{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.19515368352577656,
  "eval_steps": 500,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003252561392096276,
      "grad_norm": 7.644000053405762,
      "learning_rate": 5e-05,
      "loss": 3.7348,
      "step": 1
    },
    {
      "epoch": 0.0006505122784192552,
      "grad_norm": 6.572476387023926,
      "learning_rate": 5e-05,
      "loss": 3.5202,
      "step": 2
    },
    {
      "epoch": 0.0009757684176288828,
      "grad_norm": 5.915395736694336,
      "learning_rate": 5e-05,
      "loss": 3.2423,
      "step": 3
    },
    {
      "epoch": 0.0013010245568385104,
      "grad_norm": 5.39382266998291,
      "learning_rate": 5e-05,
      "loss": 3.2308,
      "step": 4
    },
    {
      "epoch": 0.0016262806960481379,
      "grad_norm": 5.474543571472168,
      "learning_rate": 5e-05,
      "loss": 3.3753,
      "step": 5
    },
    {
      "epoch": 0.0019515368352577655,
      "grad_norm": 5.402736663818359,
      "learning_rate": 5e-05,
      "loss": 3.3042,
      "step": 6
    },
    {
      "epoch": 0.002276792974467393,
      "grad_norm": 5.727195739746094,
      "learning_rate": 5e-05,
      "loss": 3.2722,
      "step": 7
    },
    {
      "epoch": 0.002602049113677021,
      "grad_norm": 5.997256755828857,
      "learning_rate": 5e-05,
      "loss": 3.2708,
      "step": 8
    },
    {
      "epoch": 0.002927305252886648,
      "grad_norm": 8.144789695739746,
      "learning_rate": 5e-05,
      "loss": 3.4531,
      "step": 9
    },
    {
      "epoch": 0.0032525613920962758,
      "grad_norm": 11.264220237731934,
      "learning_rate": 5e-05,
      "loss": 3.3755,
      "step": 10
    },
    {
      "epoch": 0.0035778175313059034,
      "grad_norm": 10.535292625427246,
      "learning_rate": 5e-05,
      "loss": 3.5809,
      "step": 11
    },
    {
      "epoch": 0.003903073670515531,
      "grad_norm": 8.04301929473877,
      "learning_rate": 5e-05,
      "loss": 3.3787,
      "step": 12
    },
    {
      "epoch": 0.004228329809725159,
      "grad_norm": 9.441449165344238,
      "learning_rate": 5e-05,
      "loss": 3.4919,
      "step": 13
    },
    {
      "epoch": 0.004553585948934786,
      "grad_norm": 9.322367668151855,
      "learning_rate": 5e-05,
      "loss": 3.6405,
      "step": 14
    },
    {
      "epoch": 0.004878842088144414,
      "grad_norm": 10.059698104858398,
      "learning_rate": 5e-05,
      "loss": 3.425,
      "step": 15
    },
    {
      "epoch": 0.005204098227354042,
      "grad_norm": 11.285538673400879,
      "learning_rate": 5e-05,
      "loss": 3.6643,
      "step": 16
    },
    {
      "epoch": 0.0055293543665636685,
      "grad_norm": 10.433178901672363,
      "learning_rate": 5e-05,
      "loss": 3.4485,
      "step": 17
    },
    {
      "epoch": 0.005854610505773296,
      "grad_norm": 11.724845886230469,
      "learning_rate": 5e-05,
      "loss": 3.8379,
      "step": 18
    },
    {
      "epoch": 0.006179866644982924,
      "grad_norm": 11.558403968811035,
      "learning_rate": 5e-05,
      "loss": 3.8067,
      "step": 19
    },
    {
      "epoch": 0.0065051227841925515,
      "grad_norm": 9.274937629699707,
      "learning_rate": 5e-05,
      "loss": 3.5213,
      "step": 20
    },
    {
      "epoch": 0.006830378923402179,
      "grad_norm": 11.487302780151367,
      "learning_rate": 5e-05,
      "loss": 3.8464,
      "step": 21
    },
    {
      "epoch": 0.007155635062611807,
      "grad_norm": 11.910959243774414,
      "learning_rate": 5e-05,
      "loss": 3.7159,
      "step": 22
    },
    {
      "epoch": 0.0074808912018214345,
      "grad_norm": 10.441876411437988,
      "learning_rate": 5e-05,
      "loss": 4.3052,
      "step": 23
    },
    {
      "epoch": 0.007806147341031062,
      "grad_norm": 11.492648124694824,
      "learning_rate": 5e-05,
      "loss": 4.0298,
      "step": 24
    },
    {
      "epoch": 0.00813140348024069,
      "grad_norm": 11.218420028686523,
      "learning_rate": 5e-05,
      "loss": 3.9014,
      "step": 25
    },
    {
      "epoch": 0.008456659619450317,
      "grad_norm": 9.615971565246582,
      "learning_rate": 5e-05,
      "loss": 3.8972,
      "step": 26
    },
    {
      "epoch": 0.008781915758659945,
      "grad_norm": 9.325116157531738,
      "learning_rate": 5e-05,
      "loss": 4.0339,
      "step": 27
    },
    {
      "epoch": 0.009107171897869573,
      "grad_norm": 10.537034034729004,
      "learning_rate": 5e-05,
      "loss": 4.3475,
      "step": 28
    },
    {
      "epoch": 0.0094324280370792,
      "grad_norm": 9.163812637329102,
      "learning_rate": 5e-05,
      "loss": 4.4702,
      "step": 29
    },
    {
      "epoch": 0.009757684176288828,
      "grad_norm": 8.232535362243652,
      "learning_rate": 5e-05,
      "loss": 4.5234,
      "step": 30
    },
    {
      "epoch": 0.010082940315498456,
      "grad_norm": 7.85621976852417,
      "learning_rate": 5e-05,
      "loss": 4.665,
      "step": 31
    },
    {
      "epoch": 0.010408196454708083,
      "grad_norm": 7.693171501159668,
      "learning_rate": 5e-05,
      "loss": 4.5524,
      "step": 32
    },
    {
      "epoch": 0.01073345259391771,
      "grad_norm": 6.418099403381348,
      "learning_rate": 5e-05,
      "loss": 4.3471,
      "step": 33
    },
    {
      "epoch": 0.011058708733127337,
      "grad_norm": 9.231449127197266,
      "learning_rate": 5e-05,
      "loss": 4.5491,
      "step": 34
    },
    {
      "epoch": 0.011383964872336965,
      "grad_norm": 8.351770401000977,
      "learning_rate": 5e-05,
      "loss": 4.6851,
      "step": 35
    },
    {
      "epoch": 0.011709221011546592,
      "grad_norm": 8.412186622619629,
      "learning_rate": 5e-05,
      "loss": 4.4453,
      "step": 36
    },
    {
      "epoch": 0.01203447715075622,
      "grad_norm": 7.4988932609558105,
      "learning_rate": 5e-05,
      "loss": 4.2595,
      "step": 37
    },
    {
      "epoch": 0.012359733289965848,
      "grad_norm": 6.0955424308776855,
      "learning_rate": 5e-05,
      "loss": 4.1402,
      "step": 38
    },
    {
      "epoch": 0.012684989429175475,
      "grad_norm": 5.853550434112549,
      "learning_rate": 5e-05,
      "loss": 4.2133,
      "step": 39
    },
    {
      "epoch": 0.013010245568385103,
      "grad_norm": 6.071702480316162,
      "learning_rate": 5e-05,
      "loss": 3.9406,
      "step": 40
    },
    {
      "epoch": 0.01333550170759473,
      "grad_norm": 5.181666374206543,
      "learning_rate": 5e-05,
      "loss": 3.9559,
      "step": 41
    },
    {
      "epoch": 0.013660757846804358,
      "grad_norm": 5.067506313323975,
      "learning_rate": 5e-05,
      "loss": 4.0526,
      "step": 42
    },
    {
      "epoch": 0.013986013986013986,
      "grad_norm": 4.593716621398926,
      "learning_rate": 5e-05,
      "loss": 4.0814,
      "step": 43
    },
    {
      "epoch": 0.014311270125223614,
      "grad_norm": 5.379826545715332,
      "learning_rate": 5e-05,
      "loss": 4.13,
      "step": 44
    },
    {
      "epoch": 0.014636526264433241,
      "grad_norm": 6.113279819488525,
      "learning_rate": 5e-05,
      "loss": 4.0842,
      "step": 45
    },
    {
      "epoch": 0.014961782403642869,
      "grad_norm": 4.885502815246582,
      "learning_rate": 5e-05,
      "loss": 4.147,
      "step": 46
    },
    {
      "epoch": 0.015287038542852497,
      "grad_norm": 5.065276622772217,
      "learning_rate": 5e-05,
      "loss": 4.0597,
      "step": 47
    },
    {
      "epoch": 0.015612294682062124,
      "grad_norm": 5.306569576263428,
      "learning_rate": 5e-05,
      "loss": 4.4288,
      "step": 48
    },
    {
      "epoch": 0.01593755082127175,
      "grad_norm": 6.738716125488281,
      "learning_rate": 5e-05,
      "loss": 4.2153,
      "step": 49
    },
    {
      "epoch": 0.01626280696048138,
      "grad_norm": 7.264622211456299,
      "learning_rate": 5e-05,
      "loss": 4.3567,
      "step": 50
    },
    {
      "epoch": 0.016588063099691006,
      "grad_norm": 4.799393177032471,
      "learning_rate": 5e-05,
      "loss": 4.1491,
      "step": 51
    },
    {
      "epoch": 0.016913319238900635,
      "grad_norm": 4.5021071434021,
      "learning_rate": 5e-05,
      "loss": 4.0725,
      "step": 52
    },
    {
      "epoch": 0.01723857537811026,
      "grad_norm": 5.524833679199219,
      "learning_rate": 5e-05,
      "loss": 4.405,
      "step": 53
    },
    {
      "epoch": 0.01756383151731989,
      "grad_norm": 4.327210426330566,
      "learning_rate": 5e-05,
      "loss": 4.198,
      "step": 54
    },
    {
      "epoch": 0.017889087656529516,
      "grad_norm": 4.141977787017822,
      "learning_rate": 5e-05,
      "loss": 4.0445,
      "step": 55
    },
    {
      "epoch": 0.018214343795739146,
      "grad_norm": 4.746036529541016,
      "learning_rate": 5e-05,
      "loss": 4.5174,
      "step": 56
    },
    {
      "epoch": 0.01853959993494877,
      "grad_norm": 5.5715837478637695,
      "learning_rate": 5e-05,
      "loss": 4.2292,
      "step": 57
    },
    {
      "epoch": 0.0188648560741584,
      "grad_norm": 5.887129306793213,
      "learning_rate": 5e-05,
      "loss": 4.0795,
      "step": 58
    },
    {
      "epoch": 0.019190112213368027,
      "grad_norm": 4.8050150871276855,
      "learning_rate": 5e-05,
      "loss": 4.1816,
      "step": 59
    },
    {
      "epoch": 0.019515368352577656,
      "grad_norm": 4.179840564727783,
      "learning_rate": 5e-05,
      "loss": 4.337,
      "step": 60
    },
    {
      "epoch": 0.019840624491787282,
      "grad_norm": 5.042575359344482,
      "learning_rate": 5e-05,
      "loss": 4.1466,
      "step": 61
    },
    {
      "epoch": 0.02016588063099691,
      "grad_norm": 4.339786052703857,
      "learning_rate": 5e-05,
      "loss": 3.7189,
      "step": 62
    },
    {
      "epoch": 0.020491136770206538,
      "grad_norm": 8.27956771850586,
      "learning_rate": 5e-05,
      "loss": 4.1767,
      "step": 63
    },
    {
      "epoch": 0.020816392909416167,
      "grad_norm": 6.273040294647217,
      "learning_rate": 5e-05,
      "loss": 4.363,
      "step": 64
    },
    {
      "epoch": 0.021141649048625793,
      "grad_norm": 7.342176914215088,
      "learning_rate": 5e-05,
      "loss": 4.3939,
      "step": 65
    },
    {
      "epoch": 0.02146690518783542,
      "grad_norm": 6.060370445251465,
      "learning_rate": 5e-05,
      "loss": 4.1033,
      "step": 66
    },
    {
      "epoch": 0.021792161327045048,
      "grad_norm": 6.683494567871094,
      "learning_rate": 5e-05,
      "loss": 3.9883,
      "step": 67
    },
    {
      "epoch": 0.022117417466254674,
      "grad_norm": 6.418432712554932,
      "learning_rate": 5e-05,
      "loss": 4.1472,
      "step": 68
    },
    {
      "epoch": 0.022442673605464303,
      "grad_norm": 6.342174053192139,
      "learning_rate": 5e-05,
      "loss": 4.414,
      "step": 69
    },
    {
      "epoch": 0.02276792974467393,
      "grad_norm": 10.055042266845703,
      "learning_rate": 5e-05,
      "loss": 4.1925,
      "step": 70
    },
    {
      "epoch": 0.02309318588388356,
      "grad_norm": 6.6624932289123535,
      "learning_rate": 5e-05,
      "loss": 4.1111,
      "step": 71
    },
    {
      "epoch": 0.023418442023093185,
      "grad_norm": 8.38736343383789,
      "learning_rate": 5e-05,
      "loss": 4.5028,
      "step": 72
    },
    {
      "epoch": 0.023743698162302814,
      "grad_norm": 8.479351997375488,
      "learning_rate": 5e-05,
      "loss": 4.2832,
      "step": 73
    },
    {
      "epoch": 0.02406895430151244,
      "grad_norm": 8.613444328308105,
      "learning_rate": 5e-05,
      "loss": 4.5189,
      "step": 74
    },
    {
      "epoch": 0.02439421044072207,
      "grad_norm": 6.932406425476074,
