{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0075566750629723,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005037783375314861,
      "grad_norm": 0.3518223464488983,
      "learning_rate": 2e-05,
      "loss": 2.0757,
      "step": 1
    },
    {
      "epoch": 0.010075566750629723,
      "grad_norm": 0.4766307771205902,
      "learning_rate": 4e-05,
      "loss": 2.3191,
      "step": 2
    },
    {
      "epoch": 0.015113350125944584,
      "grad_norm": 0.36295855045318604,
      "learning_rate": 6e-05,
      "loss": 1.9787,
      "step": 3
    },
    {
      "epoch": 0.020151133501259445,
      "grad_norm": 0.307400107383728,
      "learning_rate": 8e-05,
      "loss": 1.8764,
      "step": 4
    },
    {
      "epoch": 0.02518891687657431,
      "grad_norm": 0.3723292350769043,
      "learning_rate": 0.0001,
      "loss": 2.0876,
      "step": 5
    },
    {
      "epoch": 0.030226700251889168,
      "grad_norm": 0.37307557463645935,
      "learning_rate": 0.00012,
      "loss": 1.8658,
      "step": 6
    },
    {
      "epoch": 0.03526448362720403,
      "grad_norm": 0.435854434967041,
      "learning_rate": 0.00014,
      "loss": 2.0115,
      "step": 7
    },
    {
      "epoch": 0.04030226700251889,
      "grad_norm": 0.6088196039199829,
      "learning_rate": 0.00016,
      "loss": 2.184,
      "step": 8
    },
    {
      "epoch": 0.04534005037783375,
      "grad_norm": 0.32109102606773376,
      "learning_rate": 0.00018,
      "loss": 1.7607,
      "step": 9
    },
    {
      "epoch": 0.05037783375314862,
      "grad_norm": 0.36787062883377075,
      "learning_rate": 0.0002,
      "loss": 1.5996,
      "step": 10
    },
    {
      "epoch": 0.055415617128463476,
      "grad_norm": 0.3893103003501892,
      "learning_rate": 0.00019894736842105264,
      "loss": 1.6031,
      "step": 11
    },
    {
      "epoch": 0.060453400503778336,
      "grad_norm": 0.5323490500450134,
      "learning_rate": 0.00019789473684210526,
      "loss": 1.5834,
      "step": 12
    },
    {
      "epoch": 0.0654911838790932,
      "grad_norm": 0.773453950881958,
      "learning_rate": 0.0001968421052631579,
      "loss": 1.574,
      "step": 13
    },
    {
      "epoch": 0.07052896725440806,
      "grad_norm": 0.5621123313903809,
      "learning_rate": 0.00019578947368421054,
      "loss": 1.2272,
      "step": 14
    },
    {
      "epoch": 0.07556675062972293,
      "grad_norm": 0.7536848187446594,
      "learning_rate": 0.00019473684210526317,
      "loss": 1.2776,
      "step": 15
    },
    {
      "epoch": 0.08060453400503778,
      "grad_norm": 0.7452588677406311,
      "learning_rate": 0.0001936842105263158,
      "loss": 1.1667,
      "step": 16
    },
    {
      "epoch": 0.08564231738035265,
      "grad_norm": 0.7769160270690918,
      "learning_rate": 0.00019263157894736842,
      "loss": 1.0503,
      "step": 17
    },
    {
      "epoch": 0.0906801007556675,
      "grad_norm": 0.781049907207489,
      "learning_rate": 0.00019157894736842104,
      "loss": 1.0204,
      "step": 18
    },
    {
      "epoch": 0.09571788413098237,
      "grad_norm": 0.753268837928772,
      "learning_rate": 0.0001905263157894737,
      "loss": 1.1032,
      "step": 19
    },
    {
      "epoch": 0.10075566750629723,
      "grad_norm": 0.8446284532546997,
      "learning_rate": 0.00018947368421052632,
      "loss": 0.7637,
      "step": 20
    },
    {
      "epoch": 0.10579345088161209,
      "grad_norm": 3.604651927947998,
      "learning_rate": 0.00018842105263157898,
      "loss": 0.9087,
      "step": 21
    },
    {
      "epoch": 0.11083123425692695,
      "grad_norm": 0.9568591713905334,
      "learning_rate": 0.0001873684210526316,
      "loss": 0.851,
      "step": 22
    },
    {
      "epoch": 0.11586901763224182,
      "grad_norm": 1.1816169023513794,
      "learning_rate": 0.00018631578947368423,
      "loss": 0.5488,
      "step": 23
    },
    {
      "epoch": 0.12090680100755667,
      "grad_norm": 0.9833171963691711,
      "learning_rate": 0.00018526315789473685,
      "loss": 0.7534,
      "step": 24
    },
    {
      "epoch": 0.12594458438287154,
      "grad_norm": 1.3493332862854004,
      "learning_rate": 0.00018421052631578948,
      "loss": 0.593,
      "step": 25
    },
    {
      "epoch": 0.1309823677581864,
