{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9878213802435725,
  "eval_steps": 500,
  "global_step": 276,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010825439783491205,
      "grad_norm": 5.808025389606398,
      "learning_rate": 0.00011313708,
      "loss": 0.8567,
      "step": 1
    },
    {
      "epoch": 0.02165087956698241,
      "grad_norm": 63.70083680356305,
      "learning_rate": 0.00011313708,
      "loss": 3.0577,
      "step": 2
    },
    {
      "epoch": 0.03247631935047361,
      "grad_norm": 102.2601563378421,
      "learning_rate": 0.00011313708,
      "loss": 3.245,
      "step": 3
    },
    {
      "epoch": 0.04330175913396482,
      "grad_norm": 517.818032499253,
      "learning_rate": 0.00011313708,
      "loss": 10.4703,
      "step": 4
    },
    {
      "epoch": 0.05412719891745602,
      "grad_norm": 97.70792942908585,
      "learning_rate": 0.00011313708,
      "loss": 8.2239,
      "step": 5
    },
    {
      "epoch": 0.06495263870094722,
      "grad_norm": 139.40515698694134,
      "learning_rate": 0.00011313708,
      "loss": 7.5427,
      "step": 6
    },
    {
      "epoch": 0.07577807848443843,
      "grad_norm": 38.719549182895285,
      "learning_rate": 0.00011313708,
      "loss": 2.948,
      "step": 7
    },
    {
      "epoch": 0.08660351826792964,
      "grad_norm": 11.104588873802449,
      "learning_rate": 0.00011313708,
      "loss": 1.7519,
      "step": 8
    },
    {
      "epoch": 0.09742895805142084,
      "grad_norm": 249.30162080162287,
      "learning_rate": 0.00011313708,
      "loss": 2.3027,
      "step": 9
    },
    {
      "epoch": 0.10825439783491204,
      "grad_norm": 57.26401169307199,
      "learning_rate": 0.00011313708,
      "loss": 2.1727,
      "step": 10
    },
    {
      "epoch": 0.11907983761840325,
      "grad_norm": 154.85566650956403,
      "learning_rate": 0.00011313708,
      "loss": 4.2434,
      "step": 11
    },
    {
      "epoch": 0.12990527740189445,
      "grad_norm": 118.91304942926054,
      "learning_rate": 0.00011313708,
      "loss": 2.6824,
      "step": 12
    },
    {
      "epoch": 0.14073071718538566,
      "grad_norm": 8.62441539636698,
      "learning_rate": 0.00011313708,
      "loss": 1.4713,
      "step": 13
    },
    {
      "epoch": 0.15155615696887687,
      "grad_norm": 5.8329334972358575,
      "learning_rate": 0.00011313708,
      "loss": 1.2606,
      "step": 14
    },
    {
      "epoch": 0.16238159675236807,
      "grad_norm": 19.172130041954816,
      "learning_rate": 0.00011313708,
      "loss": 1.4758,
      "step": 15
    },
    {
      "epoch": 0.17320703653585928,
      "grad_norm": 6.990936525514284,
      "learning_rate": 0.00011313708,
      "loss": 1.146,
      "step": 16
    },
    {
      "epoch": 0.18403247631935046,
      "grad_norm": 2.8669615796156234,
      "learning_rate": 0.00011313708,
      "loss": 0.9958,
      "step": 17
    },
    {
      "epoch": 0.19485791610284167,
      "grad_norm": 2.172149401870726,
      "learning_rate": 0.00011313708,
      "loss": 0.8884,
      "step": 18
    },
    {
      "epoch": 0.20568335588633288,
      "grad_norm": 2.6427911214085924,
      "learning_rate": 0.00011313708,
      "loss": 0.8421,
      "step": 19
    },
    {
      "epoch": 0.2165087956698241,
