578946,
      "grad_norm": 26.690750122070312,
      "learning_rate": 7e-05,
      "loss": 3.9412,
      "step": 7
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 33.90504455566406,
      "learning_rate": 8e-05,
      "loss": 4.0138,
      "step": 8
    },
    {
      "epoch": 0.23684210526315788,
      "grad_norm": 39.74334716796875,
      "learning_rate": 9e-05,
      "loss": 4.7881,
      "step": 9
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 36.84393310546875,
      "learning_rate": 0.0001,
      "loss": 4.6449,
      "step": 10
    },
    {
      "epoch": 0.2894736842105263,
      "grad_norm": 16.538103103637695,
      "learning_rate": 9.997718922447667e-05,
      "loss": 3.6918,
      "step": 11
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 14.892024040222168,
      "learning_rate": 9.990877771116589e-05,
      "loss": 4.0027,
      "step": 12
    },
    {
      "epoch": 0.34210526315789475,
      "grad_norm": 16.028579711914062,
      "learning_rate": 9.979482788085454e-05,
      "loss": 3.3142,
      "step": 13
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 19.43064308166504,
      "learning_rate": 9.96354437049027e-05,
      "loss": 3.4893,
      "step": 14
    },
    {
      "epoch": 0.39473684210526316,
      "grad_norm": 16.012020111083984,
      "learning_rate": 9.943077061037671e-05,
      "loss": 3.2708,
      "step": 15
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 19.247434616088867,
      "learning_rate": 9.918099534735718e-05,
      "loss": 3.5145,
      "step": 16
    },
    {
      "epoch": 0.4473684210526316,
      "grad_norm": 16.79051399230957,
      "learning_rate": 9.888634581854234e-05,
      "loss": 3.2073,
      "step": 17
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 30.969362258911133,
      "learning_rate": 9.85470908713026e-05,
      "loss": 3.6592,
      "step": 18
    },
    {
      "epoch": 0.5,
      "grad_norm": 83.82894134521484,
      "learning_rate": 9.816354005237583e-05,
      "loss": 3.4321,
      "step": 19
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 22.35731315612793,
      "learning_rate": 9.773604332542729e-05,
      "loss": 3.8417,
      "step": 20
    },
    {
      "epoch": 0.5526315789473685,
      "grad_norm": 16.125959396362305,
      "learning_rate": 9.726499075173201e-05,
      "loss": 3.4863,
      "step": 21
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 16.601049423217773,
      "learning_rate": 9.675081213427076e-05,
      "loss": 3.6673,
      "step": 22
    },
    {
      "epoch": 0.6052631578947368,
      "grad_norm": 14.341440200805664,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.7706,
      "step": 23
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 14.518145561218262,
      "learning_rate": 9.559499229960451e-05,
      "loss": 3.2883,
      "step": 24
    },
    {
      "epoch": 0.6578947368421053,
      "grad_norm": 15.053692817687988,
      "learning_rate": 9.495440568827129e-05,
      "loss": 3.3129,
      "step": 25
    },
    {
      "epoch": 0.6842105263157895,
      "grad_norm": 15.76560115814209,
      "learning_rate": 9.42728012826605e-05,
      "loss": 3.4472,
      "step": 26
    },
    {
      "epoch": 0.7105263157894737,
      "grad_norm": 21.681568145751953,
      "learning_rate": 9.355080099977578e-05,
      "loss": 4.0833,
      "step": 27
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 11.0687894821167,
      "learning_rate": 9.278906361507238e-05,
      "loss": 3.4282,
      "step": 28
    },
    {
      "epoch": 0.7631578947368421,
      "grad_norm": 11.090133666992188,
      "learning_rate": 9.19882841613699e-05,
      "loss": 3.2468,
      "step": 29