      "learning_rate": 5e-05,
      "loss": 4.1228,
      "step": 75
    },
    {
      "epoch": 0.024719466579931695,
      "grad_norm": 5.989908695220947,
      "learning_rate": 5e-05,
      "loss": 4.0289,
      "step": 76
    },
    {
      "epoch": 0.025044722719141325,
      "grad_norm": 5.118892192840576,
      "learning_rate": 5e-05,
      "loss": 3.8781,
      "step": 77
    },
    {
      "epoch": 0.02536997885835095,
      "grad_norm": 5.232855796813965,
      "learning_rate": 5e-05,
      "loss": 4.2731,
      "step": 78
    },
    {
      "epoch": 0.02569523499756058,
      "grad_norm": 4.9437103271484375,
      "learning_rate": 5e-05,
      "loss": 3.1985,
      "step": 79
    },
    {
      "epoch": 0.026020491136770206,
      "grad_norm": 7.929747581481934,
      "learning_rate": 5e-05,
      "loss": 4.1925,
      "step": 80
    },
    {
      "epoch": 0.026345747275979835,
      "grad_norm": 9.323763847351074,
      "learning_rate": 5e-05,
      "loss": 4.2925,
      "step": 81
    },
    {
      "epoch": 0.02667100341518946,
      "grad_norm": 6.18411111831665,
      "learning_rate": 5e-05,
      "loss": 4.0956,
      "step": 82
    },
    {
      "epoch": 0.02699625955439909,
      "grad_norm": 4.424221038818359,
      "learning_rate": 5e-05,
      "loss": 4.1803,
      "step": 83
    },
    {
      "epoch": 0.027321515693608717,
      "grad_norm": 6.044656276702881,
      "learning_rate": 5e-05,
      "loss": 4.0551,
      "step": 84
    },
    {
      "epoch": 0.027646771832818346,
      "grad_norm": 9.380243301391602,
      "learning_rate": 5e-05,
      "loss": 4.2753,
      "step": 85
    },
    {
      "epoch": 0.027972027972027972,
      "grad_norm": 10.203062057495117,
      "learning_rate": 5e-05,
      "loss": 4.5481,
      "step": 86
    },
    {
      "epoch": 0.028297284111237598,
      "grad_norm": 12.21309757232666,
      "learning_rate": 5e-05,
      "loss": 4.2921,
      "step": 87
    },
    {
      "epoch": 0.028622540250447227,
      "grad_norm": 7.666494369506836,
      "learning_rate": 5e-05,
      "loss": 4.2344,
      "step": 88
    },
    {
      "epoch": 0.028947796389656853,
      "grad_norm": 5.388767719268799,
      "learning_rate": 5e-05,
      "loss": 4.3914,
      "step": 89
    },
    {
      "epoch": 0.029273052528866483,
      "grad_norm": 7.598433971405029,
      "learning_rate": 5e-05,
      "loss": 4.242,
      "step": 90
    },
    {
      "epoch": 0.02959830866807611,
      "grad_norm": 11.387866020202637,
      "learning_rate": 5e-05,
      "loss": 4.0014,
      "step": 91
    },
    {
      "epoch": 0.029923564807285738,
      "grad_norm": 10.232786178588867,
      "learning_rate": 5e-05,
      "loss": 4.025,
      "step": 92
    },
    {
      "epoch": 0.030248820946495364,
      "grad_norm": 9.431289672851562,
      "learning_rate": 5e-05,
      "loss": 4.2743,
      "step": 93
    },
    {
      "epoch": 0.030574077085704993,
      "grad_norm": 6.723931789398193,
      "learning_rate": 5e-05,
      "loss": 4.111,
      "step": 94
    },
    {
      "epoch": 0.03089933322491462,
      "grad_norm": 5.171010971069336,
      "learning_rate": 5e-05,
      "loss": 3.8832,
      "step": 95
    },
    {
      "epoch": 0.03122458936412425,
      "grad_norm": 7.667996883392334,
      "learning_rate": 5e-05,
      "loss": 4.1839,
      "step": 96
    },
    {
      "epoch": 0.031549845503333875,
      "grad_norm": 9.853692054748535,
      "learning_rate": 5e-05,
      "loss": 4.2596,
      "step": 97
    },
    {
      "epoch": 0.0318751016425435,
      "grad_norm": 9.22080135345459,
      "learning_rate": 5e-05,
      "loss": 3.7551,
      "step": 98
    },
    {
      "epoch": 0.03220035778175313,
      "grad_norm": 8.230822563171387,
      "learning_rate": 5e-05,
      "loss": 4.1223,
      "step": 99
    },
    {
      "epoch": 0.03252561392096276,
      "grad_norm": 4.844912052154541,
      "learning_rate": 5e-05,
      "loss": 3.9264,
      "step": 100
    },
    {
      "epoch": 0.032850870060172385,
      "grad_norm": 5.341676712036133,
      "learning_rate": 5e-05,
      "loss": 4.2083,
      "step": 101
    },
    {
      "epoch": 0.03317612619938201,
      "grad_norm": 10.346305847167969,
      "learning_rate": 5e-05,
      "loss": 4.6745,
      "step": 102
    },
    {
      "epoch": 0.033501382338591644,
      "grad_norm": 5.822200298309326,
      "learning_rate": 5e-05,
      "loss": 3.9329,
      "step": 103
    },
    {
      "epoch": 0.03382663847780127,
      "grad_norm": 4.412308692932129,
      "learning_rate": 5e-05,
      "loss": 4.2581,
      "step": 104
    },
    {
      "epoch": 0.034151894617010896,
      "grad_norm": 6.643288612365723,
      "learning_rate": 5e-05,
      "loss": 4.0638,
      "step": 105
    },
    {
      "epoch": 0.03447715075622052,
      "grad_norm": 4.771259784698486,
      "learning_rate": 5e-05,
      "loss": 3.9147,
      "step": 106
    },
    {
      "epoch": 0.034802406895430155,
      "grad_norm": 4.471869945526123,
      "learning_rate": 5e-05,
      "loss": 3.8011,
      "step": 107
    },
    {
      "epoch": 0.03512766303463978,
      "grad_norm": 6.949775218963623,
      "learning_rate": 5e-05,
      "loss": 4.3229,
      "step": 108
    },
    {
      "epoch": 0.035452919173849406,
      "grad_norm": 5.095446586608887,
      "learning_rate": 5e-05,
      "loss": 3.616,
      "step": 109
    },
    {
      "epoch": 0.03577817531305903,
      "grad_norm": 6.592041015625,
      "learning_rate": 5e-05,
      "loss": 3.7697,
      "step": 110
    },
    {
      "epoch": 0.03610343145226866,
      "grad_norm": 7.455766677856445,
      "learning_rate": 5e-05,
      "loss": 4.0375,
      "step": 111
    },
    {
      "epoch": 0.03642868759147829,
      "grad_norm": 4.540219306945801,
      "learning_rate": 5e-05,
      "loss": 3.7951,
      "step": 112
    },
    {
      "epoch": 0.03675394373068792,
      "grad_norm": 5.230220794677734,
      "learning_rate": 5e-05,
      "loss": 4.0304,
      "step": 113
    },
    {
      "epoch": 0.03707919986989754,
      "grad_norm": 5.179874420166016,
      "learning_rate": 5e-05,
      "loss": 4.0191,
      "step": 114
    },
    {
      "epoch": 0.03740445600910717,
      "grad_norm": 6.374222755432129,
      "learning_rate": 5e-05,
      "loss": 4.4934,
      "step": 115
    },
    {
      "epoch": 0.0377297121483168,
      "grad_norm": 6.96058988571167,
      "learning_rate": 5e-05,
      "loss": 4.1446,
      "step": 116
    },
    {
      "epoch": 0.03805496828752643,
      "grad_norm": 6.299279689788818,
      "learning_rate": 5e-05,
      "loss": 3.9077,
      "step": 117
    },
    {
      "epoch": 0.038380224426736054,
      "grad_norm": 6.169437408447266,
      "learning_rate": 5e-05,
      "loss": 4.1457,
      "step": 118
    },
    {
      "epoch": 0.03870548056594568,
      "grad_norm": 5.159611701965332,
      "learning_rate": 5e-05,
      "loss": 3.7067,
      "step": 119
    },
    {
      "epoch": 0.03903073670515531,
      "grad_norm": 6.676630973815918,
      "learning_rate": 5e-05,
      "loss": 4.0493,
      "step": 120
    },
    {
      "epoch": 0.03935599284436494,
      "grad_norm": 6.488524436950684,
      "learning_rate": 5e-05,
      "loss": 4.109,
      "step": 121
    },
    {
      "epoch": 0.039681248983574564,
      "grad_norm": 6.670077800750732,
      "learning_rate": 5e-05,
      "loss": 3.6645,
      "step": 122
    },
    {
      "epoch": 0.04000650512278419,
      "grad_norm": 6.173693656921387,
      "learning_rate": 5e-05,
      "loss": 4.4163,
      "step": 123
    },
    {
      "epoch": 0.04033176126199382,
      "grad_norm": 6.306183815002441,
      "learning_rate": 5e-05,
      "loss": 3.9382,
      "step": 124
    },
    {
      "epoch": 0.04065701740120345,
      "grad_norm": 6.007297039031982,
      "learning_rate": 5e-05,
      "loss": 3.956,
      "step": 125
    },
    {
      "epoch": 0.040982273540413075,
      "grad_norm": 6.0243730545043945,
      "learning_rate": 5e-05,
      "loss": 3.9613,
      "step": 126
    },
    {
      "epoch": 0.0413075296796227,
      "grad_norm": 5.6909871101379395,
      "learning_rate": 5e-05,
      "loss": 3.9213,
      "step": 127
    },
    {
      "epoch": 0.041632785818832334,
      "grad_norm": 5.5652265548706055,
      "learning_rate": 5e-05,
      "loss": 3.9325,
      "step": 128
    },
    {
      "epoch": 0.04195804195804196,
      "grad_norm": 7.6173272132873535,
      "learning_rate": 5e-05,
      "loss": 4.0422,
      "step": 129
    },
    {
      "epoch": 0.042283298097251586,
      "grad_norm": 10.900376319885254,
      "learning_rate": 5e-05,
      "loss": 3.9173,
      "step": 130
    },
    {
      "epoch": 0.04260855423646121,
      "grad_norm": 12.899847984313965,
      "learning_rate": 5e-05,
      "loss": 4.0328,
      "step": 131
    },
    {
      "epoch": 0.04293381037567084,
      "grad_norm": 11.928502082824707,
      "learning_rate": 5e-05,
      "loss": 3.9763,
      "step": 132
    },
    {
      "epoch": 0.04325906651488047,
      "grad_norm": 8.4597749710083,
      "learning_rate": 5e-05,
      "loss": 4.0895,
      "step": 133
    },
    {
      "epoch": 0.043584322654090096,
      "grad_norm": 5.162694931030273,
      "learning_rate": 5e-05,
      "loss": 4.1564,
      "step": 134
    },
    {
      "epoch": 0.04390957879329972,
      "grad_norm": 13.066299438476562,
      "learning_rate": 5e-05,
      "loss": 4.1774,
      "step": 135
    },
    {
      "epoch": 0.04423483493250935,
      "grad_norm": 14.013510704040527,
      "learning_rate": 5e-05,
      "loss": 3.5203,
      "step": 136
    },
    {
      "epoch": 0.04456009107171898,
      "grad_norm": 15.885542869567871,
      "learning_rate": 5e-05,
      "loss": 4.1405,
      "step": 137
    },
    {
      "epoch": 0.04488534721092861,
      "grad_norm": 7.15226411819458,
      "learning_rate": 5e-05,
      "loss": 4.043,
      "step": 138
    },
    {
      "epoch": 0.04521060335013823,
      "grad_norm": 5.1085686683654785,
      "learning_rate": 5e-05,
      "loss": 3.7764,
      "step": 139
    },
    {
      "epoch": 0.04553585948934786,
      "grad_norm": 6.9343390464782715,
      "learning_rate": 5e-05,
      "loss": 4.2056,
      "step": 140
    },
    {
      "epoch": 0.04586111562855749,
      "grad_norm": 11.624869346618652,
      "learning_rate": 5e-05,
      "loss": 3.7097,
      "step": 141
    },
    {
      "epoch": 0.04618637176776712,
      "grad_norm": 12.546487808227539,
      "learning_rate": 5e-05,
      "loss": 4.2067,
      "step": 142
    },
    {
      "epoch": 0.046511627906976744,
      "grad_norm": 5.573001861572266,
      "learning_rate": 5e-05,
      "loss": 3.6916,
      "step": 143
    },
    {
      "epoch": 0.04683688404618637,
      "grad_norm": 6.0869140625,
      "learning_rate": 5e-05,
      "loss": 4.1239,
      "step": 144
    },
    {
      "epoch": 0.047162140185396,
      "grad_norm": 7.625162124633789,
      "learning_rate": 5e-05,
      "loss": 3.9154,
      "step": 145
    },
    {
      "epoch": 0.04748739632460563,
      "grad_norm": 5.8476762771606445,
      "learning_rate": 5e-05,
      "loss": 3.9673,
      "step": 146
    },
    {
      "epoch": 0.047812652463815254,
      "grad_norm": 6.097865104675293,
      "learning_rate": 5e-05,
      "loss": 3.994,
      "step": 147
    },
    {
      "epoch": 0.04813790860302488,
      "grad_norm": 5.200497150421143,
      "learning_rate": 5e-05,
      "loss": 4.1332,
      "step": 148
    },
    {
      "epoch": 0.04846316474223451,
      "grad_norm": 8.92606258392334,
      "learning_rate": 5e-05,
      "loss": 4.1005,
      "step": 149
    },
    {
      "epoch": 0.04878842088144414,
      "grad_norm": 5.433960437774658,