      "grad_norm": 1.8811585286349286,
      "learning_rate": 0.00011313708,
      "loss": 0.8122,
      "step": 20
    },
    {
      "epoch": 0.2273342354533153,
      "grad_norm": 2.477011640586419,
      "learning_rate": 0.00011313708,
      "loss": 0.8148,
      "step": 21
    },
    {
      "epoch": 0.2381596752368065,
      "grad_norm": 3.5439729376670406,
      "learning_rate": 0.00011313708,
      "loss": 0.857,
      "step": 22
    },
    {
      "epoch": 0.2489851150202977,
      "grad_norm": 5.411413279293686,
      "learning_rate": 0.00011313708,
      "loss": 0.8983,
      "step": 23
    },
    {
      "epoch": 0.2598105548037889,
      "grad_norm": 1.9283128194762766,
      "learning_rate": 0.00011313708,
      "loss": 0.7966,
      "step": 24
    },
    {
      "epoch": 0.2706359945872801,
      "grad_norm": 2.612920494624994,
      "learning_rate": 0.00011313708,
      "loss": 0.766,
      "step": 25
    },
    {
      "epoch": 0.2814614343707713,
      "grad_norm": 1.1471114891937906,
      "learning_rate": 0.00011313708,
      "loss": 0.711,
      "step": 26
    },
    {
      "epoch": 0.2922868741542625,
      "grad_norm": 2.531736973390282,
      "learning_rate": 0.00011313708,
      "loss": 0.7224,
      "step": 27
    },
    {
      "epoch": 0.30311231393775373,
      "grad_norm": 1.389348030998938,
      "learning_rate": 0.00011313708,
      "loss": 0.7054,
      "step": 28
    },
    {
      "epoch": 0.31393775372124494,
      "grad_norm": 1.4832852073856424,
      "learning_rate": 0.00011313708,
      "loss": 0.69,
      "step": 29
    },
    {
      "epoch": 0.32476319350473615,
      "grad_norm": 1.1885525087217463,
      "learning_rate": 0.00011313708,
      "loss": 0.6633,
      "step": 30
    },
    {
      "epoch": 0.33558863328822736,
      "grad_norm": 0.789960974683348,
      "learning_rate": 0.00011313708,
      "loss": 0.6517,
      "step": 31
    },
    {
      "epoch": 0.34641407307171856,
      "grad_norm": 1.45945149308812,
      "learning_rate": 0.00011313708,
      "loss": 0.6425,
      "step": 32
    },
    {
      "epoch": 0.3572395128552097,
      "grad_norm": 0.9601099100161072,
      "learning_rate": 0.00011313708,
      "loss": 0.6358,
      "step": 33
    },
    {
      "epoch": 0.3680649526387009,
      "grad_norm": 1.0746701563839907,
      "learning_rate": 0.00011313708,
      "loss": 0.6306,
      "step": 34
    },
    {
      "epoch": 0.37889039242219213,
      "grad_norm": 0.8802641108555268,
      "learning_rate": 0.00011313708,
      "loss": 0.6054,
      "step": 35
    },
    {
      "epoch": 0.38971583220568334,
      "grad_norm": 0.9842667459921938,
      "learning_rate": 0.00011313708,
      "loss": 0.5953,
      "step": 36
    },
    {
      "epoch": 0.40054127198917455,
      "grad_norm": 1.008978507148328,
      "learning_rate": 0.00011313708,
      "loss": 0.6061,
      "step": 37
    },
    {
      "epoch": 0.41136671177266576,
      "grad_norm": 0.8819971357143546,
      "learning_rate": 0.00011313708,
      "loss": 0.5828,
      "step": 38
    },
    {
      "epoch": 0.42219215155615697,
      "grad_norm": 1.2452743540780522,
      "learning_rate": 0.00011313708,
      "loss": 0.586,
      "step": 39
    },
    {
      "epoch": 0.4330175913396482,
      "grad_norm": 0.9111567476287992,