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 14.295247077941895,
      "learning_rate": 9.114919329468282e-05,
      "loss": 3.5552,
      "step": 30
    },
    {
      "epoch": 0.8157894736842105,
      "grad_norm": 12.010293006896973,
      "learning_rate": 9.02725566275473e-05,
      "loss": 3.2984,
      "step": 31
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 14.833451271057129,
      "learning_rate": 8.935917403045251e-05,
      "loss": 3.5882,
      "step": 32
    },
    {
      "epoch": 0.868421052631579,
      "grad_norm": 16.68996810913086,
      "learning_rate": 8.840987890201403e-05,
      "loss": 3.8679,
      "step": 33
    },
    {
      "epoch": 0.8947368421052632,
      "grad_norm": 13.789620399475098,
      "learning_rate": 8.742553740855506e-05,
      "loss": 3.2592,
      "step": 34
    },
    {
      "epoch": 0.9210526315789473,
      "grad_norm": 13.425146102905273,
      "learning_rate": 8.640704769378942e-05,
      "loss": 3.4794,
      "step": 35
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 16.333017349243164,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.727,
      "step": 36
    },
    {
      "epoch": 0.9736842105263158,
      "grad_norm": 11.74190902709961,
      "learning_rate": 8.427137111675199e-05,
      "loss": 3.4931,
      "step": 37
    },
    {
      "epoch": 1.0,
      "grad_norm": 18.10176658630371,
      "learning_rate": 8.315613291203976e-05,
      "loss": 3.3415,
      "step": 38
    },
    {
      "epoch": 1.0263157894736843,
      "grad_norm": 8.549054145812988,
      "learning_rate": 8.201064202312441e-05,
      "loss": 3.0153,
      "step": 39
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 7.3096723556518555,
      "learning_rate": 8.083594363142717e-05,
      "loss": 1.9458,
      "step": 40
    },
    {
      "epoch": 1.0789473684210527,
      "grad_norm": 9.102021217346191,
      "learning_rate": 7.963310956820085e-05,
      "loss": 1.9039,
      "step": 41
    },
    {
      "epoch": 1.1052631578947367,
      "grad_norm": 8.0056734085083,
      "learning_rate": 7.840323733655778e-05,
      "loss": 1.704,
      "step": 42
    },
    {
      "epoch": 1.131578947368421,
      "grad_norm": 10.63204574584961,
      "learning_rate": 7.714744911007394e-05,
      "loss": 1.6481,
      "step": 43
    },
    {
      "epoch": 1.1578947368421053,
      "grad_norm": 10.899593353271484,
      "learning_rate": 7.586689070888284e-05,
      "loss": 1.4451,
      "step": 44
    },
    {
      "epoch": 1.1842105263157894,
      "grad_norm": 12.153818130493164,
      "learning_rate": 7.456273055419388e-05,
      "loss": 1.1306,
      "step": 45
    },
    {
      "epoch": 1.2105263157894737,
      "grad_norm": 12.974570274353027,
      "learning_rate": 7.323615860218843e-05,
      "loss": 0.9947,
      "step": 46
    },
    {
      "epoch": 1.236842105263158,
      "grad_norm": 19.212732315063477,
      "learning_rate": 7.188838525826702e-05,
      "loss": 1.2901,
      "step": 47
    },
    {
      "epoch": 1.263157894736842,
      "grad_norm": 14.307405471801758,
      "learning_rate": 7.052064027263786e-05,
      "loss": 2.498,
      "step": 48
    },
    {
      "epoch": 1.2894736842105263,
      "grad_norm": 13.335125923156738,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.6804,
      "step": 49
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 9.839455604553223,
      "learning_rate": 6.773024435212678e-05,
      "loss": 1.6424,
      "step": 50
    },
    {
      "epoch": 1.3157894736842106,
      "eval_loss": 0.8318732976913452,
      "eval_runtime": 4.7479,
      "eval_samples_per_second": 13.48,
      "eval_steps_per_second": 3.37,
      "step": 50
    },
    {
      "epoch": 1.3421052631578947,