      "learning_rate": 5e-05,
      "loss": 4.099,
      "step": 150
    },
    {
      "epoch": 0.049113677020653765,
      "grad_norm": 4.350966453552246,
      "learning_rate": 5e-05,
      "loss": 3.7492,
      "step": 151
    },
    {
      "epoch": 0.04943893315986339,
      "grad_norm": 8.3677978515625,
      "learning_rate": 5e-05,
      "loss": 3.8048,
      "step": 152
    },
    {
      "epoch": 0.04976418929907302,
      "grad_norm": 10.74728012084961,
      "learning_rate": 5e-05,
      "loss": 4.3122,
      "step": 153
    },
    {
      "epoch": 0.05008944543828265,
      "grad_norm": 8.89576530456543,
      "learning_rate": 5e-05,
      "loss": 4.432,
      "step": 154
    },
    {
      "epoch": 0.050414701577492275,
      "grad_norm": 6.710874080657959,
      "learning_rate": 5e-05,
      "loss": 3.9353,
      "step": 155
    },
    {
      "epoch": 0.0507399577167019,
      "grad_norm": 10.725092887878418,
      "learning_rate": 5e-05,
      "loss": 4.2776,
      "step": 156
    },
    {
      "epoch": 0.05106521385591153,
      "grad_norm": 11.6733980178833,
      "learning_rate": 5e-05,
      "loss": 4.1354,
      "step": 157
    },
    {
      "epoch": 0.05139046999512116,
      "grad_norm": 9.846784591674805,
      "learning_rate": 5e-05,
      "loss": 3.9646,
      "step": 158
    },
    {
      "epoch": 0.051715726134330786,
      "grad_norm": 8.646893501281738,
      "learning_rate": 5e-05,
      "loss": 3.9413,
      "step": 159
    },
    {
      "epoch": 0.05204098227354041,
      "grad_norm": 7.0959062576293945,
      "learning_rate": 5e-05,
      "loss": 4.0745,
      "step": 160
    },
    {
      "epoch": 0.05236623841275004,
      "grad_norm": 7.378256797790527,
      "learning_rate": 5e-05,
      "loss": 4.1712,
      "step": 161
    },
    {
      "epoch": 0.05269149455195967,
      "grad_norm": 7.3625640869140625,
      "learning_rate": 5e-05,
      "loss": 3.9466,
      "step": 162
    },
    {
      "epoch": 0.0530167506911693,
      "grad_norm": 4.918821811676025,
      "learning_rate": 5e-05,
      "loss": 3.8243,
      "step": 163
    },
    {
      "epoch": 0.05334200683037892,
      "grad_norm": 6.653145790100098,
      "learning_rate": 5e-05,
      "loss": 3.8895,
      "step": 164
    },
    {
      "epoch": 0.05366726296958855,
      "grad_norm": 8.699049949645996,
      "learning_rate": 5e-05,
      "loss": 4.1705,
      "step": 165
    },
    {
      "epoch": 0.05399251910879818,
      "grad_norm": 7.855594158172607,
      "learning_rate": 5e-05,
      "loss": 3.6343,
      "step": 166
    },
    {
      "epoch": 0.05431777524800781,
      "grad_norm": 5.597055435180664,
      "learning_rate": 5e-05,
      "loss": 3.7043,
      "step": 167
    },
    {
      "epoch": 0.05464303138721743,
      "grad_norm": 9.524121284484863,
      "learning_rate": 5e-05,
      "loss": 3.8942,
      "step": 168
    },
    {
      "epoch": 0.05496828752642706,
      "grad_norm": 5.389048099517822,
      "learning_rate": 5e-05,
      "loss": 3.4256,
      "step": 169
    },
    {
      "epoch": 0.05529354366563669,
      "grad_norm": 5.568866729736328,
      "learning_rate": 5e-05,
      "loss": 3.9784,
      "step": 170
    },
    {
      "epoch": 0.05561879980484632,
      "grad_norm": 12.199308395385742,
      "learning_rate": 5e-05,
      "loss": 3.7894,
      "step": 171
    },
    {
      "epoch": 0.055944055944055944,
      "grad_norm": 15.115793228149414,
      "learning_rate": 5e-05,
      "loss": 3.6162,
      "step": 172
    },
    {
      "epoch": 0.05626931208326557,
      "grad_norm": 5.6520538330078125,
      "learning_rate": 5e-05,
      "loss": 3.8633,
      "step": 173
    },
    {
      "epoch": 0.056594568222475196,
      "grad_norm": 5.969440937042236,
      "learning_rate": 5e-05,
      "loss": 4.0392,
      "step": 174
    },
    {
      "epoch": 0.05691982436168483,
      "grad_norm": 8.82860279083252,
      "learning_rate": 5e-05,
      "loss": 4.1596,
      "step": 175
    },
    {
      "epoch": 0.057245080500894455,
      "grad_norm": 8.133511543273926,
      "learning_rate": 5e-05,
      "loss": 4.3075,
      "step": 176
    },
    {
      "epoch": 0.05757033664010408,
      "grad_norm": 5.794802665710449,
      "learning_rate": 5e-05,
      "loss": 3.7082,
      "step": 177
    },
    {
      "epoch": 0.057895592779313707,
      "grad_norm": 6.0018744468688965,
      "learning_rate": 5e-05,
      "loss": 3.67,
      "step": 178
    },
    {
      "epoch": 0.05822084891852334,
      "grad_norm": 9.123400688171387,
      "learning_rate": 5e-05,
      "loss": 3.6293,
      "step": 179
    },
    {
      "epoch": 0.058546105057732965,
      "grad_norm": 12.262410163879395,
      "learning_rate": 5e-05,
      "loss": 4.0337,
      "step": 180
    },
    {
      "epoch": 0.05887136119694259,
      "grad_norm": 5.367374897003174,
      "learning_rate": 5e-05,
      "loss": 3.7243,
      "step": 181
    },
    {
      "epoch": 0.05919661733615222,
      "grad_norm": 5.942975997924805,
      "learning_rate": 5e-05,
      "loss": 3.691,
      "step": 182
    },
    {
      "epoch": 0.05952187347536185,
      "grad_norm": 5.772192001342773,
      "learning_rate": 5e-05,
      "loss": 3.8556,
      "step": 183
    },
    {
      "epoch": 0.059847129614571476,
      "grad_norm": 6.091885566711426,
      "learning_rate": 5e-05,
      "loss": 3.8396,
      "step": 184
    },
    {
      "epoch": 0.0601723857537811,
      "grad_norm": 6.4458231925964355,
      "learning_rate": 5e-05,
      "loss": 4.3947,
      "step": 185
    },
    {
      "epoch": 0.06049764189299073,
      "grad_norm": 6.378884315490723,
      "learning_rate": 5e-05,
      "loss": 4.375,
      "step": 186
    },
    {
      "epoch": 0.06082289803220036,
      "grad_norm": 7.179290294647217,
      "learning_rate": 5e-05,
      "loss": 3.6237,
      "step": 187
    },
    {
      "epoch": 0.06114815417140999,
      "grad_norm": 5.786200046539307,
      "learning_rate": 5e-05,
      "loss": 4.2066,
      "step": 188
    },
    {
      "epoch": 0.06147341031061961,
      "grad_norm": 5.186939239501953,
      "learning_rate": 5e-05,
      "loss": 3.9935,
      "step": 189
    },
    {
      "epoch": 0.06179866644982924,
      "grad_norm": 4.02333402633667,
      "learning_rate": 5e-05,
      "loss": 3.6273,
      "step": 190
    },
    {
      "epoch": 0.06212392258903887,
      "grad_norm": 6.622715473175049,
      "learning_rate": 5e-05,
      "loss": 4.2028,
      "step": 191
    },
    {
      "epoch": 0.0624491787282485,
      "grad_norm": 9.464071273803711,
      "learning_rate": 5e-05,
      "loss": 4.0506,
      "step": 192
    },
    {
      "epoch": 0.06277443486745812,
      "grad_norm": 6.995242595672607,
      "learning_rate": 5e-05,
      "loss": 4.1047,
      "step": 193
    },
    {
      "epoch": 0.06309969100666775,
      "grad_norm": 9.435445785522461,
      "learning_rate": 5e-05,
      "loss": 3.8718,
      "step": 194
    },
    {
      "epoch": 0.06342494714587738,
      "grad_norm": 7.273919582366943,
      "learning_rate": 5e-05,
      "loss": 3.9176,
      "step": 195
    },
    {
      "epoch": 0.063750203285087,
      "grad_norm": 6.896090030670166,
      "learning_rate": 5e-05,
      "loss": 3.8408,
      "step": 196
    },
    {
      "epoch": 0.06407545942429663,
      "grad_norm": 7.282253265380859,
      "learning_rate": 5e-05,
      "loss": 3.6903,
      "step": 197
    },
    {
      "epoch": 0.06440071556350627,
      "grad_norm": 9.39031982421875,
      "learning_rate": 5e-05,
      "loss": 3.9139,
      "step": 198
    },
    {
      "epoch": 0.06472597170271589,
      "grad_norm": 7.485379695892334,
      "learning_rate": 5e-05,
      "loss": 3.8522,
      "step": 199
    },
    {
      "epoch": 0.06505122784192552,
      "grad_norm": 7.848803997039795,
      "learning_rate": 5e-05,
      "loss": 3.879,
      "step": 200
    },
    {
      "epoch": 0.06537648398113514,
      "grad_norm": 7.829058647155762,
      "learning_rate": 5e-05,
      "loss": 4.0283,
      "step": 201
    },
    {
      "epoch": 0.06570174012034477,
      "grad_norm": 8.984028816223145,
      "learning_rate": 5e-05,
      "loss": 3.8663,
      "step": 202
    },
    {
      "epoch": 0.0660269962595544,
      "grad_norm": 7.604732513427734,
      "learning_rate": 5e-05,
      "loss": 3.7871,
      "step": 203
    },
    {
      "epoch": 0.06635225239876402,
      "grad_norm": 6.779748916625977,
      "learning_rate": 5e-05,
      "loss": 3.9423,
      "step": 204
    },
    {
      "epoch": 0.06667750853797365,
      "grad_norm": 8.93659782409668,
      "learning_rate": 5e-05,
      "loss": 4.0208,
      "step": 205
    },
    {
      "epoch": 0.06700276467718329,
      "grad_norm": 6.093626022338867,
      "learning_rate": 5e-05,
      "loss": 3.8828,
      "step": 206
    },
    {
      "epoch": 0.06732802081639291,
      "grad_norm": 6.105995178222656,
      "learning_rate": 5e-05,
      "loss": 4.0983,
      "step": 207
    },
    {
      "epoch": 0.06765327695560254,
      "grad_norm": 7.379316329956055,
      "learning_rate": 5e-05,
      "loss": 4.0493,
      "step": 208
    },
    {
      "epoch": 0.06797853309481217,
      "grad_norm": 6.404873847961426,
      "learning_rate": 5e-05,
      "loss": 3.9271,
      "step": 209
    },
    {
      "epoch": 0.06830378923402179,
      "grad_norm": 7.560967445373535,
      "learning_rate": 5e-05,
      "loss": 3.8633,
      "step": 210
    },
    {
      "epoch": 0.06862904537323142,
      "grad_norm": 6.042522430419922,
      "learning_rate": 5e-05,
      "loss": 3.7389,
      "step": 211
    },
    {
      "epoch": 0.06895430151244104,
      "grad_norm": 6.4881367683410645,
      "learning_rate": 5e-05,
      "loss": 3.8196,
      "step": 212
    },
    {
      "epoch": 0.06927955765165067,
      "grad_norm": 6.52613639831543,
      "learning_rate": 5e-05,
      "loss": 3.7737,
      "step": 213
    },
    {
      "epoch": 0.06960481379086031,
      "grad_norm": 4.999444007873535,
      "learning_rate": 5e-05,
      "loss": 3.8722,
      "step": 214
    },
    {
      "epoch": 0.06993006993006994,
      "grad_norm": 7.060845851898193,
      "learning_rate": 5e-05,
      "loss": 3.774,
      "step": 215
    },
    {
      "epoch": 0.07025532606927956,
      "grad_norm": 8.545415878295898,
      "learning_rate": 5e-05,
      "loss": 3.8479,
      "step": 216
    },
    {
      "epoch": 0.07058058220848919,
      "grad_norm": 7.625663757324219,
      "learning_rate": 5e-05,
      "loss": 3.5068,
      "step": 217
    },
    {
      "epoch": 0.07090583834769881,
      "grad_norm": 7.191437244415283,
      "learning_rate": 5e-05,
      "loss": 3.7885,
      "step": 218
    },
    {
      "epoch": 0.07123109448690844,
      "grad_norm": 7.386499881744385,
      "learning_rate": 5e-05,
      "loss": 3.9494,
      "step": 219
    },
    {
      "epoch": 0.07155635062611806,
      "grad_norm": 5.616601943969727,
      "learning_rate": 5e-05,
      "loss": 3.8093,
      "step": 220
    },
    {
      "epoch": 0.07188160676532769,
      "grad_norm": 6.17822265625,
      "learning_rate": 5e-05,
      "loss": 3.8981,
      "step": 221
    },
    {
      "epoch": 0.07220686290453732,
      "grad_norm": 6.138426303863525,
      "learning_rate": 5e-05,
      "loss": 4.0091,
      "step": 222
    },
    {
      "epoch": 0.07253211904374696,
      "grad_norm": 6.6297831535339355,
      "learning_rate": 5e-05,
      "loss": 3.9291,
      "step": 223
    },
    {
      "epoch": 0.07285737518295658,
      "grad_norm": 6.557385444641113,
      "learning_rate": 5e-05,
      "loss": 3.8338,
      "step": 224
    },
    {
      "epoch": 0.07318263132216621,
      "grad_norm": 6.9579291343688965,
      "learning_rate": 5e-05,