      "learning_rate": 0.00011313708,
      "loss": 0.5781,
      "step": 40
    },
    {
      "epoch": 0.4438430311231394,
      "grad_norm": 0.9715389785577105,
      "learning_rate": 0.00011313708,
      "loss": 0.5754,
      "step": 41
    },
    {
      "epoch": 0.4546684709066306,
      "grad_norm": 1.253718592808374,
      "learning_rate": 0.00011313708,
      "loss": 0.5827,
      "step": 42
    },
    {
      "epoch": 0.4654939106901218,
      "grad_norm": 1.232248844790283,
      "learning_rate": 0.00011313708,
      "loss": 0.563,
      "step": 43
    },
    {
      "epoch": 0.476319350473613,
      "grad_norm": 0.9331651600470512,
      "learning_rate": 0.00011313708,
      "loss": 0.5667,
      "step": 44
    },
    {
      "epoch": 0.4871447902571042,
      "grad_norm": 1.1640027059611353,
      "learning_rate": 0.00011313708,
      "loss": 0.5616,
      "step": 45
    },
    {
      "epoch": 0.4979702300405954,
      "grad_norm": 0.7306266075470852,
      "learning_rate": 0.00011313708,
      "loss": 0.5559,
      "step": 46
    },
    {
      "epoch": 0.5087956698240866,
      "grad_norm": 0.9181622508919682,
      "learning_rate": 0.00011313708,
      "loss": 0.5506,
      "step": 47
    },
    {
      "epoch": 0.5196211096075778,
      "grad_norm": 0.9699132355343132,
      "learning_rate": 0.00011313708,
      "loss": 0.5471,
      "step": 48
    },
    {
      "epoch": 0.530446549391069,
      "grad_norm": 0.7508541455961231,
      "learning_rate": 0.00011313708,
      "loss": 0.5406,
      "step": 49
    },
    {
      "epoch": 0.5412719891745602,
      "grad_norm": 0.7088588238376171,
      "learning_rate": 0.00011313708,
      "loss": 0.535,
      "step": 50
    },
    {
      "epoch": 0.5520974289580515,
      "grad_norm": 0.6209144810203802,
      "learning_rate": 0.00011313708,
      "loss": 0.5289,
      "step": 51
    },
    {
      "epoch": 0.5629228687415426,
      "grad_norm": 0.5904474199109295,
      "learning_rate": 0.00011313708,
      "loss": 0.524,
      "step": 52
    },
    {
      "epoch": 0.5737483085250338,
      "grad_norm": 0.6549550865810885,
      "learning_rate": 0.00011313708,
      "loss": 0.5201,
      "step": 53
    },
    {
      "epoch": 0.584573748308525,
      "grad_norm": 0.7507228814897264,
      "learning_rate": 0.00011313708,
      "loss": 0.5327,
      "step": 54
    },
    {
      "epoch": 0.5953991880920162,
      "grad_norm": 1.0633251061263844,
      "learning_rate": 0.00011313708,
      "loss": 0.5218,
      "step": 55
    },
    {
      "epoch": 0.6062246278755075,
      "grad_norm": 1.5012841748053845,
      "learning_rate": 0.00011313708,
      "loss": 0.528,
      "step": 56
    },
    {
      "epoch": 0.6170500676589986,
      "grad_norm": 0.5665427708656176,
      "learning_rate": 0.00011313708,
      "loss": 0.5179,
      "step": 57
    },
    {
      "epoch": 0.6278755074424899,
      "grad_norm": 1.845305650368642,
      "learning_rate": 0.00011313708,
      "loss": 0.5286,
      "step": 58
    },
    {
      "epoch": 0.638700947225981,
      "grad_norm": 0.6351244607425496,
      "learning_rate": 0.00011313708,
      "loss": 0.5044,
      "step": 59
    },
    {
      "epoch": 0.6495263870094723,
      "grad_norm": 1.6872030057088823,
      "learning_rate": 0.00011313708,