      "grad_norm": 0.7266058921813965,
      "learning_rate": 0.0001831578947368421,
      "loss": 0.574,
      "step": 26
    },
    {
      "epoch": 0.13602015113350127,
      "grad_norm": 0.7107939720153809,
      "learning_rate": 0.00018210526315789476,
      "loss": 0.2413,
      "step": 27
    },
    {
      "epoch": 0.14105793450881612,
      "grad_norm": 0.7920565605163574,
      "learning_rate": 0.00018105263157894739,
      "loss": 0.4325,
      "step": 28
    },
    {
      "epoch": 0.14609571788413098,
      "grad_norm": 0.9443809390068054,
      "learning_rate": 0.00018,
      "loss": 0.4232,
      "step": 29
    },
    {
      "epoch": 0.15113350125944586,
      "grad_norm": 0.5944586992263794,
      "learning_rate": 0.00017894736842105264,
      "loss": 0.3594,
      "step": 30
    },
    {
      "epoch": 0.1561712846347607,
      "grad_norm": 0.5987979173660278,
      "learning_rate": 0.00017789473684210526,
      "loss": 0.3781,
      "step": 31
    },
    {
      "epoch": 0.16120906801007556,
      "grad_norm": 0.6795870661735535,
      "learning_rate": 0.0001768421052631579,
      "loss": 0.5617,
      "step": 32
    },
    {
      "epoch": 0.16624685138539042,
      "grad_norm": 0.8870770931243896,
      "learning_rate": 0.00017578947368421052,
      "loss": 0.5301,
      "step": 33
    },
    {
      "epoch": 0.1712846347607053,
      "grad_norm": 0.8014320731163025,
      "learning_rate": 0.00017473684210526317,
      "loss": 0.4682,
      "step": 34
    },
    {
      "epoch": 0.17632241813602015,
      "grad_norm": 0.6445375680923462,
      "learning_rate": 0.0001736842105263158,
      "loss": 0.3388,
      "step": 35
    },
    {
      "epoch": 0.181360201511335,
      "grad_norm": 0.6574522852897644,
      "learning_rate": 0.00017263157894736842,
      "loss": 0.5185,
      "step": 36
    },
    {
      "epoch": 0.18639798488664988,
      "grad_norm": 0.5030068159103394,
      "learning_rate": 0.00017157894736842107,
      "loss": 0.2316,
      "step": 37
    },
    {
      "epoch": 0.19143576826196473,
      "grad_norm": 0.773057758808136,
      "learning_rate": 0.0001705263157894737,
      "loss": 0.3112,
      "step": 38
    },
    {
      "epoch": 0.1964735516372796,
      "grad_norm": 0.6356672048568726,
      "learning_rate": 0.00016947368421052633,
      "loss": 0.268,
      "step": 39
    },
    {
      "epoch": 0.20151133501259447,
      "grad_norm": 0.5076678991317749,
      "learning_rate": 0.00016842105263157895,
      "loss": 0.495,
      "step": 40
    },
    {
      "epoch": 0.20654911838790932,
      "grad_norm": 0.6496306657791138,
      "learning_rate": 0.0001673684210526316,
      "loss": 0.1888,
      "step": 41
    },
    {
      "epoch": 0.21158690176322417,
      "grad_norm": 1.2327401638031006,
      "learning_rate": 0.00016631578947368423,
      "loss": 0.3528,
      "step": 42
    },
    {
      "epoch": 0.21662468513853905,
      "grad_norm": 0.6327301263809204,
      "learning_rate": 0.00016526315789473686,
      "loss": 0.4691,
      "step": 43
    },
    {
      "epoch": 0.2216624685138539,
      "grad_norm": 0.864808976650238,
      "learning_rate": 0.00016421052631578948,
      "loss": 0.6131,
      "step": 44
    },
    {
      "epoch": 0.22670025188916876,
      "grad_norm": 0.6248288154602051,
      "learning_rate": 0.0001631578947368421,
      "loss": 0.3539,
      "step": 45
    },
    {
      "epoch": 0.23173803526448364,
      "grad_norm": 0.3140046298503876,
      "learning_rate": 0.00016210526315789473,
      "loss": 0.2844,
      "step": 46
    },
    {
      "epoch": 0.2367758186397985,
      "grad_norm": 0.7335410714149475,
      "learning_rate": 0.00016105263157894736,
      "loss": 0.63,
      "step": 47
    },
    {
      "epoch": 0.24181360201511334,
      "grad_norm": 0.5439632534980774,
      "learning_rate": 0.00016,
      "loss": 0.1825,
      "step": 48
    },
    {
      "epoch": 0.24685138539042822,
      "grad_norm": 0.6237998008728027,
      "learning_rate": 0.00015894736842105264,
      "loss": 0.3802,
      "step": 49
    },
    {
      "epoch": 0.2518891687657431,
      "grad_norm": 0.36704376339912415,
      "learning_rate": 0.00015789473684210527,
      "loss": 0.0994,
      "step": 50
    },
    {
      "epoch": 0.25692695214105793,
      "grad_norm": 0.4603656530380249,