      "grad_norm": 9.968130111694336,
      "learning_rate": 6.631013946104347e-05,
      "loss": 1.777,
      "step": 51
    },
    {
      "epoch": 1.368421052631579,
      "grad_norm": 11.425047874450684,
      "learning_rate": 6.487515269276016e-05,
      "loss": 1.4606,
      "step": 52
    },
    {
      "epoch": 1.3947368421052633,
      "grad_norm": 7.831254959106445,
      "learning_rate": 6.342659337371885e-05,
      "loss": 1.0979,
      "step": 53
    },
    {
      "epoch": 1.4210526315789473,
      "grad_norm": 9.724353790283203,
      "learning_rate": 6.19657832143779e-05,
      "loss": 1.29,
      "step": 54
    },
    {
      "epoch": 1.4473684210526316,
      "grad_norm": 9.942399024963379,
      "learning_rate": 6.049405510324238e-05,
      "loss": 1.07,
      "step": 55
    },
    {
      "epoch": 1.4736842105263157,
      "grad_norm": 15.583574295043945,
      "learning_rate": 5.90127518906953e-05,
      "loss": 1.4934,
      "step": 56
    },
    {
      "epoch": 1.5,
      "grad_norm": 11.082245826721191,
      "learning_rate": 5.752322516373916e-05,
      "loss": 2.705,
      "step": 57
    },
    {
      "epoch": 1.526315789473684,
      "grad_norm": 9.11624526977539,
      "learning_rate": 5.602683401276615e-05,
      "loss": 1.8791,
      "step": 58
    },
    {
      "epoch": 1.5526315789473686,
      "grad_norm": 9.091814994812012,
      "learning_rate": 5.45249437914819e-05,
      "loss": 1.6425,
      "step": 59
    },
    {
      "epoch": 1.5789473684210527,
      "grad_norm": 8.767348289489746,
      "learning_rate": 5.3018924871114305e-05,
      "loss": 1.4837,
      "step": 60
    },
    {
      "epoch": 1.6052631578947367,
      "grad_norm": 9.580700874328613,
      "learning_rate": 5.151015139004445e-05,
      "loss": 1.289,
      "step": 61
    },
    {
      "epoch": 1.631578947368421,
      "grad_norm": 11.071468353271484,
      "learning_rate": 5e-05,
      "loss": 1.2966,
      "step": 62
    },
    {
      "epoch": 1.6578947368421053,
      "grad_norm": 12.766911506652832,
      "learning_rate": 4.848984860995557e-05,
      "loss": 1.2353,
      "step": 63
    },
    {
      "epoch": 1.6842105263157894,
      "grad_norm": 10.578387260437012,
      "learning_rate": 4.6981075128885693e-05,
      "loss": 1.1841,
      "step": 64
    },
    {
      "epoch": 1.7105263157894737,
      "grad_norm": 13.818449974060059,
      "learning_rate": 4.547505620851811e-05,
      "loss": 1.1691,
      "step": 65
    },
    {
      "epoch": 1.736842105263158,
      "grad_norm": 9.914470672607422,
      "learning_rate": 4.397316598723385e-05,
      "loss": 2.4346,
      "step": 66
    },
    {
      "epoch": 1.763157894736842,
      "grad_norm": 8.47325325012207,
      "learning_rate": 4.2476774836260845e-05,
      "loss": 1.592,
      "step": 67
    },
    {
      "epoch": 1.7894736842105263,
      "grad_norm": 8.820671081542969,
      "learning_rate": 4.0987248109304714e-05,
      "loss": 1.5771,
      "step": 68
    },
    {
      "epoch": 1.8157894736842106,
      "grad_norm": 9.258101463317871,
      "learning_rate": 3.950594489675763e-05,
      "loss": 1.2339,
      "step": 69
    },
    {
      "epoch": 1.8421052631578947,
      "grad_norm": 10.028499603271484,
      "learning_rate": 3.803421678562213e-05,
      "loss": 1.4592,
      "step": 70
    },
    {
      "epoch": 1.868421052631579,
      "grad_norm": 12.280841827392578,
      "learning_rate": 3.657340662628116e-05,
      "loss": 1.2383,
      "step": 71
    },
    {
      "epoch": 1.8947368421052633,
      "grad_norm": 9.48217487335205,
      "learning_rate": 3.512484730723986e-05,
      "loss": 1.1216,
      "step": 72
    },
    {
      "epoch": 1.9210526315789473,
