{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.1585585585585587,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007207207207207207,
      "grad_norm": 11.684535026550293,
      "learning_rate": 0.0,
      "loss": 1.9738,
      "step": 1
    },
    {
      "epoch": 0.014414414414414415,
      "grad_norm": 11.136099815368652,
      "learning_rate": 4.7619047619047615e-06,
      "loss": 1.8034,
      "step": 2
    },
    {
      "epoch": 0.021621621621621623,
      "grad_norm": 11.060067176818848,
      "learning_rate": 9.523809523809523e-06,
      "loss": 1.8687,
      "step": 3
    },
    {
      "epoch": 0.02882882882882883,
      "grad_norm": 7.806331157684326,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 1.2328,
      "step": 4
    },
    {
      "epoch": 0.036036036036036036,
      "grad_norm": 10.489537239074707,
      "learning_rate": 1.9047619047619046e-05,
      "loss": 1.7451,
      "step": 5
    },
    {
      "epoch": 0.043243243243243246,
      "grad_norm": 10.609748840332031,
      "learning_rate": 2.380952380952381e-05,
      "loss": 1.9471,
      "step": 6
    },
    {
      "epoch": 0.05045045045045045,
      "grad_norm": 7.325054168701172,
      "learning_rate": 2.857142857142857e-05,
      "loss": 1.4811,
      "step": 7
    },
    {
      "epoch": 0.05765765765765766,
      "grad_norm": 6.63484001159668,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.7721,
      "step": 8
    },
    {
      "epoch": 0.06486486486486487,
      "grad_norm": 5.522454261779785,
      "learning_rate": 3.809523809523809e-05,
      "loss": 1.3708,
      "step": 9
    },
    {
      "epoch": 0.07207207207207207,
      "grad_norm": 5.074100971221924,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 1.2314,
      "step": 10
    },
    {
      "epoch": 0.07927927927927927,
      "grad_norm": 5.2653727531433105,
      "learning_rate": 4.761904761904762e-05,
      "loss": 1.3018,
      "step": 11
    },
    {
      "epoch": 0.08648648648648649,
      "grad_norm": 6.736268520355225,
      "learning_rate": 5.2380952380952384e-05,
      "loss": 1.3999,
      "step": 12
    },
    {
      "epoch": 0.0936936936936937,
      "grad_norm": 5.054599761962891,
      "learning_rate": 5.714285714285714e-05,
      "loss": 1.2591,
      "step": 13
    },
    {
      "epoch": 0.1009009009009009,
      "grad_norm": 8.724349975585938,
      "learning_rate": 6.19047619047619e-05,
      "loss": 1.2616,
      "step": 14
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 4.677655220031738,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.2418,
      "step": 15
    },
    {
      "epoch": 0.11531531531531532,
      "grad_norm": 5.682474613189697,
      "learning_rate": 7.142857142857143e-05,
      "loss": 1.1806,
      "step": 16
    },
    {
      "epoch": 0.12252252252252252,
      "grad_norm": 5.526418209075928,
      "learning_rate": 7.619047619047618e-05,
      "loss": 1.2929,
      "step": 17
    },
    {
      "epoch": 0.12972972972972974,
      "grad_norm": 6.196779727935791,
      "learning_rate": 8.095238095238096e-05,
      "loss": 1.1647,
      "step": 18
    },
    {
      "epoch": 0.13693693693693693,
      "grad_norm": 5.527401924133301,
      "learning_rate": 8.571428571428571e-05,
      "loss": 1.2824,
      "step": 19
    },
    {
      "epoch": 0.14414414414414414,
      "grad_norm": 5.004215717315674,
      "learning_rate": 9.047619047619048e-05,
      "loss": 1.2304,
      "step": 20
    },
    {
      "epoch": 0.15135135135135136,
      "grad_norm": 4.4609375,
      "learning_rate": 9.523809523809524e-05,
      "loss": 0.9803,
      "step": 21
    },
    {
      "epoch": 0.15855855855855855,
      "grad_norm": 3.6623268127441406,
      "learning_rate": 0.0001,
      "loss": 0.9208,
      "step": 22
    },
    {
      "epoch": 0.16576576576576577,
      "grad_norm": 3.9360475540161133,
      "learning_rate": 0.00010476190476190477,
      "loss": 1.0879,
      "step": 23
    },
    {
      "epoch": 0.17297297297297298,
      "grad_norm": 4.082197666168213,
      "learning_rate": 0.00010952380952380953,
      "loss": 0.898,
      "step": 24
    },
    {
      "epoch": 0.18018018018018017,
      "grad_norm": 3.7158267498016357,
      "learning_rate": 0.00011428571428571428,
      "loss": 1.0313,
      "step": 25
    },
    {
      "epoch": 0.1873873873873874,
      "grad_norm": 3.3059310913085938,
      "learning_rate": 0.00011904761904761905,
      "loss": 0.8641,
      "step": 26
    },
    {
      "epoch": 0.1945945945945946,
      "grad_norm": 4.730854034423828,
      "learning_rate": 0.0001238095238095238,
      "loss": 0.9493,
      "step": 27
    },
    {
      "epoch": 0.2018018018018018,
      "grad_norm": 3.885230541229248,
      "learning_rate": 0.00012857142857142858,
      "loss": 0.9264,
      "step": 28
    },
    {
      "epoch": 0.209009009009009,
      "grad_norm": 3.9439027309417725,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.2871,
      "step": 29
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 3.5822014808654785,
      "learning_rate": 0.0001380952380952381,
      "loss": 1.2572,
      "step": 30
    },
    {
      "epoch": 0.22342342342342342,
      "grad_norm": 3.486072540283203,
      "learning_rate": 0.00014285714285714287,
      "loss": 0.9093,
      "step": 31
    },
    {
      "epoch": 0.23063063063063063,
      "grad_norm": 3.3355259895324707,
      "learning_rate": 0.00014761904761904763,
      "loss": 1.0274,
      "step": 32
    },
    {
      "epoch": 0.23783783783783785,
      "grad_norm": 3.612154722213745,
      "learning_rate": 0.00015238095238095237,
      "loss": 1.0658,
      "step": 33
    },
    {
      "epoch": 0.24504504504504504,
      "grad_norm": 3.29073429107666,
      "learning_rate": 0.00015714285714285716,
      "loss": 1.0701,
      "step": 34
    },
    {
      "epoch": 0.25225225225225223,
      "grad_norm": 3.8151745796203613,
      "learning_rate": 0.00016190476190476192,
      "loss": 1.1347,
      "step": 35
    },
    {
      "epoch": 0.2594594594594595,
      "grad_norm": 4.158012390136719,
      "learning_rate": 0.0001666666666666667,
      "loss": 1.0801,
      "step": 36
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 4.130226135253906,
      "learning_rate": 0.00017142857142857143,
      "loss": 1.0072,
      "step": 37
    },
    {
      "epoch": 0.27387387387387385,
      "grad_norm": 3.8441193103790283,