      "learning_rate": 0.0001568421052631579,
      "loss": 0.2473,
      "step": 51
    },
    {
      "epoch": 0.2619647355163728,
      "grad_norm": 0.3848342299461365,
      "learning_rate": 0.00015578947368421052,
      "loss": 0.1398,
      "step": 52
    },
    {
      "epoch": 0.26700251889168763,
      "grad_norm": 0.6655743718147278,
      "learning_rate": 0.00015473684210526317,
      "loss": 0.4164,
      "step": 53
    },
    {
      "epoch": 0.27204030226700254,
      "grad_norm": 0.7751195430755615,
      "learning_rate": 0.0001536842105263158,
      "loss": 0.3564,
      "step": 54
    },
    {
      "epoch": 0.2770780856423174,
      "grad_norm": 0.6190752387046814,
      "learning_rate": 0.00015263157894736845,
      "loss": 0.3459,
      "step": 55
    },
    {
      "epoch": 0.28211586901763225,
      "grad_norm": 0.6057133674621582,
      "learning_rate": 0.00015157894736842108,
      "loss": 0.356,
      "step": 56
    },
    {
      "epoch": 0.2871536523929471,
      "grad_norm": 1.0536139011383057,
      "learning_rate": 0.0001505263157894737,
      "loss": 0.2324,
      "step": 57
    },
    {
      "epoch": 0.29219143576826195,
      "grad_norm": 0.7755753397941589,
      "learning_rate": 0.00014947368421052633,
      "loss": 0.4299,
      "step": 58
    },
    {
      "epoch": 0.2972292191435768,
      "grad_norm": 0.6408481597900391,
      "learning_rate": 0.00014842105263157895,
      "loss": 0.2747,
      "step": 59
    },
    {
      "epoch": 0.3022670025188917,
      "grad_norm": 0.6968539357185364,
      "learning_rate": 0.00014736842105263158,
      "loss": 0.1145,
      "step": 60
    },
    {
      "epoch": 0.30730478589420657,
      "grad_norm": 0.49692606925964355,
      "learning_rate": 0.00014631578947368423,
      "loss": 0.2619,
      "step": 61
    },
    {
      "epoch": 0.3123425692695214,
      "grad_norm": 0.3295464515686035,
      "learning_rate": 0.00014526315789473686,
      "loss": 0.0819,
      "step": 62
    },
    {
      "epoch": 0.31738035264483627,
      "grad_norm": 0.37510472536087036,
      "learning_rate": 0.00014421052631578948,
      "loss": 0.1576,
      "step": 63
    },
    {
      "epoch": 0.3224181360201511,
      "grad_norm": 0.5883765816688538,
      "learning_rate": 0.0001431578947368421,
      "loss": 0.1572,
      "step": 64
    },
    {
      "epoch": 0.327455919395466,
      "grad_norm": 0.3986837565898895,
      "learning_rate": 0.00014210526315789474,
      "loss": 0.3157,
      "step": 65
    },
    {
      "epoch": 0.33249370277078083,
      "grad_norm": 1.0316702127456665,
      "learning_rate": 0.00014105263157894736,
      "loss": 0.2099,
      "step": 66
    },
    {
      "epoch": 0.33753148614609574,
      "grad_norm": 0.6176291704177856,
      "learning_rate": 0.00014,
      "loss": 0.1361,
      "step": 67
    },
    {
      "epoch": 0.3425692695214106,
      "grad_norm": 0.37712040543556213,
      "learning_rate": 0.00013894736842105264,
      "loss": 0.2508,
      "step": 68
    },
    {
      "epoch": 0.34760705289672544,
      "grad_norm": 0.3802729845046997,
      "learning_rate": 0.00013789473684210527,
      "loss": 0.1122,
      "step": 69
    },
    {
      "epoch": 0.3526448362720403,
      "grad_norm": 0.481282502412796,
      "learning_rate": 0.0001368421052631579,
      "loss": 0.2649,
      "step": 70
    },
    {
      "epoch": 0.35768261964735515,
      "grad_norm": 0.5663158893585205,
      "learning_rate": 0.00013578947368421055,
      "loss": 0.1305,
      "step": 71
    },
    {
      "epoch": 0.36272040302267,
      "grad_norm": 0.5812940001487732,
      "learning_rate": 0.00013473684210526317,
      "loss": 0.3085,
      "step": 72
    },
    {
      "epoch": 0.3677581863979849,
      "grad_norm": 0.4372013211250305,
      "learning_rate": 0.0001336842105263158,
      "loss": 0.1936,
      "step": 73
    },
    {
      "epoch": 0.37279596977329976,
      "grad_norm": 0.20600414276123047,
      "learning_rate": 0.00013263157894736842,
      "loss": 0.0684,
      "step": 74
    },
    {
      "epoch": 0.3778337531486146,
      "grad_norm": 0.38698187470436096,
      "learning_rate": 0.00013157894736842108,
      "loss": 0.1676,
      "step": 75
    },
    {
      "epoch": 0.38287153652392947,
      "grad_norm": 0.38309377431869507,