      "grad_norm": 16.327556610107422,
      "learning_rate": 3.368986053895655e-05,
      "loss": 1.2376,
      "step": 73
    },
    {
      "epoch": 1.9473684210526314,
      "grad_norm": 13.08785343170166,
      "learning_rate": 3.226975564787322e-05,
      "loss": 1.2873,
      "step": 74
    },
    {
      "epoch": 1.973684210526316,
      "grad_norm": 9.7808198928833,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.889,
      "step": 75
    },
    {
      "epoch": 2.0,
      "grad_norm": 15.715737342834473,
      "learning_rate": 2.9479359727362173e-05,
      "loss": 1.2356,
      "step": 76
    },
    {
      "epoch": 2.026315789473684,
      "grad_norm": 5.554771900177002,
      "learning_rate": 2.811161474173297e-05,
      "loss": 1.2413,
      "step": 77
    },
    {
      "epoch": 2.0526315789473686,
      "grad_norm": 5.415524482727051,
      "learning_rate": 2.6763841397811573e-05,
      "loss": 0.7209,
      "step": 78
    },
    {
      "epoch": 2.0789473684210527,
      "grad_norm": 5.091140270233154,
      "learning_rate": 2.5437269445806145e-05,
      "loss": 0.534,
      "step": 79
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 6.28108024597168,
      "learning_rate": 2.4133109291117156e-05,
      "loss": 0.4744,
      "step": 80
    },
    {
      "epoch": 2.1315789473684212,
      "grad_norm": 7.070590019226074,
      "learning_rate": 2.2852550889926067e-05,
      "loss": 0.4707,
      "step": 81
    },
    {
      "epoch": 2.1578947368421053,
      "grad_norm": 6.633754253387451,
      "learning_rate": 2.1596762663442218e-05,
      "loss": 0.3843,
      "step": 82
    },
    {
      "epoch": 2.1842105263157894,
      "grad_norm": 5.0021843910217285,
      "learning_rate": 2.0366890431799167e-05,
      "loss": 0.2632,
      "step": 83
    },
    {
      "epoch": 2.2105263157894735,
      "grad_norm": 10.45669937133789,
      "learning_rate": 1.9164056368572846e-05,
      "loss": 0.4073,
      "step": 84
    },
    {
      "epoch": 2.236842105263158,
      "grad_norm": 7.161397933959961,
      "learning_rate": 1.7989357976875603e-05,
      "loss": 0.311,
      "step": 85
    },
    {
      "epoch": 2.263157894736842,
      "grad_norm": 10.630206108093262,
      "learning_rate": 1.684386708796025e-05,
      "loss": 1.4604,
      "step": 86
    },
    {
      "epoch": 2.2894736842105265,
      "grad_norm": 8.046797752380371,
      "learning_rate": 1.5728628883248007e-05,
      "loss": 0.5739,
      "step": 87
    },
    {
      "epoch": 2.3157894736842106,
      "grad_norm": 8.14920425415039,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.5026,
      "step": 88
    },
    {
      "epoch": 2.3421052631578947,
      "grad_norm": 6.329755783081055,
      "learning_rate": 1.3592952306210588e-05,
      "loss": 0.2924,
      "step": 89
    },
    {
      "epoch": 2.3684210526315788,
      "grad_norm": 8.487998962402344,
      "learning_rate": 1.257446259144494e-05,
      "loss": 0.4119,
      "step": 90
    },
    {
      "epoch": 2.3947368421052633,
      "grad_norm": 25.33626937866211,
      "learning_rate": 1.159012109798598e-05,
      "loss": 0.2595,
      "step": 91
    },
    {
      "epoch": 2.4210526315789473,
      "grad_norm": 7.648598670959473,
      "learning_rate": 1.0640825969547496e-05,
      "loss": 0.2641,
      "step": 92
    },
    {
      "epoch": 2.4473684210526314,
      "grad_norm": 12.669825553894043,
      "learning_rate": 9.7274433724527e-06,
      "loss": 0.3631,
      "step": 93
    },
    {
      "epoch": 2.473684210526316,
      "grad_norm": 12.002209663391113,
      "learning_rate": 8.850806705317183e-06,
      "loss": 0.4211,
      "step": 94
    },
    {
      "epoch": 2.5,