      "learning_rate": 0.0001761904761904762,
      "loss": 1.1024,
      "step": 38
    },
    {
      "epoch": 0.2810810810810811,
      "grad_norm": 3.5585989952087402,
      "learning_rate": 0.00018095238095238095,
      "loss": 0.9666,
      "step": 39
    },
    {
      "epoch": 0.2882882882882883,
      "grad_norm": 3.3715403079986572,
      "learning_rate": 0.00018571428571428572,
      "loss": 0.9336,
      "step": 40
    },
    {
      "epoch": 0.2954954954954955,
      "grad_norm": 3.3742058277130127,
      "learning_rate": 0.00019047619047619048,
      "loss": 0.8506,
      "step": 41
    },
    {
      "epoch": 0.3027027027027027,
      "grad_norm": 7.884325981140137,
      "learning_rate": 0.00019523809523809525,
      "loss": 0.827,
      "step": 42
    },
    {
      "epoch": 0.3099099099099099,
      "grad_norm": 3.457500696182251,
      "learning_rate": 0.0002,
      "loss": 1.0578,
      "step": 43
    },
    {
      "epoch": 0.3171171171171171,
      "grad_norm": 4.896909713745117,
      "learning_rate": 0.000199996434000411,
      "loss": 0.9905,
      "step": 44
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 4.666468143463135,
      "learning_rate": 0.000199985736255971,
      "loss": 0.935,
      "step": 45
    },
    {
      "epoch": 0.33153153153153153,
      "grad_norm": 3.2455365657806396,
      "learning_rate": 0.00019996790752964305,
      "loss": 0.8739,
      "step": 46
    },
    {
      "epoch": 0.3387387387387387,
      "grad_norm": 4.211050033569336,
      "learning_rate": 0.0001999429490929718,
      "loss": 0.9597,
      "step": 47
    },
    {
      "epoch": 0.34594594594594597,
      "grad_norm": 3.6991987228393555,
      "learning_rate": 0.00019991086272599273,
      "loss": 1.2004,
      "step": 48
    },
    {
      "epoch": 0.35315315315315315,
      "grad_norm": 3.0730082988739014,
      "learning_rate": 0.00019987165071710527,
      "loss": 0.9823,
      "step": 49
    },
    {
      "epoch": 0.36036036036036034,
      "grad_norm": 4.365278720855713,
      "learning_rate": 0.00019982531586290958,
      "loss": 1.0471,
      "step": 50
    },
    {
      "epoch": 0.3675675675675676,
      "grad_norm": 3.7972359657287598,
      "learning_rate": 0.00019977186146800707,
      "loss": 0.9361,
      "step": 51
    },
    {
      "epoch": 0.3747747747747748,
      "grad_norm": 2.764312982559204,
      "learning_rate": 0.00019971129134476473,
      "loss": 0.7888,
      "step": 52
    },
    {
      "epoch": 0.38198198198198197,
      "grad_norm": 3.2575714588165283,
      "learning_rate": 0.0001996436098130433,
      "loss": 1.1607,
      "step": 53
    },
    {
      "epoch": 0.3891891891891892,
      "grad_norm": 2.767519235610962,
      "learning_rate": 0.00019956882169988905,
      "loss": 1.0077,
      "step": 54
    },
    {
      "epoch": 0.3963963963963964,
      "grad_norm": 3.0031251907348633,
      "learning_rate": 0.00019948693233918952,
      "loss": 0.9016,
      "step": 55
    },
    {
      "epoch": 0.4036036036036036,
      "grad_norm": 5.109826564788818,
      "learning_rate": 0.00019939794757129332,
      "loss": 1.2846,
      "step": 56
    },
    {
      "epoch": 0.41081081081081083,
      "grad_norm": 3.3529696464538574,
      "learning_rate": 0.00019930187374259337,
      "loss": 0.8013,
      "step": 57
    },
    {
      "epoch": 0.418018018018018,
      "grad_norm": 2.8710315227508545,
      "learning_rate": 0.0001991987177050743,
      "loss": 1.0549,
      "step": 58
    },
    {
      "epoch": 0.4252252252252252,
      "grad_norm": 4.7763848304748535,
      "learning_rate": 0.00019908848681582391,
      "loss": 0.9911,
      "step": 59
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 5.199997425079346,
      "learning_rate": 0.00019897118893650825,
      "loss": 1.3337,
      "step": 60
    },
    {
      "epoch": 0.43963963963963965,
      "grad_norm": 3.5701940059661865,
      "learning_rate": 0.00019884683243281116,
      "loss": 1.0998,
      "step": 61
    },
    {
      "epoch": 0.44684684684684683,
      "grad_norm": 3.537388324737549,
      "learning_rate": 0.00019871542617383743,
      "loss": 0.8564,
      "step": 62
    },
    {
      "epoch": 0.4540540540540541,
      "grad_norm": 5.325186729431152,
      "learning_rate": 0.00019857697953148037,
      "loss": 1.1864,
      "step": 63
    },
    {
      "epoch": 0.46126126126126127,
      "grad_norm": 2.8981680870056152,
      "learning_rate": 0.00019843150237975344,
      "loss": 0.8237,
      "step": 64
    },
    {
      "epoch": 0.46846846846846846,
      "grad_norm": 2.997547149658203,
      "learning_rate": 0.00019827900509408581,
      "loss": 0.901,
      "step": 65
    },
    {
      "epoch": 0.4756756756756757,
      "grad_norm": 3.446580410003662,
      "learning_rate": 0.0001981194985505827,
      "loss": 1.0586,
      "step": 66
    },
    {
      "epoch": 0.4828828828828829,
      "grad_norm": 3.1360299587249756,
      "learning_rate": 0.00019795299412524945,
      "loss": 1.0281,
      "step": 67
    },
    {
      "epoch": 0.4900900900900901,
      "grad_norm": 3.573737859725952,
      "learning_rate": 0.00019777950369318035,
      "loss": 1.0386,
      "step": 68
    },
    {
      "epoch": 0.4972972972972973,
      "grad_norm": 2.641695499420166,
      "learning_rate": 0.00019759903962771156,
      "loss": 0.786,
      "step": 69
    },
    {
      "epoch": 0.5045045045045045,
      "grad_norm": 3.949854612350464,
      "learning_rate": 0.0001974116147995387,
      "loss": 1.0804,
      "step": 70
    },
    {
      "epoch": 0.5117117117117117,
      "grad_norm": 3.0651161670684814,
      "learning_rate": 0.00019721724257579907,
      "loss": 0.874,
      "step": 71
    },
    {
      "epoch": 0.518918918918919,
      "grad_norm": 3.4615607261657715,
      "learning_rate": 0.000197015936819118,
      "loss": 0.929,
      "step": 72
    },
    {
      "epoch": 0.5261261261261261,
      "grad_norm": 2.989096164703369,
      "learning_rate": 0.00019680771188662044,
      "loss": 1.1453,
      "step": 73
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 3.3436026573181152,
      "learning_rate": 0.00019659258262890683,
      "loss": 1.1162,
      "step": 74
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 4.048951148986816,
      "learning_rate": 0.0001963705643889941,
      "loss": 1.0755,
      "step": 75
    },
    {
      "epoch": 0.5477477477477477,
      "grad_norm": 3.2565155029296875,