      "loss": 0.523,
      "step": 60
    },
    {
      "epoch": 0.6603518267929634,
      "grad_norm": 0.9318826199274253,
      "learning_rate": 0.00011313708,
      "loss": 0.5262,
      "step": 61
    },
    {
      "epoch": 0.6711772665764547,
      "grad_norm": 1.7524595786217534,
      "learning_rate": 0.00011313708,
      "loss": 0.5226,
      "step": 62
    },
    {
      "epoch": 0.6820027063599459,
      "grad_norm": 1.3906673909977412,
      "learning_rate": 0.00011313708,
      "loss": 0.5325,
      "step": 63
    },
    {
      "epoch": 0.6928281461434371,
      "grad_norm": 1.1214175260271424,
      "learning_rate": 0.00011313708,
      "loss": 0.5178,
      "step": 64
    },
    {
      "epoch": 0.7036535859269283,
      "grad_norm": 1.1678164415246544,
      "learning_rate": 0.00011313708,
      "loss": 0.5103,
      "step": 65
    },
    {
      "epoch": 0.7144790257104194,
      "grad_norm": 0.7411559329842898,
      "learning_rate": 0.00011313708,
      "loss": 0.5156,
      "step": 66
    },
    {
      "epoch": 0.7253044654939107,
      "grad_norm": 1.2988665594902944,
      "learning_rate": 0.00011313708,
      "loss": 0.511,
      "step": 67
    },
    {
      "epoch": 0.7361299052774019,
      "grad_norm": 0.6169922587754691,
      "learning_rate": 0.00011313708,
      "loss": 0.522,
      "step": 68
    },
    {
      "epoch": 0.7469553450608931,
      "grad_norm": 1.093699187339888,
      "learning_rate": 0.00011313708,
      "loss": 0.5097,
      "step": 69
    },
    {
      "epoch": 0.7577807848443843,
      "grad_norm": 0.5030652434419646,
      "learning_rate": 0.00011313708,
      "loss": 0.4919,
      "step": 70
    },
    {
      "epoch": 0.7686062246278755,
      "grad_norm": 0.8091259698349318,
      "learning_rate": 0.00011313708,
      "loss": 0.4933,
      "step": 71
    },
    {
      "epoch": 0.7794316644113667,
      "grad_norm": 0.5752750143844069,
      "learning_rate": 0.00011313708,
      "loss": 0.5033,
      "step": 72
    },
    {
      "epoch": 0.790257104194858,
      "grad_norm": 0.5224354989602931,
      "learning_rate": 0.00011313708,
      "loss": 0.5086,
      "step": 73
    },
    {
      "epoch": 0.8010825439783491,
      "grad_norm": 0.6828095006777672,
      "learning_rate": 0.00011313708,
      "loss": 0.5027,
      "step": 74
    },
    {
      "epoch": 0.8119079837618404,
      "grad_norm": 0.6337120659384431,
      "learning_rate": 0.00011313708,
      "loss": 0.4981,
      "step": 75
    },
    {
      "epoch": 0.8227334235453315,
      "grad_norm": 0.5871444260687323,
      "learning_rate": 0.00011313708,
      "loss": 0.4903,
      "step": 76
    },
    {
      "epoch": 0.8335588633288228,
      "grad_norm": 0.46393708989650767,
      "learning_rate": 0.00011313708,
      "loss": 0.4878,
      "step": 77
    },
    {
      "epoch": 0.8443843031123139,
      "grad_norm": 0.5218485534033501,
      "learning_rate": 0.00011313708,
      "loss": 0.4932,
      "step": 78
    },
    {
      "epoch": 0.8552097428958051,
      "grad_norm": 0.6837863897695945,
      "learning_rate": 0.00011313708,
      "loss": 0.4991,
      "step": 79
    },
    {
      "epoch": 0.8660351826792964,
      "grad_norm": 1.1336244601356606,
      "learning_rate": 0.00011313708,
      "loss": 0.4998,