      "learning_rate": 0.0001305263157894737,
      "loss": 0.1936,
      "step": 76
    },
    {
      "epoch": 0.3879093198992443,
      "grad_norm": 0.3905870318412781,
      "learning_rate": 0.00012947368421052633,
      "loss": 0.1431,
      "step": 77
    },
    {
      "epoch": 0.3929471032745592,
      "grad_norm": 0.43961116671562195,
      "learning_rate": 0.00012842105263157895,
      "loss": 0.2374,
      "step": 78
    },
    {
      "epoch": 0.3979848866498741,
      "grad_norm": 1.39609694480896,
      "learning_rate": 0.00012736842105263158,
      "loss": 0.2106,
      "step": 79
    },
    {
      "epoch": 0.40302267002518893,
      "grad_norm": 0.3844812214374542,
      "learning_rate": 0.0001263157894736842,
      "loss": 0.0977,
      "step": 80
    },
    {
      "epoch": 0.4080604534005038,
      "grad_norm": 0.23563021421432495,
      "learning_rate": 0.00012526315789473683,
      "loss": 0.0693,
      "step": 81
    },
    {
      "epoch": 0.41309823677581864,
      "grad_norm": 0.3840598464012146,
      "learning_rate": 0.00012421052631578949,
      "loss": 0.17,
      "step": 82
    },
    {
      "epoch": 0.4181360201511335,
      "grad_norm": 0.4412382245063782,
      "learning_rate": 0.0001231578947368421,
      "loss": 0.148,
      "step": 83
    },
    {
      "epoch": 0.42317380352644834,
      "grad_norm": 0.27377572655677795,
      "learning_rate": 0.00012210526315789474,
      "loss": 0.073,
      "step": 84
    },
    {
      "epoch": 0.4282115869017632,
      "grad_norm": 0.2707730829715729,
      "learning_rate": 0.00012105263157894738,
      "loss": 0.1278,
      "step": 85
    },
    {
      "epoch": 0.4332493702770781,
      "grad_norm": 0.32431530952453613,
      "learning_rate": 0.00012,
      "loss": 0.1274,
      "step": 86
    },
    {
      "epoch": 0.43828715365239296,
      "grad_norm": 0.2874161899089813,
      "learning_rate": 0.00011894736842105263,
      "loss": 0.1262,
      "step": 87
    },
    {
      "epoch": 0.4433249370277078,
      "grad_norm": 0.3821753263473511,
      "learning_rate": 0.00011789473684210525,
      "loss": 0.1399,
      "step": 88
    },
    {
      "epoch": 0.44836272040302266,
      "grad_norm": 0.3060382306575775,
      "learning_rate": 0.00011684210526315791,
      "loss": 0.1567,
      "step": 89
    },
    {
      "epoch": 0.4534005037783375,
      "grad_norm": 0.26529163122177124,
      "learning_rate": 0.00011578947368421053,
      "loss": 0.0986,
      "step": 90
    },
    {
      "epoch": 0.45843828715365237,
      "grad_norm": 0.44558581709861755,
      "learning_rate": 0.00011473684210526316,
      "loss": 0.2247,
      "step": 91
    },
    {
      "epoch": 0.4634760705289673,
      "grad_norm": 0.33645686507225037,
      "learning_rate": 0.0001136842105263158,
      "loss": 0.181,
      "step": 92
    },
    {
      "epoch": 0.46851385390428213,
      "grad_norm": 0.14126701653003693,
      "learning_rate": 0.00011263157894736843,
      "loss": 0.0624,
      "step": 93
    },
    {
      "epoch": 0.473551637279597,
      "grad_norm": 0.31580325961112976,
      "learning_rate": 0.00011157894736842105,
      "loss": 0.1199,
      "step": 94
    },
    {
      "epoch": 0.47858942065491183,
      "grad_norm": 0.40185511112213135,
      "learning_rate": 0.0001105263157894737,
      "loss": 0.1006,
      "step": 95
    },
    {
      "epoch": 0.4836272040302267,
      "grad_norm": 0.3965336084365845,
      "learning_rate": 0.00010947368421052633,
      "loss": 0.1521,
      "step": 96
    },
    {
      "epoch": 0.48866498740554154,
      "grad_norm": 0.5877782702445984,
      "learning_rate": 0.00010842105263157896,
      "loss": 0.2581,
      "step": 97
    },
    {
      "epoch": 0.49370277078085645,
      "grad_norm": 0.5336182117462158,
      "learning_rate": 0.00010736842105263158,
      "loss": 0.2348,
      "step": 98
    },
    {
      "epoch": 0.4987405541561713,
      "grad_norm": 0.19688697159290314,
      "learning_rate": 0.00010631578947368421,
      "loss": 0.0784,
      "step": 99
    },
    {
      "epoch": 0.5037783375314862,
      "grad_norm": 0.2962247133255005,
      "learning_rate": 0.00010526315789473685,
      "loss": 0.1655,
      "step": 100
    },
    {
      "epoch": 0.5088161209068011,
      "grad_norm": 0.1825219988822937,