      "learning_rate": 0.00019614167300122126,
      "loss": 1.1184,
      "step": 76
    },
    {
      "epoch": 0.554954954954955,
      "grad_norm": 2.9959020614624023,
      "learning_rate": 0.00019590592479012023,
      "loss": 0.9782,
      "step": 77
    },
    {
      "epoch": 0.5621621621621622,
      "grad_norm": 3.099621534347534,
      "learning_rate": 0.00019566333656925147,
      "loss": 1.0039,
      "step": 78
    },
    {
      "epoch": 0.5693693693693693,
      "grad_norm": 2.6794540882110596,
      "learning_rate": 0.00019541392564000488,
      "loss": 0.6505,
      "step": 79
    },
    {
      "epoch": 0.5765765765765766,
      "grad_norm": 3.1174347400665283,
      "learning_rate": 0.00019515770979036594,
      "loss": 1.0842,
      "step": 80
    },
    {
      "epoch": 0.5837837837837838,
      "grad_norm": 2.441861391067505,
      "learning_rate": 0.00019489470729364692,
      "loss": 0.9361,
      "step": 81
    },
    {
      "epoch": 0.590990990990991,
      "grad_norm": 2.635843515396118,
      "learning_rate": 0.0001946249369071837,
      "loss": 1.0426,
      "step": 82
    },
    {
      "epoch": 0.5981981981981982,
      "grad_norm": 2.612903594970703,
      "learning_rate": 0.00019434841787099803,
      "loss": 0.7473,
      "step": 83
    },
    {
      "epoch": 0.6054054054054054,
      "grad_norm": 3.215303421020508,
      "learning_rate": 0.00019406516990642532,
      "loss": 0.8283,
      "step": 84
    },
    {
      "epoch": 0.6126126126126126,
      "grad_norm": 2.905101776123047,
      "learning_rate": 0.00019377521321470805,
      "loss": 0.9883,
      "step": 85
    },
    {
      "epoch": 0.6198198198198198,
      "grad_norm": 2.8337690830230713,
      "learning_rate": 0.00019347856847555512,
      "loss": 0.881,
      "step": 86
    },
    {
      "epoch": 0.6270270270270271,
      "grad_norm": 3.142810106277466,
      "learning_rate": 0.00019317525684566685,
      "loss": 0.9619,
      "step": 87
    },
    {
      "epoch": 0.6342342342342342,
      "grad_norm": 2.890902519226074,
      "learning_rate": 0.00019286529995722623,
      "loss": 0.9102,
      "step": 88
    },
    {
      "epoch": 0.6414414414414414,
      "grad_norm": 3.039911985397339,
      "learning_rate": 0.00019254871991635598,
      "loss": 0.965,
      "step": 89
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 4.075260162353516,
      "learning_rate": 0.00019222553930154198,
      "loss": 1.1541,
      "step": 90
    },
    {
      "epoch": 0.6558558558558558,
      "grad_norm": 3.2090113162994385,
      "learning_rate": 0.00019189578116202307,
      "loss": 1.2582,
      "step": 91
    },
    {
      "epoch": 0.6630630630630631,
      "grad_norm": 2.8671350479125977,
      "learning_rate": 0.00019155946901614702,
      "loss": 0.6915,
      "step": 92
    },
    {
      "epoch": 0.6702702702702703,
      "grad_norm": 3.6259381771087646,
      "learning_rate": 0.00019121662684969335,
      "loss": 0.8306,
      "step": 93
    },
    {
      "epoch": 0.6774774774774774,
      "grad_norm": 3.5522236824035645,
      "learning_rate": 0.0001908672791141625,
      "loss": 1.0978,
      "step": 94
    },
    {
      "epoch": 0.6846846846846847,
      "grad_norm": 3.524630546569824,
      "learning_rate": 0.00019051145072503215,
      "loss": 0.9786,
      "step": 95
    },
    {
      "epoch": 0.6918918918918919,
      "grad_norm": 3.0533735752105713,
      "learning_rate": 0.00019014916705998002,
      "loss": 0.9278,
      "step": 96
    },
    {
      "epoch": 0.6990990990990991,
      "grad_norm": 3.5166573524475098,
      "learning_rate": 0.00018978045395707418,
      "loss": 0.9571,
      "step": 97
    },
    {
      "epoch": 0.7063063063063063,
      "grad_norm": 2.7091610431671143,
      "learning_rate": 0.00018940533771293007,
      "loss": 0.8795,
      "step": 98
    },
    {
      "epoch": 0.7135135135135136,
      "grad_norm": 3.2437844276428223,
      "learning_rate": 0.00018902384508083517,
      "loss": 0.8935,
      "step": 99
    },
    {
      "epoch": 0.7207207207207207,
      "grad_norm": 2.761455774307251,
      "learning_rate": 0.00018863600326884082,
      "loss": 0.8749,
      "step": 100
    },
    {
      "epoch": 0.7279279279279279,
      "grad_norm": 2.5887527465820312,
      "learning_rate": 0.00018824183993782192,
      "loss": 0.7539,
      "step": 101
    },
    {
      "epoch": 0.7351351351351352,
      "grad_norm": 3.1463191509246826,
      "learning_rate": 0.00018784138319950398,
      "loss": 0.8477,
      "step": 102
    },
    {
      "epoch": 0.7423423423423423,
      "grad_norm": 3.196107864379883,
      "learning_rate": 0.00018743466161445823,
      "loss": 0.99,
      "step": 103
    },
    {
      "epoch": 0.7495495495495496,
      "grad_norm": 3.304748773574829,
      "learning_rate": 0.00018702170419006482,
      "loss": 1.1633,
      "step": 104
    },
    {
      "epoch": 0.7567567567567568,
      "grad_norm": 4.191944122314453,
      "learning_rate": 0.00018660254037844388,
      "loss": 1.0025,
      "step": 105
    },
    {
      "epoch": 0.7639639639639639,
      "grad_norm": 2.500408411026001,
      "learning_rate": 0.00018617720007435497,
      "loss": 0.7228,
      "step": 106
    },
    {
      "epoch": 0.7711711711711712,
      "grad_norm": 3.017630100250244,
      "learning_rate": 0.0001857457136130651,
      "loss": 0.84,
      "step": 107
    },
    {
      "epoch": 0.7783783783783784,
      "grad_norm": 3.539093017578125,
      "learning_rate": 0.00018530811176818514,
      "loss": 0.9757,
      "step": 108
    },
    {
      "epoch": 0.7855855855855856,
      "grad_norm": 3.014693260192871,
      "learning_rate": 0.00018486442574947511,
      "loss": 1.0803,
      "step": 109
    },
    {
      "epoch": 0.7927927927927928,
      "grad_norm": 3.0560622215270996,
      "learning_rate": 0.00018441468720061815,
      "loss": 0.975,
      "step": 110
    },
    {
      "epoch": 0.8,
      "grad_norm": 2.454893112182617,
      "learning_rate": 0.00018395892819696389,
      "loss": 0.8205,
      "step": 111
    },
    {
      "epoch": 0.8072072072072072,
      "grad_norm": 2.9785032272338867,
      "learning_rate": 0.00018349718124324076,
      "loss": 0.9708,
      "step": 112
    },
    {
      "epoch": 0.8144144144144144,
      "grad_norm": 3.3276872634887695,
      "learning_rate": 0.00018302947927123766,
      "loss": 0.9441,
      "step": 113
    },
    {