      "loss": 3.8158,
      "step": 225
    },
    {
      "epoch": 0.07350788746137583,
      "grad_norm": 7.129207611083984,
      "learning_rate": 5e-05,
      "loss": 4.1731,
      "step": 226
    },
    {
      "epoch": 0.07383314360058546,
      "grad_norm": 6.645360946655273,
      "learning_rate": 5e-05,
      "loss": 3.6926,
      "step": 227
    },
    {
      "epoch": 0.07415839973979509,
      "grad_norm": 8.101895332336426,
      "learning_rate": 5e-05,
      "loss": 4.3064,
      "step": 228
    },
    {
      "epoch": 0.07448365587900471,
      "grad_norm": 7.812802791595459,
      "learning_rate": 5e-05,
      "loss": 3.7983,
      "step": 229
    },
    {
      "epoch": 0.07480891201821434,
      "grad_norm": 7.278988838195801,
      "learning_rate": 5e-05,
      "loss": 3.9539,
      "step": 230
    },
    {
      "epoch": 0.07513416815742398,
      "grad_norm": 7.909803867340088,
      "learning_rate": 5e-05,
      "loss": 3.5888,
      "step": 231
    },
    {
      "epoch": 0.0754594242966336,
      "grad_norm": 5.668457984924316,
      "learning_rate": 5e-05,
      "loss": 3.8219,
      "step": 232
    },
    {
      "epoch": 0.07578468043584323,
      "grad_norm": 6.159639358520508,
      "learning_rate": 5e-05,
      "loss": 4.0184,
      "step": 233
    },
    {
      "epoch": 0.07610993657505286,
      "grad_norm": 6.18869161605835,
      "learning_rate": 5e-05,
      "loss": 3.7595,
      "step": 234
    },
    {
      "epoch": 0.07643519271426248,
      "grad_norm": 5.471868991851807,
      "learning_rate": 5e-05,
      "loss": 3.9409,
      "step": 235
    },
    {
      "epoch": 0.07676044885347211,
      "grad_norm": 7.921130180358887,
      "learning_rate": 5e-05,
      "loss": 4.1452,
      "step": 236
    },
    {
      "epoch": 0.07708570499268173,
      "grad_norm": 6.49941349029541,
      "learning_rate": 5e-05,
      "loss": 3.8261,
      "step": 237
    },
    {
      "epoch": 0.07741096113189136,
      "grad_norm": 10.190372467041016,
      "learning_rate": 5e-05,
      "loss": 3.6134,
      "step": 238
    },
    {
      "epoch": 0.07773621727110099,
      "grad_norm": 5.995229244232178,
      "learning_rate": 5e-05,
      "loss": 3.7563,
      "step": 239
    },
    {
      "epoch": 0.07806147341031063,
      "grad_norm": 8.94497299194336,
      "learning_rate": 5e-05,
      "loss": 3.5379,
      "step": 240
    },
    {
      "epoch": 0.07838672954952025,
      "grad_norm": 10.990089416503906,
      "learning_rate": 5e-05,
      "loss": 3.9176,
      "step": 241
    },
    {
      "epoch": 0.07871198568872988,
      "grad_norm": 7.899653434753418,
      "learning_rate": 5e-05,
      "loss": 3.7961,
      "step": 242
    },
    {
      "epoch": 0.0790372418279395,
      "grad_norm": 7.264082908630371,
      "learning_rate": 5e-05,
      "loss": 3.5957,
      "step": 243
    },
    {
      "epoch": 0.07936249796714913,
      "grad_norm": 5.855433940887451,
      "learning_rate": 5e-05,
      "loss": 3.5913,
      "step": 244
    },
    {
      "epoch": 0.07968775410635875,
      "grad_norm": 6.854794979095459,
      "learning_rate": 5e-05,
      "loss": 3.6167,
      "step": 245
    },
    {
      "epoch": 0.08001301024556838,
      "grad_norm": 7.06243896484375,
      "learning_rate": 5e-05,
      "loss": 3.7909,
      "step": 246
    },
    {
      "epoch": 0.080338266384778,
      "grad_norm": 8.033863067626953,
      "learning_rate": 5e-05,
      "loss": 4.046,
      "step": 247
    },
    {
      "epoch": 0.08066352252398765,
      "grad_norm": 6.078402519226074,
      "learning_rate": 5e-05,
      "loss": 3.3269,
      "step": 248
    },
    {
      "epoch": 0.08098877866319727,
      "grad_norm": 9.511942863464355,
      "learning_rate": 5e-05,
      "loss": 3.5749,
      "step": 249
    },
    {
      "epoch": 0.0813140348024069,
      "grad_norm": 9.74225902557373,
      "learning_rate": 5e-05,
      "loss": 3.9162,
      "step": 250
    },
    {
      "epoch": 0.08163929094161652,
      "grad_norm": 6.432509422302246,
      "learning_rate": 5e-05,
      "loss": 3.8754,
      "step": 251
    },
    {
      "epoch": 0.08196454708082615,
      "grad_norm": 7.885379314422607,
      "learning_rate": 5e-05,
      "loss": 3.7214,
      "step": 252
    },
    {
      "epoch": 0.08228980322003578,
      "grad_norm": 11.552560806274414,
      "learning_rate": 5e-05,
      "loss": 3.7367,
      "step": 253
    },
    {
      "epoch": 0.0826150593592454,
      "grad_norm": 9.054500579833984,
      "learning_rate": 5e-05,
      "loss": 3.5476,
      "step": 254
    },
    {
      "epoch": 0.08294031549845503,
      "grad_norm": 5.916128635406494,
      "learning_rate": 5e-05,
      "loss": 3.695,
      "step": 255
    },
    {
      "epoch": 0.08326557163766467,
      "grad_norm": 10.65311050415039,
      "learning_rate": 5e-05,
      "loss": 4.1597,
      "step": 256
    },
    {
      "epoch": 0.0835908277768743,
      "grad_norm": 13.63244342803955,
      "learning_rate": 5e-05,
      "loss": 3.5796,
      "step": 257
    },
    {
      "epoch": 0.08391608391608392,
      "grad_norm": 10.830595970153809,
      "learning_rate": 5e-05,
      "loss": 3.4825,
      "step": 258
    },
    {
      "epoch": 0.08424134005529355,
      "grad_norm": 5.9953718185424805,
      "learning_rate": 5e-05,
      "loss": 3.792,
      "step": 259
    },
    {
      "epoch": 0.08456659619450317,
      "grad_norm": 12.76282787322998,
      "learning_rate": 5e-05,
      "loss": 3.5532,
      "step": 260
    },
    {
      "epoch": 0.0848918523337128,
      "grad_norm": 18.605255126953125,
      "learning_rate": 5e-05,
      "loss": 3.7788,
      "step": 261
    },
    {
      "epoch": 0.08521710847292242,
      "grad_norm": 12.753776550292969,
      "learning_rate": 5e-05,
      "loss": 3.7542,
      "step": 262
    },
    {
      "epoch": 0.08554236461213205,
      "grad_norm": 7.8098673820495605,
      "learning_rate": 5e-05,
      "loss": 4.4529,
      "step": 263
    },
    {
      "epoch": 0.08586762075134168,
      "grad_norm": 9.642732620239258,
      "learning_rate": 5e-05,
      "loss": 3.8515,
      "step": 264
    },
    {
      "epoch": 0.08619287689055131,
      "grad_norm": 5.820125102996826,
      "learning_rate": 5e-05,
      "loss": 4.3286,
      "step": 265
    },
    {
      "epoch": 0.08651813302976094,
      "grad_norm": 9.613585472106934,
      "learning_rate": 5e-05,
      "loss": 3.9569,
      "step": 266
    },
    {
      "epoch": 0.08684338916897057,
      "grad_norm": 9.211997985839844,
      "learning_rate": 5e-05,
      "loss": 3.9244,
      "step": 267
    },
    {
      "epoch": 0.08716864530818019,
      "grad_norm": 6.351746559143066,
      "learning_rate": 5e-05,
      "loss": 3.6584,
      "step": 268
    },
    {
      "epoch": 0.08749390144738982,
      "grad_norm": 6.802426815032959,
      "learning_rate": 5e-05,
      "loss": 3.8361,
      "step": 269
    },
    {
      "epoch": 0.08781915758659944,
      "grad_norm": 7.498976707458496,
      "learning_rate": 5e-05,
      "loss": 3.6589,
      "step": 270
    },
    {
      "epoch": 0.08814441372580907,
      "grad_norm": 6.058091163635254,
      "learning_rate": 5e-05,
      "loss": 3.6699,
      "step": 271
    },
    {
      "epoch": 0.0884696698650187,
      "grad_norm": 5.347617149353027,
      "learning_rate": 5e-05,
      "loss": 3.586,
      "step": 272
    },
    {
      "epoch": 0.08879492600422834,
      "grad_norm": 6.720355033874512,
      "learning_rate": 5e-05,
      "loss": 3.9508,
      "step": 273
    },
    {
      "epoch": 0.08912018214343796,
      "grad_norm": 5.8187174797058105,
      "learning_rate": 5e-05,
      "loss": 4.1922,
      "step": 274
    },
    {
      "epoch": 0.08944543828264759,
      "grad_norm": 4.981271743774414,
      "learning_rate": 5e-05,
      "loss": 3.5997,
      "step": 275
    },
    {
      "epoch": 0.08977069442185721,
      "grad_norm": 6.238826751708984,
      "learning_rate": 5e-05,
      "loss": 3.6929,
      "step": 276
    },
    {
      "epoch": 0.09009595056106684,
      "grad_norm": 7.073620796203613,
      "learning_rate": 5e-05,
      "loss": 3.7813,
      "step": 277
    },
    {
      "epoch": 0.09042120670027647,
      "grad_norm": 7.445998668670654,
      "learning_rate": 5e-05,
      "loss": 3.5475,
      "step": 278
    },
    {
      "epoch": 0.09074646283948609,
      "grad_norm": 6.120103359222412,
      "learning_rate": 5e-05,
      "loss": 3.7499,
      "step": 279
    },
    {
      "epoch": 0.09107171897869572,
      "grad_norm": 8.138337135314941,
      "learning_rate": 5e-05,
      "loss": 3.8753,
      "step": 280
    },
    {
      "epoch": 0.09139697511790534,
      "grad_norm": 7.516664981842041,
      "learning_rate": 5e-05,
      "loss": 3.6093,
      "step": 281
    },
    {
      "epoch": 0.09172223125711498,
      "grad_norm": 5.630866050720215,
      "learning_rate": 5e-05,
      "loss": 3.7269,
      "step": 282
    },
    {
      "epoch": 0.09204748739632461,
      "grad_norm": 5.958463668823242,
      "learning_rate": 5e-05,
      "loss": 3.7448,
      "step": 283
    },
    {
      "epoch": 0.09237274353553424,
      "grad_norm": 6.990318298339844,
      "learning_rate": 5e-05,
      "loss": 3.6994,
      "step": 284
    },
    {
      "epoch": 0.09269799967474386,
      "grad_norm": 6.364505767822266,
      "learning_rate": 5e-05,
      "loss": 3.5316,
      "step": 285
    },
    {
      "epoch": 0.09302325581395349,
      "grad_norm": 6.308237552642822,
      "learning_rate": 5e-05,
      "loss": 4.1899,
      "step": 286
    },
    {
      "epoch": 0.09334851195316311,
      "grad_norm": 8.585831642150879,
      "learning_rate": 5e-05,
      "loss": 3.7078,
      "step": 287
    },
    {
      "epoch": 0.09367376809237274,
      "grad_norm": 6.02251672744751,
      "learning_rate": 5e-05,
      "loss": 3.7081,
      "step": 288
    },
    {
      "epoch": 0.09399902423158236,
      "grad_norm": 6.891519546508789,
      "learning_rate": 5e-05,
      "loss": 3.9432,
      "step": 289
    },
    {
      "epoch": 0.094324280370792,
      "grad_norm": 8.65449047088623,
      "learning_rate": 5e-05,
      "loss": 3.4704,
      "step": 290
    },
    {
      "epoch": 0.09464953651000163,
      "grad_norm": 6.133912563323975,
      "learning_rate": 5e-05,
      "loss": 3.8847,
      "step": 291
    },
    {
      "epoch": 0.09497479264921126,
      "grad_norm": 6.619656085968018,
      "learning_rate": 5e-05,
      "loss": 3.5818,
      "step": 292
    },
    {
      "epoch": 0.09530004878842088,
      "grad_norm": 9.706931114196777,
      "learning_rate": 5e-05,
      "loss": 3.6839,
      "step": 293
    },
    {
      "epoch": 0.09562530492763051,
      "grad_norm": 6.43947172164917,
      "learning_rate": 5e-05,
      "loss": 4.0691,
      "step": 294
    },
    {
      "epoch": 0.09595056106684013,
      "grad_norm": 7.45628547668457,
      "learning_rate": 5e-05,
      "loss": 3.9546,
      "step": 295
    },
    {
      "epoch": 0.09627581720604976,
      "grad_norm": 9.464739799499512,
      "learning_rate": 5e-05,
      "loss": 3.8893,
      "step": 296
    },
    {
      "epoch": 0.09660107334525939,
      "grad_norm": 9.263232231140137,
      "learning_rate": 5e-05,
      "loss": 4.3718,
      "step": 297
    },
    {
      "epoch": 0.09692632948446903,
      "grad_norm": 6.793147087097168,
      "learning_rate": 5e-05,
      "loss": 3.7036,
      "step": 298
    },
    {
      "epoch": 0.09725158562367865,
      "grad_norm": 12.16869831085205,
      "learning_rate": 5e-05,
      "loss": 4.2924,
      "step": 299
    },
    {
      "epoch": 0.09757684176288828,
      "grad_norm": 10.058348655700684,
      "learning_rate": 5e-05,
      "loss": 3.852,