      "learning_rate": 0.00010421052631578947,
      "loss": 0.0822,
      "step": 101
    },
    {
      "epoch": 0.5138539042821159,
      "grad_norm": 0.6996546387672424,
      "learning_rate": 0.00010315789473684211,
      "loss": 0.2294,
      "step": 102
    },
    {
      "epoch": 0.5188916876574308,
      "grad_norm": 0.39225417375564575,
      "learning_rate": 0.00010210526315789475,
      "loss": 0.1107,
      "step": 103
    },
    {
      "epoch": 0.5239294710327456,
      "grad_norm": 0.19891326129436493,
      "learning_rate": 0.00010105263157894738,
      "loss": 0.0728,
      "step": 104
    },
    {
      "epoch": 0.5289672544080605,
      "grad_norm": 0.6324350833892822,
      "learning_rate": 0.0001,
      "loss": 0.3342,
      "step": 105
    },
    {
      "epoch": 0.5340050377833753,
      "grad_norm": 0.4613906741142273,
      "learning_rate": 9.894736842105263e-05,
      "loss": 0.2443,
      "step": 106
    },
    {
      "epoch": 0.5390428211586902,
      "grad_norm": 0.18734556436538696,
      "learning_rate": 9.789473684210527e-05,
      "loss": 0.0727,
      "step": 107
    },
    {
      "epoch": 0.5440806045340051,
      "grad_norm": 0.339933305978775,
      "learning_rate": 9.68421052631579e-05,
      "loss": 0.2469,
      "step": 108
    },
    {
      "epoch": 0.5491183879093199,
      "grad_norm": 0.48570263385772705,
      "learning_rate": 9.578947368421052e-05,
      "loss": 0.1371,
      "step": 109
    },
    {
      "epoch": 0.5541561712846348,
      "grad_norm": 0.30081725120544434,
      "learning_rate": 9.473684210526316e-05,
      "loss": 0.0915,
      "step": 110
    },
    {
      "epoch": 0.5591939546599496,
      "grad_norm": 0.26690733432769775,
      "learning_rate": 9.36842105263158e-05,
      "loss": 0.1134,
      "step": 111
    },
    {
      "epoch": 0.5642317380352645,
      "grad_norm": 0.4141266345977783,
      "learning_rate": 9.263157894736843e-05,
      "loss": 0.1727,
      "step": 112
    },
    {
      "epoch": 0.5692695214105793,
      "grad_norm": 0.33365899324417114,
      "learning_rate": 9.157894736842105e-05,
      "loss": 0.1533,
      "step": 113
    },
    {
      "epoch": 0.5743073047858942,
      "grad_norm": 0.36651313304901123,
      "learning_rate": 9.052631578947369e-05,
      "loss": 0.1598,
      "step": 114
    },
    {
      "epoch": 0.5793450881612091,
      "grad_norm": 0.39123257994651794,
      "learning_rate": 8.947368421052632e-05,
      "loss": 0.1852,
      "step": 115
    },
    {
      "epoch": 0.5843828715365239,
      "grad_norm": 1.0382803678512573,
      "learning_rate": 8.842105263157894e-05,
      "loss": 0.3205,
      "step": 116
    },
    {
      "epoch": 0.5894206549118388,
      "grad_norm": 0.13224704563617706,
      "learning_rate": 8.736842105263158e-05,
      "loss": 0.0522,
      "step": 117
    },
    {
      "epoch": 0.5944584382871536,
      "grad_norm": 0.561414897441864,
      "learning_rate": 8.631578947368421e-05,
      "loss": 0.1471,
      "step": 118
    },
    {
      "epoch": 0.5994962216624685,
      "grad_norm": 0.40099918842315674,
      "learning_rate": 8.526315789473685e-05,
      "loss": 0.194,
      "step": 119
    },
    {
      "epoch": 0.6045340050377834,
      "grad_norm": 0.4563421607017517,
      "learning_rate": 8.421052631578948e-05,
      "loss": 0.1486,
      "step": 120
    },
    {
      "epoch": 0.6095717884130982,
      "grad_norm": 0.48477980494499207,
      "learning_rate": 8.315789473684212e-05,
      "loss": 0.1673,
      "step": 121
    },
    {
      "epoch": 0.6146095717884131,
      "grad_norm": 0.22391052544116974,
      "learning_rate": 8.210526315789474e-05,
      "loss": 0.0837,
      "step": 122
    },
    {
      "epoch": 0.6196473551637279,
      "grad_norm": 0.3828778564929962,
      "learning_rate": 8.105263157894737e-05,
      "loss": 0.1297,
      "step": 123
    },
    {
      "epoch": 0.6246851385390428,
      "grad_norm": 0.3207460045814514,
      "learning_rate": 8e-05,
      "loss": 0.1185,
      "step": 124
    },
    {
      "epoch": 0.6297229219143576,
      "grad_norm": 0.37645190954208374,
      "learning_rate": 7.894736842105263e-05,
      "loss": 0.1658,
      "step": 125
    },
    {
      "epoch": 0.6347607052896725,
      "grad_norm": 0.3294924199581146,