      "epoch": 0.8216216216216217,
      "grad_norm": 2.9160008430480957,
      "learning_rate": 0.00018255585563745538,
      "loss": 1.1011,
      "step": 114
    },
    {
      "epoch": 0.8288288288288288,
      "grad_norm": 2.756060838699341,
      "learning_rate": 0.00018207634412072764,
      "loss": 0.8479,
      "step": 115
    },
    {
      "epoch": 0.836036036036036,
      "grad_norm": 2.8569912910461426,
      "learning_rate": 0.00018159097891981186,
      "loss": 0.923,
      "step": 116
    },
    {
      "epoch": 0.8432432432432433,
      "grad_norm": 2.985607624053955,
      "learning_rate": 0.00018109979465095013,
      "loss": 1.0308,
      "step": 117
    },
    {
      "epoch": 0.8504504504504504,
      "grad_norm": 2.8948869705200195,
      "learning_rate": 0.00018060282634540053,
      "loss": 0.8382,
      "step": 118
    },
    {
      "epoch": 0.8576576576576577,
      "grad_norm": 2.6343963146209717,
      "learning_rate": 0.00018010010944693848,
      "loss": 0.7894,
      "step": 119
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 3.4868533611297607,
      "learning_rate": 0.00017959167980932908,
      "loss": 0.844,
      "step": 120
    },
    {
      "epoch": 0.872072072072072,
      "grad_norm": 2.749204158782959,
      "learning_rate": 0.00017907757369376985,
      "loss": 1.0067,
      "step": 121
    },
    {
      "epoch": 0.8792792792792793,
      "grad_norm": 2.7613115310668945,
      "learning_rate": 0.00017855782776630483,
      "loss": 0.9647,
      "step": 122
    },
    {
      "epoch": 0.8864864864864865,
      "grad_norm": 3.023930072784424,
      "learning_rate": 0.0001780324790952092,
      "loss": 1.0151,
      "step": 123
    },
    {
      "epoch": 0.8936936936936937,
      "grad_norm": 2.894148349761963,
      "learning_rate": 0.0001775015651483459,
      "loss": 0.7528,
      "step": 124
    },
    {
      "epoch": 0.9009009009009009,
      "grad_norm": 2.740029811859131,
      "learning_rate": 0.00017696512379049325,
      "loss": 0.7695,
      "step": 125
    },
    {
      "epoch": 0.9081081081081082,
      "grad_norm": 3.4892916679382324,
      "learning_rate": 0.00017642319328064446,
      "loss": 1.1829,
      "step": 126
    },
    {
      "epoch": 0.9153153153153153,
      "grad_norm": 3.0546014308929443,
      "learning_rate": 0.0001758758122692791,
      "loss": 0.8454,
      "step": 127
    },
    {
      "epoch": 0.9225225225225225,
      "grad_norm": 3.2734737396240234,
      "learning_rate": 0.00017532301979560636,
      "loss": 0.7378,
      "step": 128
    },
    {
      "epoch": 0.9297297297297298,
      "grad_norm": 3.5465164184570312,
      "learning_rate": 0.00017476485528478093,
      "loss": 1.0544,
      "step": 129
    },
    {
      "epoch": 0.9369369369369369,
      "grad_norm": 2.907961130142212,
      "learning_rate": 0.0001742013585450911,
      "loss": 0.8242,
      "step": 130
    },
    {
      "epoch": 0.9441441441441442,
      "grad_norm": 3.7469565868377686,
      "learning_rate": 0.00017363256976511972,
      "loss": 1.0882,
      "step": 131
    },
    {
      "epoch": 0.9513513513513514,
      "grad_norm": 2.788562774658203,
      "learning_rate": 0.00017305852951087798,
      "loss": 0.6901,
      "step": 132
    },
    {
      "epoch": 0.9585585585585585,
      "grad_norm": 3.597954511642456,
      "learning_rate": 0.000172479278722912,
      "loss": 1.0036,
      "step": 133
    },
    {
      "epoch": 0.9657657657657658,
      "grad_norm": 2.6259546279907227,
      "learning_rate": 0.0001718948587133833,
      "loss": 0.775,
      "step": 134
    },
    {
      "epoch": 0.972972972972973,
      "grad_norm": 2.546386480331421,
      "learning_rate": 0.00017130531116312203,
      "loss": 1.1544,
      "step": 135
    },
    {
      "epoch": 0.9801801801801802,
      "grad_norm": 3.005147695541382,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.9333,
      "step": 136
    },
    {
      "epoch": 0.9873873873873874,
      "grad_norm": 3.014779806137085,
      "learning_rate": 0.0001701110019892053,
      "loss": 0.9593,
      "step": 137
    },
    {
      "epoch": 0.9945945945945946,
      "grad_norm": 3.0027060508728027,
      "learning_rate": 0.00016950632554367019,
      "loss": 0.8674,
      "step": 138
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.3540961742401123,
      "learning_rate": 0.00016889669190756868,
      "loss": 1.0522,
      "step": 139
    },
    {
      "epoch": 1.0072072072072071,
      "grad_norm": 2.276853561401367,
      "learning_rate": 0.00016828214455996658,
      "loss": 0.6489,
      "step": 140
    },
    {
      "epoch": 1.0144144144144145,
      "grad_norm": 2.078212022781372,
      "learning_rate": 0.00016766272733037576,
      "loss": 0.5525,
      "step": 141
    },
    {
      "epoch": 1.0216216216216216,
      "grad_norm": 2.5213096141815186,
      "learning_rate": 0.00016703848439562785,
      "loss": 0.5721,
      "step": 142
    },
    {
      "epoch": 1.0288288288288288,
      "grad_norm": 2.609396457672119,
      "learning_rate": 0.00016640946027672392,
      "loss": 0.5182,
      "step": 143
    },
    {
      "epoch": 1.0360360360360361,
      "grad_norm": 3.169931411743164,
      "learning_rate": 0.0001657756998356589,
      "loss": 0.66,
      "step": 144
    },
    {
      "epoch": 1.0432432432432432,
      "grad_norm": 3.4300990104675293,
      "learning_rate": 0.00016513724827222227,
      "loss": 0.7957,
      "step": 145
    },
    {
      "epoch": 1.0504504504504504,
      "grad_norm": 3.529196262359619,
      "learning_rate": 0.0001644941511207742,
      "loss": 0.6789,
      "step": 146
    },
    {
      "epoch": 1.0576576576576577,
      "grad_norm": 3.195830821990967,
      "learning_rate": 0.00016384645424699835,
      "loss": 0.6448,
      "step": 147
    },
    {
      "epoch": 1.0648648648648649,
      "grad_norm": 3.7281556129455566,
      "learning_rate": 0.0001631942038446304,
      "loss": 0.7441,
      "step": 148
    },
    {
      "epoch": 1.072072072072072,
      "grad_norm": 3.6758270263671875,
      "learning_rate": 0.00016253744643216368,
      "loss": 0.6576,
      "step": 149
    },
    {
      "epoch": 1.0792792792792794,
      "grad_norm": 2.8492960929870605,
      "learning_rate": 0.00016187622884953145,
      "loss": 0.5277,
      "step": 150
    },
    {
      "epoch": 1.0864864864864865,
      "grad_norm": 4.0120439529418945,
      "learning_rate": 0.0001612105982547663,