      "step": 300
    },
    {
      "epoch": 0.0979020979020979,
      "grad_norm": 5.966858386993408,
      "learning_rate": 5e-05,
      "loss": 3.7514,
      "step": 301
    },
    {
      "epoch": 0.09822735404130753,
      "grad_norm": 9.075318336486816,
      "learning_rate": 5e-05,
      "loss": 3.6808,
      "step": 302
    },
    {
      "epoch": 0.09855261018051716,
      "grad_norm": 11.372644424438477,
      "learning_rate": 5e-05,
      "loss": 4.0671,
      "step": 303
    },
    {
      "epoch": 0.09887786631972678,
      "grad_norm": 12.080697059631348,
      "learning_rate": 5e-05,
      "loss": 3.2312,
      "step": 304
    },
    {
      "epoch": 0.09920312245893641,
      "grad_norm": 5.336820125579834,
      "learning_rate": 5e-05,
      "loss": 3.5947,
      "step": 305
    },
    {
      "epoch": 0.09952837859814603,
      "grad_norm": 7.266972064971924,
      "learning_rate": 5e-05,
      "loss": 3.1227,
      "step": 306
    },
    {
      "epoch": 0.09985363473735567,
      "grad_norm": 6.334729194641113,
      "learning_rate": 5e-05,
      "loss": 3.6156,
      "step": 307
    },
    {
      "epoch": 0.1001788908765653,
      "grad_norm": 5.643017768859863,
      "learning_rate": 5e-05,
      "loss": 3.6258,
      "step": 308
    },
    {
      "epoch": 0.10050414701577493,
      "grad_norm": 5.640905380249023,
      "learning_rate": 5e-05,
      "loss": 3.9051,
      "step": 309
    },
    {
      "epoch": 0.10082940315498455,
      "grad_norm": 6.985749244689941,
      "learning_rate": 5e-05,
      "loss": 3.6725,
      "step": 310
    },
    {
      "epoch": 0.10115465929419418,
      "grad_norm": 6.893199443817139,
      "learning_rate": 5e-05,
      "loss": 3.4541,
      "step": 311
    },
    {
      "epoch": 0.1014799154334038,
      "grad_norm": 6.803256511688232,
      "learning_rate": 5e-05,
      "loss": 3.0762,
      "step": 312
    },
    {
      "epoch": 0.10180517157261343,
      "grad_norm": 8.491405487060547,
      "learning_rate": 5e-05,
      "loss": 3.719,
      "step": 313
    },
    {
      "epoch": 0.10213042771182305,
      "grad_norm": 5.912895202636719,
      "learning_rate": 5e-05,
      "loss": 3.6613,
      "step": 314
    },
    {
      "epoch": 0.1024556838510327,
      "grad_norm": 6.211380958557129,
      "learning_rate": 5e-05,
      "loss": 3.632,
      "step": 315
    },
    {
      "epoch": 0.10278093999024232,
      "grad_norm": 8.083343505859375,
      "learning_rate": 5e-05,
      "loss": 3.5327,
      "step": 316
    },
    {
      "epoch": 0.10310619612945195,
      "grad_norm": 8.091614723205566,
      "learning_rate": 5e-05,
      "loss": 3.8166,
      "step": 317
    },
    {
      "epoch": 0.10343145226866157,
      "grad_norm": 5.631373405456543,
      "learning_rate": 5e-05,
      "loss": 3.6482,
      "step": 318
    },
    {
      "epoch": 0.1037567084078712,
      "grad_norm": 12.532264709472656,
      "learning_rate": 5e-05,
      "loss": 3.5283,
      "step": 319
    },
    {
      "epoch": 0.10408196454708082,
      "grad_norm": 5.990050315856934,
      "learning_rate": 5e-05,
      "loss": 3.9679,
      "step": 320
    },
    {
      "epoch": 0.10440722068629045,
      "grad_norm": 6.2988667488098145,
      "learning_rate": 5e-05,
      "loss": 3.8285,
      "step": 321
    },
    {
      "epoch": 0.10473247682550008,
      "grad_norm": 8.320550918579102,
      "learning_rate": 5e-05,
      "loss": 4.0295,
      "step": 322
    },
    {
      "epoch": 0.10505773296470972,
      "grad_norm": 6.640725612640381,
      "learning_rate": 5e-05,
      "loss": 3.5094,
      "step": 323
    },
    {
      "epoch": 0.10538298910391934,
      "grad_norm": 6.340143203735352,
      "learning_rate": 5e-05,
      "loss": 3.6144,
      "step": 324
    },
    {
      "epoch": 0.10570824524312897,
      "grad_norm": 7.403520584106445,
      "learning_rate": 5e-05,
      "loss": 3.9676,
      "step": 325
    },
    {
      "epoch": 0.1060335013823386,
      "grad_norm": 7.462515354156494,
      "learning_rate": 5e-05,
      "loss": 3.7215,
      "step": 326
    },
    {
      "epoch": 0.10635875752154822,
      "grad_norm": 5.612910747528076,
      "learning_rate": 5e-05,
      "loss": 3.5211,
      "step": 327
    },
    {
      "epoch": 0.10668401366075785,
      "grad_norm": 7.502828598022461,
      "learning_rate": 5e-05,
      "loss": 4.0133,
      "step": 328
    },
    {
      "epoch": 0.10700926979996747,
      "grad_norm": 8.6078462600708,
      "learning_rate": 5e-05,
      "loss": 4.1303,
      "step": 329
    },
    {
      "epoch": 0.1073345259391771,
      "grad_norm": 9.176727294921875,
      "learning_rate": 5e-05,
      "loss": 3.8978,
      "step": 330
    },
    {
      "epoch": 0.10765978207838672,
      "grad_norm": 10.041065216064453,
      "learning_rate": 5e-05,
      "loss": 4.0287,
      "step": 331
    },
    {
      "epoch": 0.10798503821759636,
      "grad_norm": 9.741332054138184,
      "learning_rate": 5e-05,
      "loss": 3.5463,
      "step": 332
    },
    {
      "epoch": 0.10831029435680599,
      "grad_norm": 7.8142499923706055,
      "learning_rate": 5e-05,
      "loss": 3.7777,
      "step": 333
    },
    {
      "epoch": 0.10863555049601561,
      "grad_norm": 8.65985107421875,
      "learning_rate": 5e-05,
      "loss": 3.7169,
      "step": 334
    },
    {
      "epoch": 0.10896080663522524,
      "grad_norm": 9.955862998962402,
      "learning_rate": 5e-05,
      "loss": 3.4762,
      "step": 335
    },
    {
      "epoch": 0.10928606277443487,
      "grad_norm": 8.422538757324219,
      "learning_rate": 5e-05,
      "loss": 3.8524,
      "step": 336
    },
    {
      "epoch": 0.10961131891364449,
      "grad_norm": 6.849399089813232,
      "learning_rate": 5e-05,
      "loss": 3.5617,
      "step": 337
    },
    {
      "epoch": 0.10993657505285412,
      "grad_norm": 10.709142684936523,
      "learning_rate": 5e-05,
      "loss": 3.8691,
      "step": 338
    },
    {
      "epoch": 0.11026183119206374,
      "grad_norm": 6.636946678161621,
      "learning_rate": 5e-05,
      "loss": 3.9301,
      "step": 339
    },
    {
      "epoch": 0.11058708733127338,
      "grad_norm": 7.364269256591797,
      "learning_rate": 5e-05,
      "loss": 3.485,
      "step": 340
    },
    {
      "epoch": 0.11091234347048301,
      "grad_norm": 12.705086708068848,
      "learning_rate": 5e-05,
      "loss": 3.8413,
      "step": 341
    },
    {
      "epoch": 0.11123759960969264,
      "grad_norm": 6.6930928230285645,
      "learning_rate": 5e-05,
      "loss": 3.8912,
      "step": 342
    },
    {
      "epoch": 0.11156285574890226,
      "grad_norm": 6.823209285736084,
      "learning_rate": 5e-05,
      "loss": 4.2082,
      "step": 343
    },
    {
      "epoch": 0.11188811188811189,
      "grad_norm": 9.133801460266113,
      "learning_rate": 5e-05,
      "loss": 4.0229,
      "step": 344
    },
    {
      "epoch": 0.11221336802732151,
      "grad_norm": 7.471242904663086,
      "learning_rate": 5e-05,
      "loss": 3.6206,
      "step": 345
    },
    {
      "epoch": 0.11253862416653114,
      "grad_norm": 7.450990676879883,
      "learning_rate": 5e-05,
      "loss": 3.7254,
      "step": 346
    },
    {
      "epoch": 0.11286388030574077,
      "grad_norm": 7.53968620300293,
      "learning_rate": 5e-05,
      "loss": 4.0496,
      "step": 347
    },
    {
      "epoch": 0.11318913644495039,
      "grad_norm": 12.383916854858398,
      "learning_rate": 5e-05,
      "loss": 3.6815,
      "step": 348
    },
    {
      "epoch": 0.11351439258416003,
      "grad_norm": 8.754898071289062,
      "learning_rate": 5e-05,
      "loss": 3.5597,
      "step": 349
    },
    {
      "epoch": 0.11383964872336966,
      "grad_norm": 7.65074348449707,
      "learning_rate": 5e-05,
      "loss": 4.0558,
      "step": 350
    },
    {
      "epoch": 0.11416490486257928,
      "grad_norm": 6.735880374908447,
      "learning_rate": 5e-05,
      "loss": 3.5702,
      "step": 351
    },
    {
      "epoch": 0.11449016100178891,
      "grad_norm": 6.371280670166016,
      "learning_rate": 5e-05,
      "loss": 3.7325,
      "step": 352
    },
    {
      "epoch": 0.11481541714099854,
      "grad_norm": 6.2961745262146,
      "learning_rate": 5e-05,
      "loss": 3.8299,
      "step": 353
    },
    {
      "epoch": 0.11514067328020816,
      "grad_norm": 8.073019027709961,
      "learning_rate": 5e-05,
      "loss": 3.77,
      "step": 354
    },
    {
      "epoch": 0.11546592941941779,
      "grad_norm": 7.552728176116943,
      "learning_rate": 5e-05,
      "loss": 3.6974,
      "step": 355
    },
    {
      "epoch": 0.11579118555862741,
      "grad_norm": 6.595133304595947,
      "learning_rate": 5e-05,
      "loss": 3.6737,
      "step": 356
    },
    {
      "epoch": 0.11611644169783705,
      "grad_norm": 7.287491321563721,
      "learning_rate": 5e-05,
      "loss": 3.5135,
      "step": 357
    },
    {
      "epoch": 0.11644169783704668,
      "grad_norm": 8.068704605102539,
      "learning_rate": 5e-05,
      "loss": 3.9036,
      "step": 358
    },
    {
      "epoch": 0.1167669539762563,
      "grad_norm": 6.8040618896484375,
      "learning_rate": 5e-05,
      "loss": 3.8034,
      "step": 359
    },
    {
      "epoch": 0.11709221011546593,
      "grad_norm": 9.113652229309082,
      "learning_rate": 5e-05,
      "loss": 3.4709,
      "step": 360
    },
    {
      "epoch": 0.11741746625467556,
      "grad_norm": 8.15011978149414,
      "learning_rate": 5e-05,
      "loss": 4.111,
      "step": 361
    },
    {
      "epoch": 0.11774272239388518,
      "grad_norm": 6.63869047164917,
      "learning_rate": 5e-05,
      "loss": 3.8713,
      "step": 362
    },
    {
      "epoch": 0.11806797853309481,
      "grad_norm": 6.785707473754883,
      "learning_rate": 5e-05,
      "loss": 3.1996,
      "step": 363
    },
    {
      "epoch": 0.11839323467230443,
      "grad_norm": 7.099983215332031,
      "learning_rate": 5e-05,
      "loss": 3.4236,
      "step": 364
    },
    {
      "epoch": 0.11871849081151407,
      "grad_norm": 7.014822006225586,
      "learning_rate": 5e-05,
      "loss": 3.7598,
      "step": 365
    },
    {
      "epoch": 0.1190437469507237,
      "grad_norm": 7.138816833496094,
      "learning_rate": 5e-05,
      "loss": 3.6681,
      "step": 366
    },
    {
      "epoch": 0.11936900308993333,
      "grad_norm": 6.563411235809326,
      "learning_rate": 5e-05,
      "loss": 3.82,
      "step": 367
    },
    {
      "epoch": 0.11969425922914295,
      "grad_norm": 6.389061450958252,
      "learning_rate": 5e-05,
      "loss": 3.7305,
      "step": 368
    },
    {
      "epoch": 0.12001951536835258,
      "grad_norm": 8.009288787841797,
      "learning_rate": 5e-05,
      "loss": 3.9673,
      "step": 369
    },
    {
      "epoch": 0.1203447715075622,
      "grad_norm": 6.436244964599609,
      "learning_rate": 5e-05,
      "loss": 3.6934,
      "step": 370
    },
    {
      "epoch": 0.12067002764677183,
      "grad_norm": 7.818999767303467,
      "learning_rate": 5e-05,
      "loss": 3.8564,
      "step": 371
    },
    {
      "epoch": 0.12099528378598146,
      "grad_norm": 7.891193866729736,
      "learning_rate": 5e-05,
      "loss": 3.9254,
      "step": 372
    },
    {
      "epoch": 0.12132053992519108,
      "grad_norm": 8.381048202514648,
      "learning_rate": 5e-05,
      "loss": 3.8966,
      "step": 373
    },
    {
      "epoch": 0.12164579606440072,
      "grad_norm": 7.328115940093994,
      "learning_rate": 5e-05,
      "loss": 3.4804,
      "step": 374
    },
    {
      "epoch": 0.12197105220361035,
      "grad_norm": 7.0525922775268555,
      "learning_rate": 5e-05,
      "loss": 4.0177,
      "step": 375
    },