      "learning_rate": 7.789473684210526e-05,
      "loss": 0.1122,
      "step": 126
    },
    {
      "epoch": 0.6397984886649875,
      "grad_norm": 0.3875572979450226,
      "learning_rate": 7.68421052631579e-05,
      "loss": 0.2184,
      "step": 127
    },
    {
      "epoch": 0.6448362720403022,
      "grad_norm": 0.4404910206794739,
      "learning_rate": 7.578947368421054e-05,
      "loss": 0.1977,
      "step": 128
    },
    {
      "epoch": 0.6498740554156172,
      "grad_norm": 0.10779596865177155,
      "learning_rate": 7.473684210526316e-05,
      "loss": 0.0367,
      "step": 129
    },
    {
      "epoch": 0.654911838790932,
      "grad_norm": 0.16290880739688873,
      "learning_rate": 7.368421052631579e-05,
      "loss": 0.0449,
      "step": 130
    },
    {
      "epoch": 0.6599496221662469,
      "grad_norm": 0.314554899930954,
      "learning_rate": 7.263157894736843e-05,
      "loss": 0.0759,
      "step": 131
    },
    {
      "epoch": 0.6649874055415617,
      "grad_norm": 0.3773807883262634,
      "learning_rate": 7.157894736842105e-05,
      "loss": 0.1595,
      "step": 132
    },
    {
      "epoch": 0.6700251889168766,
      "grad_norm": 0.3229176998138428,
      "learning_rate": 7.052631578947368e-05,
      "loss": 0.152,
      "step": 133
    },
    {
      "epoch": 0.6750629722921915,
      "grad_norm": 0.41587066650390625,
      "learning_rate": 6.947368421052632e-05,
      "loss": 0.0599,
      "step": 134
    },
    {
      "epoch": 0.6801007556675063,
      "grad_norm": 0.2982085943222046,
      "learning_rate": 6.842105263157895e-05,
      "loss": 0.104,
      "step": 135
    },
    {
      "epoch": 0.6851385390428212,
      "grad_norm": 0.5094094276428223,
      "learning_rate": 6.736842105263159e-05,
      "loss": 0.1886,
      "step": 136
    },
    {
      "epoch": 0.690176322418136,
      "grad_norm": 0.3865503668785095,
      "learning_rate": 6.631578947368421e-05,
      "loss": 0.337,
      "step": 137
    },
    {
      "epoch": 0.6952141057934509,
      "grad_norm": 0.4261918365955353,
      "learning_rate": 6.526315789473685e-05,
      "loss": 0.1312,
      "step": 138
    },
    {
      "epoch": 0.7002518891687658,
      "grad_norm": 0.31689754128456116,
      "learning_rate": 6.421052631578948e-05,
      "loss": 0.1656,
      "step": 139
    },
    {
      "epoch": 0.7052896725440806,
      "grad_norm": 0.46111634373664856,
      "learning_rate": 6.31578947368421e-05,
      "loss": 0.1724,
      "step": 140
    },
    {
      "epoch": 0.7103274559193955,
      "grad_norm": 0.20221607387065887,
      "learning_rate": 6.210526315789474e-05,
      "loss": 0.0835,
      "step": 141
    },
    {
      "epoch": 0.7153652392947103,
      "grad_norm": 0.3247107267379761,
      "learning_rate": 6.105263157894737e-05,
      "loss": 0.1468,
      "step": 142
    },
    {
      "epoch": 0.7204030226700252,
      "grad_norm": 0.2768368124961853,
      "learning_rate": 6e-05,
      "loss": 0.1175,
      "step": 143
    },
    {
      "epoch": 0.72544080604534,
      "grad_norm": 0.27166804671287537,
      "learning_rate": 5.894736842105263e-05,
      "loss": 0.0795,
      "step": 144
    },
    {
      "epoch": 0.7304785894206549,
      "grad_norm": 0.10148835927248001,
      "learning_rate": 5.789473684210527e-05,
      "loss": 0.0391,
      "step": 145
    },
    {
      "epoch": 0.7355163727959698,
      "grad_norm": 0.2717987596988678,
      "learning_rate": 5.68421052631579e-05,
      "loss": 0.0882,
      "step": 146
    },
    {
      "epoch": 0.7405541561712846,
      "grad_norm": 0.18068474531173706,
      "learning_rate": 5.5789473684210526e-05,
      "loss": 0.0565,
      "step": 147
    },
    {
      "epoch": 0.7455919395465995,
      "grad_norm": 0.4956297278404236,
      "learning_rate": 5.4736842105263165e-05,
      "loss": 0.1371,
      "step": 148
    },
    {
      "epoch": 0.7506297229219143,
      "grad_norm": 0.5892757177352905,
      "learning_rate": 5.368421052631579e-05,
      "loss": 0.1155,
      "step": 149
    },
    {
      "epoch": 0.7556675062972292,
      "grad_norm": 0.23781464993953705,
      "learning_rate": 5.2631578947368424e-05,
      "loss": 0.1411,
      "step": 150
    },
    {
      "epoch": 0.760705289672544,
      "grad_norm": 0.26974135637283325,