      "loss": 0.7105,
      "step": 151
    },
    {
      "epoch": 1.0936936936936936,
      "grad_norm": 3.6597225666046143,
      "learning_rate": 0.00016054060212063672,
      "loss": 0.6119,
      "step": 152
    },
    {
      "epoch": 1.100900900900901,
      "grad_norm": 3.324005365371704,
      "learning_rate": 0.0001598662882312615,
      "loss": 0.5402,
      "step": 153
    },
    {
      "epoch": 1.1081081081081081,
      "grad_norm": 3.6454312801361084,
      "learning_rate": 0.0001591877046787017,
      "loss": 0.5997,
      "step": 154
    },
    {
      "epoch": 1.1153153153153152,
      "grad_norm": 3.3868091106414795,
      "learning_rate": 0.00015850489985953076,
      "loss": 0.6123,
      "step": 155
    },
    {
      "epoch": 1.1225225225225226,
      "grad_norm": 4.359033584594727,
      "learning_rate": 0.0001578179224713827,
      "loss": 0.8261,
      "step": 156
    },
    {
      "epoch": 1.1297297297297297,
      "grad_norm": 3.414869785308838,
      "learning_rate": 0.00015712682150947923,
      "loss": 0.6084,
      "step": 157
    },
    {
      "epoch": 1.1369369369369369,
      "grad_norm": 3.363609552383423,
      "learning_rate": 0.00015643164626313527,
      "loss": 0.4678,
      "step": 158
    },
    {
      "epoch": 1.1441441441441442,
      "grad_norm": 3.4990248680114746,
      "learning_rate": 0.00015573244631224365,
      "loss": 0.5549,
      "step": 159
    },
    {
      "epoch": 1.1513513513513514,
      "grad_norm": 3.346892833709717,
      "learning_rate": 0.00015502927152373914,
      "loss": 0.5847,
      "step": 160
    },
    {
      "epoch": 1.1585585585585585,
      "grad_norm": 3.1101760864257812,
      "learning_rate": 0.0001543221720480419,
      "loss": 0.4695,
      "step": 161
    },
    {
      "epoch": 1.1657657657657658,
      "grad_norm": 3.5808727741241455,
      "learning_rate": 0.00015361119831548069,
      "loss": 0.6057,
      "step": 162
    },
    {
      "epoch": 1.172972972972973,
      "grad_norm": 2.9661688804626465,
      "learning_rate": 0.00015289640103269625,
      "loss": 0.4864,
      "step": 163
    },
    {
      "epoch": 1.1801801801801801,
      "grad_norm": 3.4772303104400635,
      "learning_rate": 0.00015217783117902497,
      "loss": 0.5846,
      "step": 164
    },
    {
      "epoch": 1.1873873873873875,
      "grad_norm": 4.1343841552734375,
      "learning_rate": 0.0001514555400028629,
      "loss": 0.5762,
      "step": 165
    },
    {
      "epoch": 1.1945945945945946,
      "grad_norm": 4.29697847366333,
      "learning_rate": 0.00015072957901801076,
      "loss": 0.6847,
      "step": 166
    },
    {
      "epoch": 1.2018018018018017,
      "grad_norm": 3.9759178161621094,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.5391,
      "step": 167
    },
    {
      "epoch": 1.209009009009009,
      "grad_norm": 3.587759017944336,
      "learning_rate": 0.00014926685498240028,
      "loss": 0.7039,
      "step": 168
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 3.6181018352508545,
      "learning_rate": 0.00014853019625310813,
      "loss": 0.4963,
      "step": 169
    },
    {
      "epoch": 1.2234234234234234,
      "grad_norm": 3.5132596492767334,
      "learning_rate": 0.0001477900763506181,
      "loss": 0.5419,
      "step": 170
    },
    {
      "epoch": 1.2306306306306307,
      "grad_norm": 4.010970115661621,
      "learning_rate": 0.0001470465480602756,
      "loss": 0.6267,
      "step": 171
    },
    {
      "epoch": 1.2378378378378379,
      "grad_norm": 3.2222988605499268,
      "learning_rate": 0.00014629966441051208,
      "loss": 0.4639,
      "step": 172
    },
    {
      "epoch": 1.245045045045045,
      "grad_norm": 2.956730604171753,
      "learning_rate": 0.0001455494786690634,
      "loss": 0.4572,
      "step": 173
    },
    {
      "epoch": 1.2522522522522523,
      "grad_norm": 3.9305412769317627,
      "learning_rate": 0.00014479604433917045,
      "loss": 0.635,
      "step": 174
    },
    {
      "epoch": 1.2594594594594595,
      "grad_norm": 4.476108074188232,
      "learning_rate": 0.00014403941515576344,
      "loss": 0.7155,
      "step": 175
    },
    {
      "epoch": 1.2666666666666666,
      "grad_norm": 3.3448009490966797,
      "learning_rate": 0.0001432796450816295,
      "loss": 0.5718,
      "step": 176
    },
    {
      "epoch": 1.2738738738738737,
      "grad_norm": 3.6916096210479736,
      "learning_rate": 0.00014251678830356408,
      "loss": 0.5516,
      "step": 177
    },
    {
      "epoch": 1.281081081081081,
      "grad_norm": 4.04361629486084,
      "learning_rate": 0.00014175089922850633,
      "loss": 0.6114,
      "step": 178
    },
    {
      "epoch": 1.2882882882882882,
      "grad_norm": 3.9775683879852295,
      "learning_rate": 0.00014098203247965875,
      "loss": 0.6083,
      "step": 179
    },
    {
      "epoch": 1.2954954954954956,
      "grad_norm": 3.9424428939819336,
      "learning_rate": 0.00014021024289259158,
      "loss": 0.5872,
      "step": 180
    },
    {
      "epoch": 1.3027027027027027,
      "grad_norm": 3.335747003555298,
      "learning_rate": 0.00013943558551133186,
      "loss": 0.6535,
      "step": 181
    },
    {
      "epoch": 1.3099099099099099,
      "grad_norm": 4.008434295654297,
      "learning_rate": 0.0001386581155844376,
      "loss": 0.5727,
      "step": 182
    },
    {
      "epoch": 1.317117117117117,
      "grad_norm": 3.780360698699951,
      "learning_rate": 0.0001378778885610576,
      "loss": 0.5755,
      "step": 183
    },
    {
      "epoch": 1.3243243243243243,
      "grad_norm": 3.519291400909424,
      "learning_rate": 0.0001370949600869768,
      "loss": 0.6356,
      "step": 184
    },
    {
      "epoch": 1.3315315315315315,
      "grad_norm": 3.550152540206909,
      "learning_rate": 0.00013630938600064747,
      "loss": 0.493,
      "step": 185
    },
    {
      "epoch": 1.3387387387387388,
      "grad_norm": 3.578202247619629,
      "learning_rate": 0.00013552122232920707,
      "loss": 0.4639,
      "step": 186
    },
    {
      "epoch": 1.345945945945946,
      "grad_norm": 3.857863187789917,
      "learning_rate": 0.00013473052528448201,
      "loss": 0.4861,
      "step": 187
    },
    {
      "epoch": 1.353153153153153,
      "grad_norm": 3.5476558208465576,
      "learning_rate": 0.00013393735125897925,
      "loss": 0.4221,
      "step": 188
    },
    {