    {
      "epoch": 0.12229630834281997,
      "grad_norm": 7.212350845336914,
      "learning_rate": 5e-05,
      "loss": 3.4131,
      "step": 376
    },
    {
      "epoch": 0.1226215644820296,
      "grad_norm": 6.808897972106934,
      "learning_rate": 5e-05,
      "loss": 3.5174,
      "step": 377
    },
    {
      "epoch": 0.12294682062123923,
      "grad_norm": 7.094473838806152,
      "learning_rate": 5e-05,
      "loss": 3.7852,
      "step": 378
    },
    {
      "epoch": 0.12327207676044885,
      "grad_norm": 6.998628616333008,
      "learning_rate": 5e-05,
      "loss": 3.8094,
      "step": 379
    },
    {
      "epoch": 0.12359733289965848,
      "grad_norm": 7.043560028076172,
      "learning_rate": 5e-05,
      "loss": 3.6862,
      "step": 380
    },
    {
      "epoch": 0.1239225890388681,
      "grad_norm": 6.198429107666016,
      "learning_rate": 5e-05,
      "loss": 3.5462,
      "step": 381
    },
    {
      "epoch": 0.12424784517807774,
      "grad_norm": 6.5926513671875,
      "learning_rate": 5e-05,
      "loss": 3.9851,
      "step": 382
    },
    {
      "epoch": 0.12457310131728737,
      "grad_norm": 5.893482208251953,
      "learning_rate": 5e-05,
      "loss": 3.6685,
      "step": 383
    },
    {
      "epoch": 0.124898357456497,
      "grad_norm": 5.886164665222168,
      "learning_rate": 5e-05,
      "loss": 3.7367,
      "step": 384
    },
    {
      "epoch": 0.1252236135957066,
      "grad_norm": 7.275190353393555,
      "learning_rate": 5e-05,
      "loss": 3.4105,
      "step": 385
    },
    {
      "epoch": 0.12554886973491625,
      "grad_norm": 8.864086151123047,
      "learning_rate": 5e-05,
      "loss": 4.0736,
      "step": 386
    },
    {
      "epoch": 0.1258741258741259,
      "grad_norm": 9.517216682434082,
      "learning_rate": 5e-05,
      "loss": 3.6961,
      "step": 387
    },
    {
      "epoch": 0.1261993820133355,
      "grad_norm": 8.437984466552734,
      "learning_rate": 5e-05,
      "loss": 4.1894,
      "step": 388
    },
    {
      "epoch": 0.12652463815254514,
      "grad_norm": 9.38377571105957,
      "learning_rate": 5e-05,
      "loss": 3.9029,
      "step": 389
    },
    {
      "epoch": 0.12684989429175475,
      "grad_norm": 8.621910095214844,
      "learning_rate": 5e-05,
      "loss": 3.9334,
      "step": 390
    },
    {
      "epoch": 0.1271751504309644,
      "grad_norm": 7.772785186767578,
      "learning_rate": 5e-05,
      "loss": 3.4678,
      "step": 391
    },
    {
      "epoch": 0.127500406570174,
      "grad_norm": 8.752019882202148,
      "learning_rate": 5e-05,
      "loss": 3.62,
      "step": 392
    },
    {
      "epoch": 0.12782566270938364,
      "grad_norm": 7.4593706130981445,
      "learning_rate": 5e-05,
      "loss": 3.907,
      "step": 393
    },
    {
      "epoch": 0.12815091884859325,
      "grad_norm": 7.014523983001709,
      "learning_rate": 5e-05,
      "loss": 3.7242,
      "step": 394
    },
    {
      "epoch": 0.1284761749878029,
      "grad_norm": 7.254335403442383,
      "learning_rate": 5e-05,
      "loss": 3.8927,
      "step": 395
    },
    {
      "epoch": 0.12880143112701253,
      "grad_norm": 7.555474281311035,
      "learning_rate": 5e-05,
      "loss": 4.3168,
      "step": 396
    },
    {
      "epoch": 0.12912668726622215,
      "grad_norm": 11.899949073791504,
      "learning_rate": 5e-05,
      "loss": 3.6753,
      "step": 397
    },
    {
      "epoch": 0.12945194340543179,
      "grad_norm": 11.901144027709961,
      "learning_rate": 5e-05,
      "loss": 3.7524,
      "step": 398
    },
    {
      "epoch": 0.1297771995446414,
      "grad_norm": 9.584845542907715,
      "learning_rate": 5e-05,
      "loss": 3.4015,
      "step": 399
    },
    {
      "epoch": 0.13010245568385104,
      "grad_norm": 12.348978042602539,
      "learning_rate": 5e-05,
      "loss": 3.6966,
      "step": 400
    },
    {
      "epoch": 0.13042771182306065,
      "grad_norm": 12.886831283569336,
      "learning_rate": 5e-05,
      "loss": 4.5981,
      "step": 401
    },
    {
      "epoch": 0.1307529679622703,
      "grad_norm": 7.066255569458008,
      "learning_rate": 5e-05,
      "loss": 3.6408,
      "step": 402
    },
    {
      "epoch": 0.13107822410147993,
      "grad_norm": 7.1310014724731445,
      "learning_rate": 5e-05,
      "loss": 3.7652,
      "step": 403
    },
    {
      "epoch": 0.13140348024068954,
      "grad_norm": 7.658654689788818,
      "learning_rate": 5e-05,
      "loss": 3.9908,
      "step": 404
    },
    {
      "epoch": 0.13172873637989918,
      "grad_norm": 9.139669418334961,
      "learning_rate": 5e-05,
      "loss": 3.7055,
      "step": 405
    },
    {
      "epoch": 0.1320539925191088,
      "grad_norm": 7.406591892242432,
      "learning_rate": 5e-05,
      "loss": 3.9435,
      "step": 406
    },
    {
      "epoch": 0.13237924865831843,
      "grad_norm": 7.888886451721191,
      "learning_rate": 5e-05,
      "loss": 3.7047,
      "step": 407
    },
    {
      "epoch": 0.13270450479752804,
      "grad_norm": 6.58457088470459,
      "learning_rate": 5e-05,
      "loss": 3.5882,
      "step": 408
    },
    {
      "epoch": 0.13302976093673768,
      "grad_norm": 6.361485958099365,
      "learning_rate": 5e-05,
      "loss": 3.6571,
      "step": 409
    },
    {
      "epoch": 0.1333550170759473,
      "grad_norm": 10.977415084838867,
      "learning_rate": 5e-05,
      "loss": 3.9192,
      "step": 410
    },
    {
      "epoch": 0.13368027321515694,
      "grad_norm": 8.509581565856934,
      "learning_rate": 5e-05,
      "loss": 3.7566,
      "step": 411
    },
    {
      "epoch": 0.13400552935436658,
      "grad_norm": 7.781307220458984,
      "learning_rate": 5e-05,
      "loss": 4.1816,
      "step": 412
    },
    {
      "epoch": 0.1343307854935762,
      "grad_norm": 7.275979518890381,
      "learning_rate": 5e-05,
      "loss": 3.2031,
      "step": 413
    },
    {
      "epoch": 0.13465604163278583,
      "grad_norm": 7.543152332305908,
      "learning_rate": 5e-05,
      "loss": 3.9525,
      "step": 414
    },
    {
      "epoch": 0.13498129777199544,
      "grad_norm": 9.093851089477539,
      "learning_rate": 5e-05,
      "loss": 3.9126,
      "step": 415
    },
    {
      "epoch": 0.13530655391120508,
      "grad_norm": 12.760071754455566,
      "learning_rate": 5e-05,
      "loss": 3.7383,
      "step": 416
    },
    {
      "epoch": 0.1356318100504147,
      "grad_norm": 8.025795936584473,
      "learning_rate": 5e-05,
      "loss": 3.5959,
      "step": 417
    },
    {
      "epoch": 0.13595706618962433,
      "grad_norm": 7.363426685333252,
      "learning_rate": 5e-05,
      "loss": 3.7238,
      "step": 418
    },
    {
      "epoch": 0.13628232232883394,
      "grad_norm": 8.554017066955566,
      "learning_rate": 5e-05,
      "loss": 3.3142,
      "step": 419
    },
    {
      "epoch": 0.13660757846804358,
      "grad_norm": 7.679929256439209,
      "learning_rate": 5e-05,
      "loss": 3.6632,
      "step": 420
    },
    {
      "epoch": 0.13693283460725322,
      "grad_norm": 7.977594375610352,
      "learning_rate": 5e-05,
      "loss": 3.3469,
      "step": 421
    },
    {
      "epoch": 0.13725809074646284,
      "grad_norm": 7.612384796142578,
      "learning_rate": 5e-05,
      "loss": 3.6385,
      "step": 422
    },
    {
      "epoch": 0.13758334688567248,
      "grad_norm": 9.067974090576172,
      "learning_rate": 5e-05,
      "loss": 3.7935,
      "step": 423
    },
    {
      "epoch": 0.1379086030248821,
      "grad_norm": 9.513571739196777,
      "learning_rate": 5e-05,
      "loss": 4.0498,
      "step": 424
    },
    {
      "epoch": 0.13823385916409173,
      "grad_norm": 10.234723091125488,
      "learning_rate": 5e-05,
      "loss": 3.9196,
      "step": 425
    },
    {
      "epoch": 0.13855911530330134,
      "grad_norm": 8.635189056396484,
      "learning_rate": 5e-05,
      "loss": 3.8482,
      "step": 426
    },
    {
      "epoch": 0.13888437144251098,
      "grad_norm": 10.970733642578125,
      "learning_rate": 5e-05,
      "loss": 3.765,
      "step": 427
    },
    {
      "epoch": 0.13920962758172062,
      "grad_norm": 9.9661226272583,
      "learning_rate": 5e-05,
      "loss": 3.939,
      "step": 428
    },
    {
      "epoch": 0.13953488372093023,
      "grad_norm": 9.381548881530762,
      "learning_rate": 5e-05,
      "loss": 3.749,
      "step": 429
    },
    {
      "epoch": 0.13986013986013987,
      "grad_norm": 8.287264823913574,
      "learning_rate": 5e-05,
      "loss": 3.7818,
      "step": 430
    },
    {
      "epoch": 0.14018539599934948,
      "grad_norm": 8.97390365600586,
      "learning_rate": 5e-05,
      "loss": 4.0317,
      "step": 431
    },
    {
      "epoch": 0.14051065213855912,
      "grad_norm": 7.877195835113525,
      "learning_rate": 5e-05,
      "loss": 3.5584,
      "step": 432
    },
    {
      "epoch": 0.14083590827776873,
      "grad_norm": 9.581697463989258,
      "learning_rate": 5e-05,
      "loss": 3.4095,
      "step": 433
    },
    {
      "epoch": 0.14116116441697837,
      "grad_norm": 17.695627212524414,
      "learning_rate": 5e-05,
      "loss": 4.3531,
      "step": 434
    },
    {
      "epoch": 0.141486420556188,
      "grad_norm": 8.333785057067871,
      "learning_rate": 5e-05,
      "loss": 3.3827,
      "step": 435
    },
    {
      "epoch": 0.14181167669539763,
      "grad_norm": 7.970407009124756,
      "learning_rate": 5e-05,
      "loss": 3.5483,
      "step": 436
    },
    {
      "epoch": 0.14213693283460727,
      "grad_norm": 9.061053276062012,
      "learning_rate": 5e-05,
      "loss": 3.7439,
      "step": 437
    },
    {
      "epoch": 0.14246218897381688,
      "grad_norm": 6.50039005279541,
      "learning_rate": 5e-05,
      "loss": 3.9181,
      "step": 438
    },
    {
      "epoch": 0.14278744511302652,
      "grad_norm": 9.928549766540527,
      "learning_rate": 5e-05,
      "loss": 3.5832,
      "step": 439
    },
    {
      "epoch": 0.14311270125223613,
      "grad_norm": 12.250447273254395,
      "learning_rate": 5e-05,
      "loss": 3.4639,
      "step": 440
    },
    {
      "epoch": 0.14343795739144577,
      "grad_norm": 8.427464485168457,
      "learning_rate": 5e-05,
      "loss": 3.4289,
      "step": 441
    },
    {
      "epoch": 0.14376321353065538,
      "grad_norm": 12.150249481201172,
      "learning_rate": 5e-05,
      "loss": 3.8382,
      "step": 442
    },
    {
      "epoch": 0.14408846966986502,
      "grad_norm": 7.406175136566162,
      "learning_rate": 5e-05,
      "loss": 3.9814,
      "step": 443
    },
    {
      "epoch": 0.14441372580907463,
      "grad_norm": 6.988471031188965,
      "learning_rate": 5e-05,
      "loss": 4.0547,
      "step": 444
    },
    {
      "epoch": 0.14473898194828427,
      "grad_norm": 12.318148612976074,
      "learning_rate": 5e-05,
      "loss": 3.9433,
      "step": 445
    },
    {
      "epoch": 0.1450642380874939,
      "grad_norm": 10.347890853881836,
      "learning_rate": 5e-05,
      "loss": 3.7052,
      "step": 446
    },
    {
      "epoch": 0.14538949422670353,
      "grad_norm": 9.213937759399414,
      "learning_rate": 5e-05,
      "loss": 3.9906,
      "step": 447
    },
    {
      "epoch": 0.14571475036591316,
      "grad_norm": 10.614618301391602,
      "learning_rate": 5e-05,
      "loss": 3.276,
      "step": 448
    },
    {
      "epoch": 0.14604000650512278,
      "grad_norm": 11.268338203430176,
      "learning_rate": 5e-05,
      "loss": 3.5563,
      "step": 449
    },
    {
      "epoch": 0.14636526264433242,
      "grad_norm": 8.418384552001953,
      "learning_rate": 5e-05,
      "loss": 3.4222,
      "step": 450
    },
    {
      "epoch": 0.14669051878354203,