      "learning_rate": 5.157894736842106e-05,
      "loss": 0.0933,
      "step": 151
    },
    {
      "epoch": 0.7657430730478589,
      "grad_norm": 0.11715666949748993,
      "learning_rate": 5.052631578947369e-05,
      "loss": 0.0466,
      "step": 152
    },
    {
      "epoch": 0.7707808564231738,
      "grad_norm": 0.21726714074611664,
      "learning_rate": 4.9473684210526315e-05,
      "loss": 0.0699,
      "step": 153
    },
    {
      "epoch": 0.7758186397984886,
      "grad_norm": 0.2556859254837036,
      "learning_rate": 4.842105263157895e-05,
      "loss": 0.0981,
      "step": 154
    },
    {
      "epoch": 0.7808564231738035,
      "grad_norm": 0.12423796951770782,
      "learning_rate": 4.736842105263158e-05,
      "loss": 0.0455,
      "step": 155
    },
    {
      "epoch": 0.7858942065491183,
      "grad_norm": 0.20723406970500946,
      "learning_rate": 4.6315789473684214e-05,
      "loss": 0.088,
      "step": 156
    },
    {
      "epoch": 0.7909319899244333,
      "grad_norm": 0.18069583177566528,
      "learning_rate": 4.5263157894736846e-05,
      "loss": 0.0684,
      "step": 157
    },
    {
      "epoch": 0.7959697732997482,
      "grad_norm": 0.19325508177280426,
      "learning_rate": 4.421052631578947e-05,
      "loss": 0.0833,
      "step": 158
    },
    {
      "epoch": 0.801007556675063,
      "grad_norm": 0.10966863483190536,
      "learning_rate": 4.3157894736842105e-05,
      "loss": 0.0445,
      "step": 159
    },
    {
      "epoch": 0.8060453400503779,
      "grad_norm": 0.16270394623279572,
      "learning_rate": 4.210526315789474e-05,
      "loss": 0.0656,
      "step": 160
    },
    {
      "epoch": 0.8110831234256927,
      "grad_norm": 0.13497555255889893,
      "learning_rate": 4.105263157894737e-05,
      "loss": 0.0471,
      "step": 161
    },
    {
      "epoch": 0.8161209068010076,
      "grad_norm": 0.4956112504005432,
      "learning_rate": 4e-05,
      "loss": 0.1575,
      "step": 162
    },
    {
      "epoch": 0.8211586901763224,
      "grad_norm": 0.20514702796936035,
      "learning_rate": 3.894736842105263e-05,
      "loss": 0.0584,
      "step": 163
    },
    {
      "epoch": 0.8261964735516373,
      "grad_norm": 0.25432294607162476,
      "learning_rate": 3.789473684210527e-05,
      "loss": 0.1155,
      "step": 164
    },
    {
      "epoch": 0.8312342569269522,
      "grad_norm": 0.1398286372423172,
      "learning_rate": 3.6842105263157895e-05,
      "loss": 0.0557,
      "step": 165
    },
    {
      "epoch": 0.836272040302267,
      "grad_norm": 0.41116705536842346,
      "learning_rate": 3.578947368421053e-05,
      "loss": 0.1305,
      "step": 166
    },
    {
      "epoch": 0.8413098236775819,
      "grad_norm": 0.2796281576156616,
      "learning_rate": 3.473684210526316e-05,
      "loss": 0.0721,
      "step": 167
    },
    {
      "epoch": 0.8463476070528967,
      "grad_norm": 0.10607501864433289,
      "learning_rate": 3.368421052631579e-05,
      "loss": 0.0425,
      "step": 168
    },
    {
      "epoch": 0.8513853904282116,
      "grad_norm": 0.462009996175766,
      "learning_rate": 3.2631578947368426e-05,
      "loss": 0.0876,
      "step": 169
    },
    {
      "epoch": 0.8564231738035264,
      "grad_norm": 0.3923139274120331,
      "learning_rate": 3.157894736842105e-05,
      "loss": 0.0865,
      "step": 170
    },
    {
      "epoch": 0.8614609571788413,
      "grad_norm": 0.23710176348686218,
      "learning_rate": 3.0526315789473684e-05,
      "loss": 0.1687,
      "step": 171
    },
    {
      "epoch": 0.8664987405541562,
      "grad_norm": 0.5242993235588074,
      "learning_rate": 2.9473684210526314e-05,
      "loss": 0.1478,
      "step": 172
    },
    {
      "epoch": 0.871536523929471,
      "grad_norm": 0.12361127138137817,
      "learning_rate": 2.842105263157895e-05,
      "loss": 0.0555,
      "step": 173
    },
    {
      "epoch": 0.8765743073047859,
      "grad_norm": 0.31850466132164,
      "learning_rate": 2.7368421052631583e-05,
      "loss": 0.1228,
      "step": 174
    },
    {
      "epoch": 0.8816120906801007,
      "grad_norm": 0.23594436049461365,
      "learning_rate": 2.6315789473684212e-05,
      "loss": 0.0663,
      "step": 175
    },
    {
      "epoch": 0.8866498740554156,
      "grad_norm": 0.3258284330368042,