      "epoch": 1.3603603603603602,
      "grad_norm": 4.612096786499023,
      "learning_rate": 0.0001331417568218636,
      "loss": 0.6924,
      "step": 189
    },
    {
      "epoch": 1.3675675675675676,
      "grad_norm": 3.7291951179504395,
      "learning_rate": 0.0001323437987149238,
      "loss": 0.5414,
      "step": 190
    },
    {
      "epoch": 1.3747747747747747,
      "grad_norm": 3.549318790435791,
      "learning_rate": 0.00013154353384852558,
      "loss": 0.5876,
      "step": 191
    },
    {
      "epoch": 1.381981981981982,
      "grad_norm": 3.562321424484253,
      "learning_rate": 0.00013074101929755252,
      "loss": 0.5237,
      "step": 192
    },
    {
      "epoch": 1.3891891891891892,
      "grad_norm": 3.622387409210205,
      "learning_rate": 0.00012993631229733582,
      "loss": 0.5796,
      "step": 193
    },
    {
      "epoch": 1.3963963963963963,
      "grad_norm": 4.345496654510498,
      "learning_rate": 0.00012912947023957212,
      "loss": 0.5582,
      "step": 194
    },
    {
      "epoch": 1.4036036036036035,
      "grad_norm": 3.7925331592559814,
      "learning_rate": 0.00012832055066823038,
      "loss": 0.4847,
      "step": 195
    },
    {
      "epoch": 1.4108108108108108,
      "grad_norm": 3.877462148666382,
      "learning_rate": 0.0001275096112754478,
      "loss": 0.6631,
      "step": 196
    },
    {
      "epoch": 1.418018018018018,
      "grad_norm": 3.4748427867889404,
      "learning_rate": 0.00012669670989741517,
      "loss": 0.4883,
      "step": 197
    },
    {
      "epoch": 1.4252252252252253,
      "grad_norm": 5.154613494873047,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.7408,
      "step": 198
    },
    {
      "epoch": 1.4324324324324325,
      "grad_norm": 4.5702009201049805,
      "learning_rate": 0.00012506525322587207,
      "loss": 0.6509,
      "step": 199
    },
    {
      "epoch": 1.4396396396396396,
      "grad_norm": 4.41005802154541,
      "learning_rate": 0.000124246814287838,
      "loss": 0.6209,
      "step": 200
    },
    {
      "epoch": 1.4468468468468467,
      "grad_norm": 3.8622541427612305,
      "learning_rate": 0.00012342664606720822,
      "loss": 0.4897,
      "step": 201
    },
    {
      "epoch": 1.454054054054054,
      "grad_norm": 3.2512149810791016,
      "learning_rate": 0.0001226048070583735,
      "loss": 0.4093,
      "step": 202
    },
    {
      "epoch": 1.4612612612612612,
      "grad_norm": 4.367804527282715,
      "learning_rate": 0.00012178135587488515,
      "loss": 0.7187,
      "step": 203
    },
    {
      "epoch": 1.4684684684684686,
      "grad_norm": 4.4729695320129395,
      "learning_rate": 0.00012095635124527486,
      "loss": 0.6875,
      "step": 204
    },
    {
      "epoch": 1.4756756756756757,
      "grad_norm": 3.868335723876953,
      "learning_rate": 0.00012012985200886602,
      "loss": 0.4708,
      "step": 205
    },
    {
      "epoch": 1.4828828828828828,
      "grad_norm": 4.509119987487793,
      "learning_rate": 0.00011930191711157737,
      "loss": 0.6751,
      "step": 206
    },
    {
      "epoch": 1.49009009009009,
      "grad_norm": 4.019607067108154,
      "learning_rate": 0.00011847260560171896,
      "loss": 0.5807,
      "step": 207
    },
    {
      "epoch": 1.4972972972972973,
      "grad_norm": 4.538064479827881,
      "learning_rate": 0.00011764197662578086,
      "loss": 0.5487,
      "step": 208
    },
    {
      "epoch": 1.5045045045045045,
      "grad_norm": 3.9388089179992676,
      "learning_rate": 0.00011681008942421483,
      "loss": 0.6733,
      "step": 209
    },
    {
      "epoch": 1.5117117117117118,
      "grad_norm": 3.6662909984588623,
      "learning_rate": 0.00011597700332720923,
      "loss": 0.6427,
      "step": 210
    },
    {
      "epoch": 1.518918918918919,
      "grad_norm": 4.474135875701904,
      "learning_rate": 0.00011514277775045768,
      "loss": 0.461,
      "step": 211
    },
    {
      "epoch": 1.526126126126126,
      "grad_norm": 4.503089904785156,
      "learning_rate": 0.00011430747219092142,
      "loss": 0.6343,
      "step": 212
    },
    {
      "epoch": 1.5333333333333332,
      "grad_norm": 3.5401525497436523,
      "learning_rate": 0.00011347114622258612,
      "loss": 0.4952,
      "step": 213
    },
    {
      "epoch": 1.5405405405405406,
      "grad_norm": 3.793971300125122,
      "learning_rate": 0.00011263385949221295,
      "loss": 0.5508,
      "step": 214
    },
    {
      "epoch": 1.5477477477477477,
      "grad_norm": 4.067086219787598,
      "learning_rate": 0.00011179567171508463,
      "loss": 0.6104,
      "step": 215
    },
    {
      "epoch": 1.554954954954955,
      "grad_norm": 3.9283523559570312,
      "learning_rate": 0.00011095664267074655,
      "loss": 0.4628,
      "step": 216
    },
    {
      "epoch": 1.5621621621621622,
      "grad_norm": 4.976551532745361,
      "learning_rate": 0.00011011683219874323,
      "loss": 0.876,
      "step": 217
    },
    {
      "epoch": 1.5693693693693693,
      "grad_norm": 4.267294406890869,
      "learning_rate": 0.00010927630019435066,
      "loss": 0.4994,
      "step": 218
    },
    {
      "epoch": 1.5765765765765765,
      "grad_norm": 3.360891819000244,
      "learning_rate": 0.00010843510660430447,
      "loss": 0.3533,
      "step": 219
    },
    {
      "epoch": 1.5837837837837838,
      "grad_norm": 3.7110517024993896,
      "learning_rate": 0.00010759331142252462,
      "loss": 0.5224,
      "step": 220
    },
    {
      "epoch": 1.590990990990991,
      "grad_norm": 4.481605052947998,
      "learning_rate": 0.00010675097468583652,
      "loss": 0.5574,
      "step": 221
    },
    {
      "epoch": 1.5981981981981983,
      "grad_norm": 4.053014278411865,
      "learning_rate": 0.00010590815646968934,
      "loss": 0.6144,
      "step": 222
    },
    {
      "epoch": 1.6054054054054054,
      "grad_norm": 4.868806838989258,
      "learning_rate": 0.00010506491688387127,
      "loss": 0.6848,
      "step": 223
    },
    {
      "epoch": 1.6126126126126126,
      "grad_norm": 3.274519681930542,
      "learning_rate": 0.00010422131606822269,
      "loss": 0.4239,
      "step": 224
    },
    {
      "epoch": 1.6198198198198197,
      "grad_norm": 4.9189276695251465,
      "learning_rate": 0.00010337741418834684,
      "loss": 0.7214,
      "step": 225
    },
    {
      "epoch": 1.627027027027027,
      "grad_norm": 4.758511066436768,