      "grad_norm": 12.904454231262207,
      "learning_rate": 5e-05,
      "loss": 3.7737,
      "step": 451
    },
    {
      "epoch": 0.14701577492275167,
      "grad_norm": 9.767146110534668,
      "learning_rate": 5e-05,
      "loss": 4.0424,
      "step": 452
    },
    {
      "epoch": 0.1473410310619613,
      "grad_norm": 8.333344459533691,
      "learning_rate": 5e-05,
      "loss": 3.7574,
      "step": 453
    },
    {
      "epoch": 0.14766628720117092,
      "grad_norm": 11.907800674438477,
      "learning_rate": 5e-05,
      "loss": 3.7266,
      "step": 454
    },
    {
      "epoch": 0.14799154334038056,
      "grad_norm": 9.306441307067871,
      "learning_rate": 5e-05,
      "loss": 3.8885,
      "step": 455
    },
    {
      "epoch": 0.14831679947959017,
      "grad_norm": 10.486589431762695,
      "learning_rate": 5e-05,
      "loss": 3.7777,
      "step": 456
    },
    {
      "epoch": 0.1486420556187998,
      "grad_norm": 12.291946411132812,
      "learning_rate": 5e-05,
      "loss": 3.6718,
      "step": 457
    },
    {
      "epoch": 0.14896731175800942,
      "grad_norm": 12.743392944335938,
      "learning_rate": 5e-05,
      "loss": 3.6533,
      "step": 458
    },
    {
      "epoch": 0.14929256789721906,
      "grad_norm": 9.82790470123291,
      "learning_rate": 5e-05,
      "loss": 3.8719,
      "step": 459
    },
    {
      "epoch": 0.14961782403642868,
      "grad_norm": 11.749984741210938,
      "learning_rate": 5e-05,
      "loss": 3.495,
      "step": 460
    },
    {
      "epoch": 0.14994308017563832,
      "grad_norm": 11.35322380065918,
      "learning_rate": 5e-05,
      "loss": 4.0119,
      "step": 461
    },
    {
      "epoch": 0.15026833631484796,
      "grad_norm": 7.1181159019470215,
      "learning_rate": 5e-05,
      "loss": 3.6675,
      "step": 462
    },
    {
      "epoch": 0.15059359245405757,
      "grad_norm": 11.3037109375,
      "learning_rate": 5e-05,
      "loss": 3.5125,
      "step": 463
    },
    {
      "epoch": 0.1509188485932672,
      "grad_norm": 10.003439903259277,
      "learning_rate": 5e-05,
      "loss": 3.2109,
      "step": 464
    },
    {
      "epoch": 0.15124410473247682,
      "grad_norm": 7.561882019042969,
      "learning_rate": 5e-05,
      "loss": 3.566,
      "step": 465
    },
    {
      "epoch": 0.15156936087168646,
      "grad_norm": 7.8044586181640625,
      "learning_rate": 5e-05,
      "loss": 3.5393,
      "step": 466
    },
    {
      "epoch": 0.15189461701089607,
      "grad_norm": 11.766450881958008,
      "learning_rate": 5e-05,
      "loss": 3.7168,
      "step": 467
    },
    {
      "epoch": 0.1522198731501057,
      "grad_norm": 7.827965259552002,
      "learning_rate": 5e-05,
      "loss": 3.7292,
      "step": 468
    },
    {
      "epoch": 0.15254512928931532,
      "grad_norm": 9.4542236328125,
      "learning_rate": 5e-05,
      "loss": 3.4709,
      "step": 469
    },
    {
      "epoch": 0.15287038542852496,
      "grad_norm": 8.595137596130371,
      "learning_rate": 5e-05,
      "loss": 4.3444,
      "step": 470
    },
    {
      "epoch": 0.1531956415677346,
      "grad_norm": 8.952139854431152,
      "learning_rate": 5e-05,
      "loss": 4.3924,
      "step": 471
    },
    {
      "epoch": 0.15352089770694421,
      "grad_norm": 9.41843318939209,
      "learning_rate": 5e-05,
      "loss": 3.7794,
      "step": 472
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 7.201237201690674,
      "learning_rate": 5e-05,
      "loss": 3.3527,
      "step": 473
    },
    {
      "epoch": 0.15417140998536347,
      "grad_norm": 9.496088981628418,
      "learning_rate": 5e-05,
      "loss": 3.3554,
      "step": 474
    },
    {
      "epoch": 0.1544966661245731,
      "grad_norm": 8.370413780212402,
      "learning_rate": 5e-05,
      "loss": 3.8943,
      "step": 475
    },
    {
      "epoch": 0.15482192226378272,
      "grad_norm": 8.910099029541016,
      "learning_rate": 5e-05,
      "loss": 3.5867,
      "step": 476
    },
    {
      "epoch": 0.15514717840299236,
      "grad_norm": 7.085155963897705,
      "learning_rate": 5e-05,
      "loss": 3.3267,
      "step": 477
    },
    {
      "epoch": 0.15547243454220197,
      "grad_norm": 8.49357795715332,
      "learning_rate": 5e-05,
      "loss": 3.5925,
      "step": 478
    },
    {
      "epoch": 0.1557976906814116,
      "grad_norm": 7.811654567718506,
      "learning_rate": 5e-05,
      "loss": 3.9464,
      "step": 479
    },
    {
      "epoch": 0.15612294682062125,
      "grad_norm": 9.111326217651367,
      "learning_rate": 5e-05,
      "loss": 3.5547,
      "step": 480
    },
    {
      "epoch": 0.15644820295983086,
      "grad_norm": 7.44144344329834,
      "learning_rate": 5e-05,
      "loss": 3.9226,
      "step": 481
    },
    {
      "epoch": 0.1567734590990405,
      "grad_norm": 9.64633846282959,
      "learning_rate": 5e-05,
      "loss": 3.887,
      "step": 482
    },
    {
      "epoch": 0.15709871523825011,
      "grad_norm": 11.60362720489502,
      "learning_rate": 5e-05,
      "loss": 3.7125,
      "step": 483
    },
    {
      "epoch": 0.15742397137745975,
      "grad_norm": 7.746142864227295,
      "learning_rate": 5e-05,
      "loss": 3.9722,
      "step": 484
    },
    {
      "epoch": 0.15774922751666937,
      "grad_norm": 7.080160140991211,
      "learning_rate": 5e-05,
      "loss": 3.1951,
      "step": 485
    },
    {
      "epoch": 0.158074483655879,
      "grad_norm": 17.081741333007812,
      "learning_rate": 5e-05,
      "loss": 3.7901,
      "step": 486
    },
    {
      "epoch": 0.15839973979508865,
      "grad_norm": 7.917695999145508,
      "learning_rate": 5e-05,
      "loss": 3.5357,
      "step": 487
    },
    {
      "epoch": 0.15872499593429826,
      "grad_norm": 8.854647636413574,
      "learning_rate": 5e-05,
      "loss": 3.7515,
      "step": 488
    },
    {
      "epoch": 0.1590502520735079,
      "grad_norm": 9.028191566467285,
      "learning_rate": 5e-05,
      "loss": 3.5516,
      "step": 489
    },
    {
      "epoch": 0.1593755082127175,
      "grad_norm": 10.008574485778809,
      "learning_rate": 5e-05,
      "loss": 3.6189,
      "step": 490
    },
    {
      "epoch": 0.15970076435192715,
      "grad_norm": 10.596325874328613,
      "learning_rate": 5e-05,
      "loss": 3.4306,
      "step": 491
    },
    {
      "epoch": 0.16002602049113676,
      "grad_norm": 12.258661270141602,
      "learning_rate": 5e-05,
      "loss": 3.5577,
      "step": 492
    },
    {
      "epoch": 0.1603512766303464,
      "grad_norm": 11.506673812866211,
      "learning_rate": 5e-05,
      "loss": 3.9079,
      "step": 493
    },
    {
      "epoch": 0.160676532769556,
      "grad_norm": 7.967488765716553,
      "learning_rate": 5e-05,
      "loss": 3.6066,
      "step": 494
    },
    {
      "epoch": 0.16100178890876565,
      "grad_norm": 11.729570388793945,
      "learning_rate": 5e-05,
      "loss": 3.9043,
      "step": 495
    },
    {
      "epoch": 0.1613270450479753,
      "grad_norm": 8.846243858337402,
      "learning_rate": 5e-05,
      "loss": 3.8228,
      "step": 496
    },
    {
      "epoch": 0.1616523011871849,
      "grad_norm": 12.016153335571289,
      "learning_rate": 5e-05,
      "loss": 3.9159,
      "step": 497
    },
    {
      "epoch": 0.16197755732639454,
      "grad_norm": 8.154533386230469,
      "learning_rate": 5e-05,
      "loss": 3.7158,
      "step": 498
    },
    {
      "epoch": 0.16230281346560416,
      "grad_norm": 11.766820907592773,
      "learning_rate": 5e-05,
      "loss": 3.5189,
      "step": 499
    },
    {
      "epoch": 0.1626280696048138,
      "grad_norm": 11.467671394348145,
      "learning_rate": 5e-05,
      "loss": 3.8887,
      "step": 500
    },
    {
      "epoch": 0.1629533257440234,
      "grad_norm": 7.477685451507568,
      "learning_rate": 5e-05,
      "loss": 4.0159,
      "step": 501
    },
    {
      "epoch": 0.16327858188323305,
      "grad_norm": 6.95028018951416,
      "learning_rate": 5e-05,
      "loss": 3.7446,
      "step": 502
    },
    {
      "epoch": 0.16360383802244266,
      "grad_norm": 11.298054695129395,
      "learning_rate": 5e-05,
      "loss": 3.692,
      "step": 503
    },
    {
      "epoch": 0.1639290941616523,
      "grad_norm": 7.807789325714111,
      "learning_rate": 5e-05,
      "loss": 3.6819,
      "step": 504
    },
    {
      "epoch": 0.16425435030086194,
      "grad_norm": 7.94120454788208,
      "learning_rate": 5e-05,
      "loss": 3.6853,
      "step": 505
    },
    {
      "epoch": 0.16457960644007155,
      "grad_norm": 8.74360466003418,
      "learning_rate": 5e-05,
      "loss": 3.5674,
      "step": 506
    },
    {
      "epoch": 0.1649048625792812,
      "grad_norm": 8.877306938171387,
      "learning_rate": 5e-05,
      "loss": 3.5393,
      "step": 507
    },
    {
      "epoch": 0.1652301187184908,
      "grad_norm": 7.502864837646484,
      "learning_rate": 5e-05,
      "loss": 3.6376,
      "step": 508
    },
    {
      "epoch": 0.16555537485770044,
      "grad_norm": 11.325250625610352,
      "learning_rate": 5e-05,
      "loss": 3.7114,
      "step": 509
    },
    {
      "epoch": 0.16588063099691006,
      "grad_norm": 9.918580055236816,
      "learning_rate": 5e-05,
      "loss": 3.783,
      "step": 510
    },
    {
      "epoch": 0.1662058871361197,
      "grad_norm": 8.940899848937988,
      "learning_rate": 5e-05,
      "loss": 3.707,
      "step": 511
    },
    {
      "epoch": 0.16653114327532934,
      "grad_norm": 17.020418167114258,
      "learning_rate": 5e-05,
      "loss": 4.319,
      "step": 512
    },
    {
      "epoch": 0.16685639941453895,
      "grad_norm": 10.722935676574707,
      "learning_rate": 5e-05,
      "loss": 3.4215,
      "step": 513
    },
    {
      "epoch": 0.1671816555537486,
      "grad_norm": 9.579489707946777,
      "learning_rate": 5e-05,
      "loss": 2.835,
      "step": 514
    },
    {
      "epoch": 0.1675069116929582,
      "grad_norm": 8.158295631408691,
      "learning_rate": 5e-05,
      "loss": 2.78,
      "step": 515
    },
    {
      "epoch": 0.16783216783216784,
      "grad_norm": 8.238765716552734,
      "learning_rate": 5e-05,
      "loss": 3.4628,
      "step": 516
    },
    {
      "epoch": 0.16815742397137745,
      "grad_norm": 8.580034255981445,
      "learning_rate": 5e-05,
      "loss": 3.9686,
      "step": 517
    },
    {
      "epoch": 0.1684826801105871,
      "grad_norm": 8.966435432434082,
      "learning_rate": 5e-05,
      "loss": 3.4936,
      "step": 518
    },
    {
      "epoch": 0.1688079362497967,
      "grad_norm": 6.970677375793457,
      "learning_rate": 5e-05,
      "loss": 3.4287,
      "step": 519
    },
    {
      "epoch": 0.16913319238900634,
      "grad_norm": 7.750168323516846,
      "learning_rate": 5e-05,
      "loss": 3.3396,
      "step": 520
    },
    {
      "epoch": 0.16945844852821598,
      "grad_norm": 7.394572734832764,
      "learning_rate": 5e-05,
      "loss": 3.6622,
      "step": 521
    },
    {
      "epoch": 0.1697837046674256,
      "grad_norm": 6.781547546386719,
      "learning_rate": 5e-05,
      "loss": 3.5704,
      "step": 522
    },
    {
      "epoch": 0.17010896080663523,
      "grad_norm": 11.887150764465332,
      "learning_rate": 5e-05,
      "loss": 3.4968,
      "step": 523
    },
    {
      "epoch": 0.17043421694584485,
      "grad_norm": 7.665548324584961,
      "learning_rate": 5e-05,
      "loss": 3.6475,
      "step": 524
    },
    {
      "epoch": 0.1707594730850545,
      "grad_norm": 8.977829933166504,
      "learning_rate": 5e-05,
      "loss": 2.6397,
      "step": 525
    },
    {
      "epoch": 0.1710847292242641,
      "grad_norm": 9.76028060913086,