      "learning_rate": 2.5263157894736845e-05,
      "loss": 0.2063,
      "step": 176
    },
    {
      "epoch": 0.8916876574307305,
      "grad_norm": 0.3880285918712616,
      "learning_rate": 2.4210526315789474e-05,
      "loss": 0.1116,
      "step": 177
    },
    {
      "epoch": 0.8967254408060453,
      "grad_norm": 0.165984645485878,
      "learning_rate": 2.3157894736842107e-05,
      "loss": 0.0751,
      "step": 178
    },
    {
      "epoch": 0.9017632241813602,
      "grad_norm": 0.47083160281181335,
      "learning_rate": 2.2105263157894736e-05,
      "loss": 0.1682,
      "step": 179
    },
    {
      "epoch": 0.906801007556675,
      "grad_norm": 0.2563510239124298,
      "learning_rate": 2.105263157894737e-05,
      "loss": 0.0924,
      "step": 180
    },
    {
      "epoch": 0.9118387909319899,
      "grad_norm": 0.2977278232574463,
      "learning_rate": 2e-05,
      "loss": 0.107,
      "step": 181
    },
    {
      "epoch": 0.9168765743073047,
      "grad_norm": 0.16103056073188782,
      "learning_rate": 1.8947368421052634e-05,
      "loss": 0.0648,
      "step": 182
    },
    {
      "epoch": 0.9219143576826196,
      "grad_norm": 0.14750486612319946,
      "learning_rate": 1.7894736842105264e-05,
      "loss": 0.0613,
      "step": 183
    },
    {
      "epoch": 0.9269521410579346,
      "grad_norm": 0.4347628951072693,
      "learning_rate": 1.6842105263157896e-05,
      "loss": 0.1277,
      "step": 184
    },
    {
      "epoch": 0.9319899244332494,
      "grad_norm": 0.2826248109340668,
      "learning_rate": 1.5789473684210526e-05,
      "loss": 0.1377,
      "step": 185
    },
    {
      "epoch": 0.9370277078085643,
      "grad_norm": 0.29777997732162476,
      "learning_rate": 1.4736842105263157e-05,
      "loss": 0.0928,
      "step": 186
    },
    {
      "epoch": 0.9420654911838791,
      "grad_norm": 0.26641038060188293,
      "learning_rate": 1.3684210526315791e-05,
      "loss": 0.1496,
      "step": 187
    },
    {
      "epoch": 0.947103274559194,
      "grad_norm": 0.34339556097984314,
      "learning_rate": 1.2631578947368422e-05,
      "loss": 0.2262,
      "step": 188
    },
    {
      "epoch": 0.9521410579345088,
      "grad_norm": 0.13338394463062286,
      "learning_rate": 1.1578947368421053e-05,
      "loss": 0.0446,
      "step": 189
    },
    {
      "epoch": 0.9571788413098237,
      "grad_norm": 0.3551732301712036,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 0.0587,
      "step": 190
    },
    {
      "epoch": 0.9622166246851386,
      "grad_norm": 0.20613446831703186,
      "learning_rate": 9.473684210526317e-06,
      "loss": 0.1182,
      "step": 191
    },
    {
      "epoch": 0.9672544080604534,
      "grad_norm": 0.15159928798675537,
      "learning_rate": 8.421052631578948e-06,
      "loss": 0.0549,
      "step": 192
    },
    {
      "epoch": 0.9722921914357683,
      "grad_norm": 0.17634347081184387,
      "learning_rate": 7.3684210526315784e-06,
      "loss": 0.0599,
      "step": 193
    },
    {
      "epoch": 0.9773299748110831,
      "grad_norm": 0.40340152382850647,
      "learning_rate": 6.315789473684211e-06,
      "loss": 0.1586,
      "step": 194
    },
    {
      "epoch": 0.982367758186398,
      "grad_norm": 0.18197712302207947,
      "learning_rate": 5.263157894736842e-06,
      "loss": 0.0772,
      "step": 195
    },
    {
      "epoch": 0.9874055415617129,
      "grad_norm": 0.19643299281597137,
      "learning_rate": 4.210526315789474e-06,
      "loss": 0.1048,
      "step": 196
    },
    {
      "epoch": 0.9924433249370277,
      "grad_norm": 0.3259267508983612,
      "learning_rate": 3.1578947368421056e-06,
      "loss": 0.1996,
      "step": 197
    },
    {
      "epoch": 0.9974811083123426,
      "grad_norm": 0.2846713066101074,
      "learning_rate": 2.105263157894737e-06,
      "loss": 0.1113,
      "step": 198
    },
    {
      "epoch": 1.0025188916876575,
      "grad_norm": 0.06972451508045197,
      "learning_rate": 1.0526315789473685e-06,
      "loss": 0.0277,
      "step": 199
    },
    {
      "epoch": 1.0075566750629723,
      "grad_norm": 0.11068534851074219,
      "learning_rate": 0.0,
      "loss": 0.03,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.65920283789312e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}