      "step": 80
    },
    {
      "epoch": 0.8768606224627875,
      "grad_norm": 1.3010735431771652,
      "learning_rate": 0.00011313708,
      "loss": 0.5067,
      "step": 81
    },
    {
      "epoch": 0.8876860622462788,
      "grad_norm": 0.5003035079164821,
      "learning_rate": 0.00011313708,
      "loss": 0.4883,
      "step": 82
    },
    {
      "epoch": 0.8985115020297699,
      "grad_norm": 0.859775600686613,
      "learning_rate": 0.00011313708,
      "loss": 0.4966,
      "step": 83
    },
    {
      "epoch": 0.9093369418132612,
      "grad_norm": 1.0087493068226512,
      "learning_rate": 0.00011313708,
      "loss": 0.4945,
      "step": 84
    },
    {
      "epoch": 0.9201623815967523,
      "grad_norm": 0.9537773614377257,
      "learning_rate": 0.00011313708,
      "loss": 0.4922,
      "step": 85
    },
    {
      "epoch": 0.9309878213802436,
      "grad_norm": 0.7390524153902613,
      "learning_rate": 0.00011313708,
      "loss": 0.4955,
      "step": 86
    },
    {
      "epoch": 0.9418132611637348,
      "grad_norm": 0.6345202177956891,
      "learning_rate": 0.00011313708,
      "loss": 0.4883,
      "step": 87
    },
    {
      "epoch": 0.952638700947226,
      "grad_norm": 0.7420193864107432,
      "learning_rate": 0.00011313708,
      "loss": 0.4749,
      "step": 88
    },
    {
      "epoch": 0.9634641407307172,
      "grad_norm": 0.6081923653172661,
      "learning_rate": 0.00011313708,
      "loss": 0.4878,
      "step": 89
    },
    {
      "epoch": 0.9742895805142084,
      "grad_norm": 0.666338542467456,
      "learning_rate": 0.00011313708,
      "loss": 0.4877,
      "step": 90
    },
    {
      "epoch": 0.9851150202976996,
      "grad_norm": 0.5101695969954052,
      "learning_rate": 0.00011313708,
      "loss": 0.4856,
      "step": 91
    },
    {
      "epoch": 0.9959404600811907,
      "grad_norm": 0.5471304787788676,
      "learning_rate": 0.00011313708,
      "loss": 0.487,
      "step": 92
    },
    {
      "epoch": 1.006765899864682,
      "grad_norm": 0.8290825238269952,
      "learning_rate": 0.00011313708,
      "loss": 0.7554,
      "step": 93
    },
    {
      "epoch": 1.0175913396481733,
      "grad_norm": 0.982482416828812,
      "learning_rate": 0.00011313708,
      "loss": 0.4744,
      "step": 94
    },
    {
      "epoch": 1.0284167794316643,
      "grad_norm": 0.8350075692311496,
      "learning_rate": 0.00011313708,
      "loss": 0.4707,
      "step": 95
    },
    {
      "epoch": 1.0392422192151556,
      "grad_norm": 1.0241030720849982,
      "learning_rate": 0.00011313708,
      "loss": 0.4712,
      "step": 96
    },
    {
      "epoch": 1.0500676589986468,
      "grad_norm": 0.8765653225578105,
      "learning_rate": 0.00011313708,
      "loss": 0.4587,
      "step": 97
    },
    {
      "epoch": 1.060893098782138,
      "grad_norm": 0.7439079711740966,
      "learning_rate": 0.00011313708,
      "loss": 0.4645,
      "step": 98
    },
    {
      "epoch": 1.0717185385656292,
      "grad_norm": 0.8440907885663632,
      "learning_rate": 0.00011313708,
      "loss": 0.4623,
      "step": 99
    },
    {
      "epoch": 1.0825439783491204,
      "grad_norm": 0.6732031936214207,
      "learning_rate": 0.00011313708,
      "loss": 0.4571,
      "step": 100