      "learning_rate": 5e-05,
      "loss": 3.6625,
      "step": 526
    },
    {
      "epoch": 0.17140998536347374,
      "grad_norm": 9.248437881469727,
      "learning_rate": 5e-05,
      "loss": 3.5199,
      "step": 527
    },
    {
      "epoch": 0.17173524150268335,
      "grad_norm": 9.724522590637207,
      "learning_rate": 5e-05,
      "loss": 3.7095,
      "step": 528
    },
    {
      "epoch": 0.172060497641893,
      "grad_norm": 8.21666431427002,
      "learning_rate": 5e-05,
      "loss": 3.6802,
      "step": 529
    },
    {
      "epoch": 0.17238575378110263,
      "grad_norm": 7.362802505493164,
      "learning_rate": 5e-05,
      "loss": 3.6511,
      "step": 530
    },
    {
      "epoch": 0.17271100992031224,
      "grad_norm": 7.2599334716796875,
      "learning_rate": 5e-05,
      "loss": 3.1097,
      "step": 531
    },
    {
      "epoch": 0.17303626605952188,
      "grad_norm": 9.250597953796387,
      "learning_rate": 5e-05,
      "loss": 3.608,
      "step": 532
    },
    {
      "epoch": 0.1733615221987315,
      "grad_norm": 8.88681411743164,
      "learning_rate": 5e-05,
      "loss": 3.8212,
      "step": 533
    },
    {
      "epoch": 0.17368677833794113,
      "grad_norm": 11.290247917175293,
      "learning_rate": 5e-05,
      "loss": 3.3286,
      "step": 534
    },
    {
      "epoch": 0.17401203447715075,
      "grad_norm": 10.88404369354248,
      "learning_rate": 5e-05,
      "loss": 3.5241,
      "step": 535
    },
    {
      "epoch": 0.17433729061636039,
      "grad_norm": 9.20648193359375,
      "learning_rate": 5e-05,
      "loss": 3.6005,
      "step": 536
    },
    {
      "epoch": 0.17466254675557003,
      "grad_norm": 8.10119342803955,
      "learning_rate": 5e-05,
      "loss": 3.5739,
      "step": 537
    },
    {
      "epoch": 0.17498780289477964,
      "grad_norm": 10.661712646484375,
      "learning_rate": 5e-05,
      "loss": 3.4837,
      "step": 538
    },
    {
      "epoch": 0.17531305903398928,
      "grad_norm": 10.739490509033203,
      "learning_rate": 5e-05,
      "loss": 3.6787,
      "step": 539
    },
    {
      "epoch": 0.1756383151731989,
      "grad_norm": 9.183284759521484,
      "learning_rate": 5e-05,
      "loss": 3.6174,
      "step": 540
    },
    {
      "epoch": 0.17596357131240853,
      "grad_norm": 8.37816047668457,
      "learning_rate": 5e-05,
      "loss": 3.5964,
      "step": 541
    },
    {
      "epoch": 0.17628882745161814,
      "grad_norm": 10.69176959991455,
      "learning_rate": 5e-05,
      "loss": 3.8804,
      "step": 542
    },
    {
      "epoch": 0.17661408359082778,
      "grad_norm": 8.007463455200195,
      "learning_rate": 5e-05,
      "loss": 3.8485,
      "step": 543
    },
    {
      "epoch": 0.1769393397300374,
      "grad_norm": 8.839487075805664,
      "learning_rate": 5e-05,
      "loss": 3.6356,
      "step": 544
    },
    {
      "epoch": 0.17726459586924703,
      "grad_norm": 11.773893356323242,
      "learning_rate": 5e-05,
      "loss": 3.8846,
      "step": 545
    },
    {
      "epoch": 0.17758985200845667,
      "grad_norm": 11.021324157714844,
      "learning_rate": 5e-05,
      "loss": 3.8369,
      "step": 546
    },
    {
      "epoch": 0.17791510814766628,
      "grad_norm": 10.33259391784668,
      "learning_rate": 5e-05,
      "loss": 3.392,
      "step": 547
    },
    {
      "epoch": 0.17824036428687592,
      "grad_norm": 8.52408504486084,
      "learning_rate": 5e-05,
      "loss": 3.8102,
      "step": 548
    },
    {
      "epoch": 0.17856562042608554,
      "grad_norm": 9.792526245117188,
      "learning_rate": 5e-05,
      "loss": 3.9087,
      "step": 549
    },
    {
      "epoch": 0.17889087656529518,
      "grad_norm": 9.989365577697754,
      "learning_rate": 5e-05,
      "loss": 3.8268,
      "step": 550
    },
    {
      "epoch": 0.1792161327045048,
      "grad_norm": 9.42458438873291,
      "learning_rate": 5e-05,
      "loss": 3.7863,
      "step": 551
    },
    {
      "epoch": 0.17954138884371443,
      "grad_norm": 8.195592880249023,
      "learning_rate": 5e-05,
      "loss": 3.7507,
      "step": 552
    },
    {
      "epoch": 0.17986664498292404,
      "grad_norm": 9.999628067016602,
      "learning_rate": 5e-05,
      "loss": 3.742,
      "step": 553
    },
    {
      "epoch": 0.18019190112213368,
      "grad_norm": 8.54041576385498,
      "learning_rate": 5e-05,
      "loss": 4.4209,
      "step": 554
    },
    {
      "epoch": 0.18051715726134332,
      "grad_norm": 8.870122909545898,
      "learning_rate": 5e-05,
      "loss": 3.2489,
      "step": 555
    },
    {
      "epoch": 0.18084241340055293,
      "grad_norm": 10.103729248046875,
      "learning_rate": 5e-05,
      "loss": 3.5182,
      "step": 556
    },
    {
      "epoch": 0.18116766953976257,
      "grad_norm": 9.698139190673828,
      "learning_rate": 5e-05,
      "loss": 3.7934,
      "step": 557
    },
    {
      "epoch": 0.18149292567897218,
      "grad_norm": 9.132758140563965,
      "learning_rate": 5e-05,
      "loss": 3.3561,
      "step": 558
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 8.661752700805664,
      "learning_rate": 5e-05,
      "loss": 3.5775,
      "step": 559
    },
    {
      "epoch": 0.18214343795739144,
      "grad_norm": 9.332806587219238,
      "learning_rate": 5e-05,
      "loss": 3.0548,
      "step": 560
    },
    {
      "epoch": 0.18246869409660108,
      "grad_norm": 9.24280071258545,
      "learning_rate": 5e-05,
      "loss": 4.0208,
      "step": 561
    },
    {
      "epoch": 0.1827939502358107,
      "grad_norm": 9.924572944641113,
      "learning_rate": 5e-05,
      "loss": 3.6914,
      "step": 562
    },
    {
      "epoch": 0.18311920637502033,
      "grad_norm": 9.362936973571777,
      "learning_rate": 5e-05,
      "loss": 3.9219,
      "step": 563
    },
    {
      "epoch": 0.18344446251422997,
      "grad_norm": 12.603287696838379,
      "learning_rate": 5e-05,
      "loss": 3.4585,
      "step": 564
    },
    {
      "epoch": 0.18376971865343958,
      "grad_norm": 10.904036521911621,
      "learning_rate": 5e-05,
      "loss": 3.3266,
      "step": 565
    },
    {
      "epoch": 0.18409497479264922,
      "grad_norm": 9.598895072937012,
      "learning_rate": 5e-05,
      "loss": 3.6607,
      "step": 566
    },
    {
      "epoch": 0.18442023093185883,
      "grad_norm": 8.842279434204102,
      "learning_rate": 5e-05,
      "loss": 3.5674,
      "step": 567
    },
    {
      "epoch": 0.18474548707106847,
      "grad_norm": 9.379899024963379,
      "learning_rate": 5e-05,
      "loss": 3.6743,
      "step": 568
    },
    {
      "epoch": 0.18507074321027808,
      "grad_norm": 9.745834350585938,
      "learning_rate": 5e-05,
      "loss": 4.0652,
      "step": 569
    },
    {
      "epoch": 0.18539599934948772,
      "grad_norm": 8.990086555480957,
      "learning_rate": 5e-05,
      "loss": 3.637,
      "step": 570
    },
    {
      "epoch": 0.18572125548869736,
      "grad_norm": 8.382301330566406,
      "learning_rate": 5e-05,
      "loss": 3.967,
      "step": 571
    },
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 8.533965110778809,
      "learning_rate": 5e-05,
      "loss": 3.4941,
      "step": 572
    },
    {
      "epoch": 0.18637176776711661,
      "grad_norm": 9.823786735534668,
      "learning_rate": 5e-05,
      "loss": 3.7345,
      "step": 573
    },
    {
      "epoch": 0.18669702390632623,
      "grad_norm": 7.766260147094727,
      "learning_rate": 5e-05,
      "loss": 3.6831,
      "step": 574
    },
    {
      "epoch": 0.18702228004553587,
      "grad_norm": 8.095032691955566,
      "learning_rate": 5e-05,
      "loss": 3.4701,
      "step": 575
    },
    {
      "epoch": 0.18734753618474548,
      "grad_norm": 11.641885757446289,
      "learning_rate": 5e-05,
      "loss": 4.0934,
      "step": 576
    },
    {
      "epoch": 0.18767279232395512,
      "grad_norm": 9.155062675476074,
      "learning_rate": 5e-05,
      "loss": 3.5356,
      "step": 577
    },
    {
      "epoch": 0.18799804846316473,
      "grad_norm": 8.703105926513672,
      "learning_rate": 5e-05,
      "loss": 3.8144,
      "step": 578
    },
    {
      "epoch": 0.18832330460237437,
      "grad_norm": 9.528350830078125,
      "learning_rate": 5e-05,
      "loss": 3.2073,
      "step": 579
    },
    {
      "epoch": 0.188648560741584,
      "grad_norm": 9.156220436096191,
      "learning_rate": 5e-05,
      "loss": 3.777,
      "step": 580
    },
    {
      "epoch": 0.18897381688079362,
      "grad_norm": 8.443305015563965,
      "learning_rate": 5e-05,
      "loss": 3.7239,
      "step": 581
    },
    {
      "epoch": 0.18929907302000326,
      "grad_norm": 7.838225841522217,
      "learning_rate": 5e-05,
      "loss": 3.4467,
      "step": 582
    },
    {
      "epoch": 0.18962432915921287,
      "grad_norm": 7.3834757804870605,
      "learning_rate": 5e-05,
      "loss": 3.5151,
      "step": 583
    },
    {
      "epoch": 0.1899495852984225,
      "grad_norm": 9.460673332214355,
      "learning_rate": 5e-05,
      "loss": 3.4287,
      "step": 584
    },
    {
      "epoch": 0.19027484143763213,
      "grad_norm": 8.232035636901855,
      "learning_rate": 5e-05,
      "loss": 4.2533,
      "step": 585
    },
    {
      "epoch": 0.19060009757684176,
      "grad_norm": 12.586129188537598,
      "learning_rate": 5e-05,
      "loss": 3.7747,
      "step": 586
    },
    {
      "epoch": 0.19092535371605138,
      "grad_norm": 8.150300979614258,
      "learning_rate": 5e-05,
      "loss": 3.9724,
      "step": 587
    },
    {
      "epoch": 0.19125060985526102,
      "grad_norm": 8.529426574707031,
      "learning_rate": 5e-05,
      "loss": 4.6377,
      "step": 588
    },
    {
      "epoch": 0.19157586599447066,
      "grad_norm": 7.794090747833252,
      "learning_rate": 5e-05,
      "loss": 3.2597,
      "step": 589
    },
    {
      "epoch": 0.19190112213368027,
      "grad_norm": 8.038799285888672,
      "learning_rate": 5e-05,
      "loss": 3.9826,
      "step": 590
    },
    {
      "epoch": 0.1922263782728899,
      "grad_norm": 7.855754852294922,
      "learning_rate": 5e-05,
      "loss": 3.7777,
      "step": 591
    },
    {
      "epoch": 0.19255163441209952,
      "grad_norm": 8.140380859375,
      "learning_rate": 5e-05,
      "loss": 3.443,
      "step": 592
    },
    {
      "epoch": 0.19287689055130916,
      "grad_norm": 9.79352855682373,
      "learning_rate": 5e-05,
      "loss": 3.7066,
      "step": 593
    },
    {
      "epoch": 0.19320214669051877,
      "grad_norm": 13.119344711303711,
      "learning_rate": 5e-05,
      "loss": 3.9336,
      "step": 594
    },
    {
      "epoch": 0.1935274028297284,
      "grad_norm": 8.955309867858887,
      "learning_rate": 5e-05,
      "loss": 3.3643,
      "step": 595
    },
    {
      "epoch": 0.19385265896893805,
      "grad_norm": 8.016314506530762,
      "learning_rate": 5e-05,
      "loss": 3.7039,
      "step": 596
    },
    {
      "epoch": 0.19417791510814766,
      "grad_norm": 8.888792991638184,
      "learning_rate": 5e-05,
      "loss": 3.6356,
      "step": 597
    },
    {
      "epoch": 0.1945031712473573,
      "grad_norm": 9.017245292663574,
      "learning_rate": 5e-05,
      "loss": 3.6173,
      "step": 598
    },
    {
      "epoch": 0.19482842738656692,
      "grad_norm": 9.05187702178955,
      "learning_rate": 5e-05,
      "loss": 3.7156,
      "step": 599
    },
    {
      "epoch": 0.19515368352577656,
      "grad_norm": 8.980157852172852,
      "learning_rate": 5e-05,
      "loss": 3.5519,
      "step": 600
    }
  ],
  "logging_steps": 1,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2792420391095808.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}