      "learning_rate": 0.00010253327143131879,
      "loss": 0.7428,
      "step": 226
    },
    {
      "epoch": 1.6342342342342342,
      "grad_norm": 3.2766125202178955,
      "learning_rate": 0.0001016889480013931,
      "loss": 0.4058,
      "step": 227
    },
    {
      "epoch": 1.6414414414414416,
      "grad_norm": 4.384894847869873,
      "learning_rate": 0.00010084450411570985,
      "loss": 0.5434,
      "step": 228
    },
    {
      "epoch": 1.6486486486486487,
      "grad_norm": 3.8896596431732178,
      "learning_rate": 0.0001,
      "loss": 0.5409,
      "step": 229
    },
    {
      "epoch": 1.6558558558558558,
      "grad_norm": 3.30137038230896,
      "learning_rate": 9.915549588429015e-05,
      "loss": 0.3562,
      "step": 230
    },
    {
      "epoch": 1.663063063063063,
      "grad_norm": 3.669996976852417,
      "learning_rate": 9.83110519986069e-05,
      "loss": 0.5631,
      "step": 231
    },
    {
      "epoch": 1.6702702702702703,
      "grad_norm": 4.830873966217041,
      "learning_rate": 9.746672856868123e-05,
      "loss": 0.5807,
      "step": 232
    },
    {
      "epoch": 1.6774774774774774,
      "grad_norm": 4.004265308380127,
      "learning_rate": 9.662258581165319e-05,
      "loss": 0.4425,
      "step": 233
    },
    {
      "epoch": 1.6846846846846848,
      "grad_norm": 3.8576467037200928,
      "learning_rate": 9.577868393177732e-05,
      "loss": 0.5727,
      "step": 234
    },
    {
      "epoch": 1.691891891891892,
      "grad_norm": 3.7281970977783203,
      "learning_rate": 9.493508311612874e-05,
      "loss": 0.4434,
      "step": 235
    },
    {
      "epoch": 1.699099099099099,
      "grad_norm": 3.8081681728363037,
      "learning_rate": 9.409184353031068e-05,
      "loss": 0.6825,
      "step": 236
    },
    {
      "epoch": 1.7063063063063062,
      "grad_norm": 4.315023422241211,
      "learning_rate": 9.324902531416349e-05,
      "loss": 0.6077,
      "step": 237
    },
    {
      "epoch": 1.7135135135135136,
      "grad_norm": 4.316312313079834,
      "learning_rate": 9.24066885774754e-05,
      "loss": 0.6121,
      "step": 238
    },
    {
      "epoch": 1.7207207207207207,
      "grad_norm": 5.163501262664795,
      "learning_rate": 9.156489339569554e-05,
      "loss": 0.7748,
      "step": 239
    },
    {
      "epoch": 1.727927927927928,
      "grad_norm": 3.634093999862671,
      "learning_rate": 9.072369980564935e-05,
      "loss": 0.751,
      "step": 240
    },
    {
      "epoch": 1.7351351351351352,
      "grad_norm": 3.306368350982666,
      "learning_rate": 8.98831678012568e-05,
      "loss": 0.3867,
      "step": 241
    },
    {
      "epoch": 1.7423423423423423,
      "grad_norm": 4.843188285827637,
      "learning_rate": 8.90433573292535e-05,
      "loss": 0.6822,
      "step": 242
    },
    {
      "epoch": 1.7495495495495494,
      "grad_norm": 5.148568153381348,
      "learning_rate": 8.820432828491542e-05,
      "loss": 0.8646,
      "step": 243
    },
    {
      "epoch": 1.7567567567567568,
      "grad_norm": 4.512259006500244,
      "learning_rate": 8.73661405077871e-05,
      "loss": 0.8513,
      "step": 244
    },
    {
      "epoch": 1.763963963963964,
      "grad_norm": 4.428910255432129,
      "learning_rate": 8.652885377741393e-05,
      "loss": 0.583,
      "step": 245
    },
    {
      "epoch": 1.7711711711711713,
      "grad_norm": 3.868445873260498,
      "learning_rate": 8.569252780907862e-05,
      "loss": 0.4966,
      "step": 246
    },
    {
      "epoch": 1.7783783783783784,
      "grad_norm": 4.749986171722412,
      "learning_rate": 8.485722224954237e-05,
      "loss": 0.8847,
      "step": 247
    },
    {
      "epoch": 1.7855855855855856,
      "grad_norm": 3.9325308799743652,
      "learning_rate": 8.402299667279078e-05,
      "loss": 0.611,
      "step": 248
    },
    {
      "epoch": 1.7927927927927927,
      "grad_norm": 4.074451446533203,
      "learning_rate": 8.31899105757852e-05,
      "loss": 0.6358,
      "step": 249
    },
    {
      "epoch": 1.8,
      "grad_norm": 3.572497844696045,
      "learning_rate": 8.235802337421919e-05,
      "loss": 0.6278,
      "step": 250
    },
    {
      "epoch": 1.8072072072072072,
      "grad_norm": 4.139247417449951,
      "learning_rate": 8.15273943982811e-05,
      "loss": 0.6351,
      "step": 251
    },
    {
      "epoch": 1.8144144144144145,
      "grad_norm": 3.6678519248962402,
      "learning_rate": 8.06980828884227e-05,
      "loss": 0.5672,
      "step": 252
    },
    {
      "epoch": 1.8216216216216217,
      "grad_norm": 3.446139097213745,
      "learning_rate": 7.987014799113397e-05,
      "loss": 0.4856,
      "step": 253
    },
    {
      "epoch": 1.8288288288288288,
      "grad_norm": 3.493777275085449,
      "learning_rate": 7.904364875472513e-05,
      "loss": 0.6045,
      "step": 254
    },
    {
      "epoch": 1.836036036036036,
      "grad_norm": 4.7790961265563965,
      "learning_rate": 7.821864412511485e-05,
      "loss": 0.7036,
      "step": 255
    },
    {
      "epoch": 1.8432432432432433,
      "grad_norm": 4.165652275085449,
      "learning_rate": 7.739519294162652e-05,
      "loss": 0.5238,
      "step": 256
    },
    {
      "epoch": 1.8504504504504504,
      "grad_norm": 3.581364870071411,
      "learning_rate": 7.65733539327918e-05,
      "loss": 0.4565,
      "step": 257
    },
    {
      "epoch": 1.8576576576576578,
      "grad_norm": 3.2657792568206787,
      "learning_rate": 7.5753185712162e-05,
      "loss": 0.3849,
      "step": 258
    },
    {
      "epoch": 1.864864864864865,
      "grad_norm": 3.9218881130218506,
      "learning_rate": 7.493474677412794e-05,
      "loss": 0.4958,
      "step": 259
    },
    {
      "epoch": 1.872072072072072,
      "grad_norm": 3.588848829269409,
      "learning_rate": 7.411809548974792e-05,
      "loss": 0.503,
      "step": 260
    },
    {
      "epoch": 1.8792792792792792,
      "grad_norm": 4.164908409118652,
      "learning_rate": 7.330329010258483e-05,
      "loss": 0.4935,
      "step": 261
    },
    {
      "epoch": 1.8864864864864865,
      "grad_norm": 3.1876206398010254,
      "learning_rate": 7.24903887245522e-05,
      "loss": 0.4137,
      "step": 262
    },
    {
      "epoch": 1.8936936936936937,
      "grad_norm": 4.017881870269775,
      "learning_rate": 7.16794493317696e-05,
      "loss": 0.5476,
      "step": 263
    },
    {
      "epoch": 1.900900900900901,