      "grad_norm": 9.969554901123047,
      "learning_rate": 8.011715838630107e-06,
      "loss": 1.0852,
      "step": 95
    },
    {
      "epoch": 2.526315789473684,
      "grad_norm": 7.537227630615234,
      "learning_rate": 7.21093638492763e-06,
      "loss": 0.5648,
      "step": 96
    },
    {
      "epoch": 2.5526315789473686,
      "grad_norm": 8.888556480407715,
      "learning_rate": 6.449199000224221e-06,
      "loss": 0.5441,
      "step": 97
    },
    {
      "epoch": 2.5789473684210527,
      "grad_norm": 8.26941967010498,
      "learning_rate": 5.727198717339511e-06,
      "loss": 0.5021,
      "step": 98
    },
    {
      "epoch": 2.6052631578947367,
      "grad_norm": 8.29023265838623,
      "learning_rate": 5.045594311728707e-06,
      "loss": 0.3533,
      "step": 99
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 9.796151161193848,
      "learning_rate": 4.405007700395497e-06,
      "loss": 0.4029,
      "step": 100
    },
    {
      "epoch": 2.6315789473684212,
      "eval_loss": 0.9618005752563477,
      "eval_runtime": 4.7519,
      "eval_samples_per_second": 13.468,
      "eval_steps_per_second": 3.367,
      "step": 100
    },
    {
      "epoch": 2.6578947368421053,
      "grad_norm": 8.112892150878906,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.2688,
      "step": 101
    },
    {
      "epoch": 2.6842105263157894,
      "grad_norm": 9.736104965209961,
      "learning_rate": 3.249187865729264e-06,
      "loss": 0.4238,
      "step": 102
    },
    {
      "epoch": 2.7105263157894735,
      "grad_norm": 5.671924591064453,
      "learning_rate": 2.7350092482679836e-06,
      "loss": 0.1915,
      "step": 103
    },
    {
      "epoch": 2.736842105263158,
      "grad_norm": 8.172745704650879,
      "learning_rate": 2.2639566745727205e-06,
      "loss": 1.0132,
      "step": 104
    },
    {
      "epoch": 2.763157894736842,
      "grad_norm": 6.747289180755615,
      "learning_rate": 1.8364599476241862e-06,
      "loss": 0.5678,
      "step": 105
    },
    {
      "epoch": 2.7894736842105265,
      "grad_norm": 8.281822204589844,
      "learning_rate": 1.4529091286973995e-06,
      "loss": 0.4592,
      "step": 106
    },
    {
      "epoch": 2.8157894736842106,
      "grad_norm": 8.051541328430176,
      "learning_rate": 1.1136541814576573e-06,
      "loss": 0.3611,
      "step": 107
    },
    {
      "epoch": 2.8421052631578947,
      "grad_norm": 9.0069580078125,
      "learning_rate": 8.190046526428242e-07,
      "loss": 0.3382,
      "step": 108
    },
    {
      "epoch": 2.8684210526315788,
      "grad_norm": 5.615657329559326,
      "learning_rate": 5.692293896232936e-07,
      "loss": 0.233,
      "step": 109
    },
    {
      "epoch": 2.8947368421052633,
      "grad_norm": 8.225751876831055,
      "learning_rate": 3.6455629509730136e-07,
      "loss": 0.316,
      "step": 110
    },
    {
      "epoch": 2.9210526315789473,
      "grad_norm": 15.0908203125,
      "learning_rate": 2.0517211914545254e-07,
      "loss": 0.26,
      "step": 111
    },
    {
      "epoch": 2.9473684210526314,
      "grad_norm": 9.770281791687012,
      "learning_rate": 9.12222888341252e-08,
      "loss": 0.3276,
      "step": 112
    },
    {
      "epoch": 2.973684210526316,
      "grad_norm": 5.682199954986572,
      "learning_rate": 2.2810775523329773e-08,
      "loss": 0.3726,
      "step": 113
    },
    {
      "epoch": 3.0,
      "grad_norm": 10.495176315307617,
      "learning_rate": 0.0,
      "loss": 0.3121,
      "step": 114
    }
  ],
  "logging_steps": 1,
  "max_steps": 114,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6219486313408102e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}