      "grad_norm": 4.565951347351074,
      "learning_rate": 7.087052976042789e-05,
      "loss": 0.6215,
      "step": 264
    },
    {
      "epoch": 1.9081081081081082,
      "grad_norm": 4.266515731811523,
      "learning_rate": 7.006368770266421e-05,
      "loss": 0.6048,
      "step": 265
    },
    {
      "epoch": 1.9153153153153153,
      "grad_norm": 5.410391807556152,
      "learning_rate": 6.925898070244752e-05,
      "loss": 0.7368,
      "step": 266
    },
    {
      "epoch": 1.9225225225225224,
      "grad_norm": 4.181150436401367,
      "learning_rate": 6.845646615147445e-05,
      "loss": 0.5578,
      "step": 267
    },
    {
      "epoch": 1.9297297297297298,
      "grad_norm": 3.141552448272705,
      "learning_rate": 6.765620128507619e-05,
      "loss": 0.4533,
      "step": 268
    },
    {
      "epoch": 1.936936936936937,
      "grad_norm": 4.941766738891602,
      "learning_rate": 6.685824317813643e-05,
      "loss": 0.8238,
      "step": 269
    },
    {
      "epoch": 1.9441441441441443,
      "grad_norm": 4.092807769775391,
      "learning_rate": 6.606264874102079e-05,
      "loss": 0.5195,
      "step": 270
    },
    {
      "epoch": 1.9513513513513514,
      "grad_norm": 4.641556262969971,
      "learning_rate": 6.526947471551798e-05,
      "loss": 0.7784,
      "step": 271
    },
    {
      "epoch": 1.9585585585585585,
      "grad_norm": 5.080158710479736,
      "learning_rate": 6.447877767079298e-05,
      "loss": 0.7487,
      "step": 272
    },
    {
      "epoch": 1.9657657657657657,
      "grad_norm": 4.7158403396606445,
      "learning_rate": 6.369061399935255e-05,
      "loss": 0.7191,
      "step": 273
    },
    {
      "epoch": 1.972972972972973,
      "grad_norm": 4.332622528076172,
      "learning_rate": 6.290503991302324e-05,
      "loss": 0.7141,
      "step": 274
    },
    {
      "epoch": 1.9801801801801802,
      "grad_norm": 3.9569380283355713,
      "learning_rate": 6.21221114389424e-05,
      "loss": 0.5547,
      "step": 275
    },
    {
      "epoch": 1.9873873873873875,
      "grad_norm": 4.2110371589660645,
      "learning_rate": 6.134188441556241e-05,
      "loss": 0.5634,
      "step": 276
    },
    {
      "epoch": 1.9945945945945946,
      "grad_norm": 3.706193685531616,
      "learning_rate": 6.0564414488668165e-05,
      "loss": 0.3742,
      "step": 277
    },
    {
      "epoch": 2.0,
      "grad_norm": 5.037712097167969,
      "learning_rate": 5.9789757107408416e-05,
      "loss": 0.6155,
      "step": 278
    },
    {
      "epoch": 2.007207207207207,
      "grad_norm": 2.617781639099121,
      "learning_rate": 5.901796752034128e-05,
      "loss": 0.2552,
      "step": 279
    },
    {
      "epoch": 2.0144144144144143,
      "grad_norm": 3.264190435409546,
      "learning_rate": 5.824910077149371e-05,
      "loss": 0.3758,
      "step": 280
    },
    {
      "epoch": 2.0216216216216214,
      "grad_norm": 2.382774829864502,
      "learning_rate": 5.748321169643596e-05,
      "loss": 0.2344,
      "step": 281
    },
    {
      "epoch": 2.028828828828829,
      "grad_norm": 2.84346604347229,
      "learning_rate": 5.672035491837053e-05,
      "loss": 0.2901,
      "step": 282
    },
    {
      "epoch": 2.036036036036036,
      "grad_norm": 3.0451385974884033,
      "learning_rate": 5.596058484423656e-05,
      "loss": 0.283,
      "step": 283
    },
    {
      "epoch": 2.0432432432432432,
      "grad_norm": 2.93656587600708,
      "learning_rate": 5.5203955660829544e-05,
      "loss": 0.2312,
      "step": 284
    },
    {
      "epoch": 2.0504504504504504,
      "grad_norm": 2.954282283782959,
      "learning_rate": 5.44505213309366e-05,
      "loss": 0.2203,
      "step": 285
    },
    {
      "epoch": 2.0576576576576575,
      "grad_norm": 3.2899863719940186,
      "learning_rate": 5.3700335589487925e-05,
      "loss": 0.2358,
      "step": 286
    },
    {
      "epoch": 2.064864864864865,
      "grad_norm": 3.8231899738311768,
      "learning_rate": 5.2953451939724454e-05,
      "loss": 0.3681,
      "step": 287
    },
    {
      "epoch": 2.0720720720720722,
      "grad_norm": 3.0866289138793945,
      "learning_rate": 5.220992364938193e-05,
      "loss": 0.2551,
      "step": 288
    },
    {
      "epoch": 2.0792792792792794,
      "grad_norm": 3.7291922569274902,
      "learning_rate": 5.146980374689192e-05,
      "loss": 0.2682,
      "step": 289
    },
    {
      "epoch": 2.0864864864864865,
      "grad_norm": 3.8686490058898926,
      "learning_rate": 5.073314501759977e-05,
      "loss": 0.3748,
      "step": 290
    },
    {
      "epoch": 2.0936936936936936,
      "grad_norm": 3.421870708465576,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.2552,
      "step": 291
    },
    {
      "epoch": 2.1009009009009008,
      "grad_norm": 2.767481803894043,
      "learning_rate": 4.9270420981989294e-05,
      "loss": 0.1309,
      "step": 292
    },
    {
      "epoch": 2.108108108108108,
      "grad_norm": 4.461688041687012,
      "learning_rate": 4.854445999713715e-05,
      "loss": 0.4446,
      "step": 293
    },
    {
      "epoch": 2.1153153153153155,
      "grad_norm": 4.609604358673096,
      "learning_rate": 4.7822168820975066e-05,
      "loss": 0.2715,
      "step": 294
    },
    {
      "epoch": 2.1225225225225226,
      "grad_norm": 4.200955390930176,
      "learning_rate": 4.710359896730379e-05,
      "loss": 0.1522,
      "step": 295
    },
    {
      "epoch": 2.1297297297297297,
      "grad_norm": 4.314525127410889,
      "learning_rate": 4.638880168451938e-05,
      "loss": 0.1918,
      "step": 296
    },
    {
      "epoch": 2.136936936936937,
      "grad_norm": 5.728034973144531,
      "learning_rate": 4.567782795195816e-05,
      "loss": 0.373,
      "step": 297
    },
    {
      "epoch": 2.144144144144144,
      "grad_norm": 3.6254327297210693,
      "learning_rate": 4.497072847626087e-05,
      "loss": 0.2126,
      "step": 298
    },
    {
      "epoch": 2.1513513513513516,
      "grad_norm": 5.762700080871582,
      "learning_rate": 4.426755368775637e-05,
      "loss": 0.3238,
      "step": 299
    },
    {
      "epoch": 2.1585585585585587,
      "grad_norm": 4.812894344329834,
      "learning_rate": 4.356835373686475e-05,
      "loss": 0.261,
      "step": 300
    }
  ],
  "logging_steps": 1,
  "max_steps": 414,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3170278325901995e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}