    },
    {
      "epoch": 1.0933694181326117,
      "grad_norm": 0.5965469878494846,
      "learning_rate": 0.00011313708,
      "loss": 0.4555,
      "step": 101
    },
    {
      "epoch": 1.104194857916103,
      "grad_norm": 0.5257150716254049,
      "learning_rate": 0.00011313708,
      "loss": 0.4542,
      "step": 102
    },
    {
      "epoch": 1.115020297699594,
      "grad_norm": 0.5489308006419329,
      "learning_rate": 0.00011313708,
      "loss": 0.4579,
      "step": 103
    },
    {
      "epoch": 1.1258457374830853,
      "grad_norm": 0.3764598981540829,
      "learning_rate": 0.00011313708,
      "loss": 0.4471,
      "step": 104
    },
    {
      "epoch": 1.1366711772665765,
      "grad_norm": 0.7032598643635346,
      "learning_rate": 0.00011313708,
      "loss": 0.4529,
      "step": 105
    },
    {
      "epoch": 1.1474966170500678,
      "grad_norm": 0.5532083498627568,
      "learning_rate": 0.00011313708,
      "loss": 0.4567,
      "step": 106
    },
    {
      "epoch": 1.1583220568335588,
      "grad_norm": 0.3958025435063403,
      "learning_rate": 0.00011313708,
      "loss": 0.4496,
      "step": 107
    },
    {
      "epoch": 1.16914749661705,
      "grad_norm": 0.6396179687905124,
      "learning_rate": 0.00011313708,
      "loss": 0.445,
      "step": 108
    },
    {
      "epoch": 1.1799729364005414,
      "grad_norm": 0.47835601761794067,
      "learning_rate": 0.00011313708,
      "loss": 0.4509,
      "step": 109
    },
    {
      "epoch": 1.1907983761840324,
      "grad_norm": 0.6099687463967337,
      "learning_rate": 0.00011313708,
      "loss": 0.456,
      "step": 110
    },
    {
      "epoch": 1.2016238159675237,
      "grad_norm": 0.7547404628083604,
      "learning_rate": 0.00011313708,
      "loss": 0.4551,
      "step": 111
    },
    {
      "epoch": 1.212449255751015,
      "grad_norm": 0.8939333075200716,
      "learning_rate": 0.00011313708,
      "loss": 0.4512,
      "step": 112
    },
    {
      "epoch": 1.2232746955345062,
      "grad_norm": 1.1387307397907769,
      "learning_rate": 0.00011313708,
      "loss": 0.4497,
      "step": 113
    },
    {
      "epoch": 1.2341001353179972,
      "grad_norm": 0.8587286838838012,
      "learning_rate": 0.00011313708,
      "loss": 0.4537,
      "step": 114
    },
    {
      "epoch": 1.2449255751014885,
      "grad_norm": 0.5903669647092009,
      "learning_rate": 0.00011313708,
      "loss": 0.458,
      "step": 115
    },
    {
      "epoch": 1.2557510148849798,
      "grad_norm": 0.4071712648959291,
      "learning_rate": 0.00011313708,
      "loss": 0.4483,
      "step": 116
    },
    {
      "epoch": 1.266576454668471,
      "grad_norm": 0.48614666575754834,
      "learning_rate": 0.00011313708,
      "loss": 0.4466,
      "step": 117
    },
    {
      "epoch": 1.277401894451962,
      "grad_norm": 0.441704721810817,
      "learning_rate": 0.00011313708,
      "loss": 0.4469,
      "step": 118
    },
    {
      "epoch": 1.2882273342354533,
      "grad_norm": 0.46292563875783255,
      "learning_rate": 0.00011313708,
      "loss": 0.4512,
      "step": 119
    },
    {
      "epoch": 1.2990527740189446,
      "grad_norm": 0.48480225045492004,
      "learning_rate": 0.00011313708,
      "loss": 0.4447,
      "step": 120
    },
    {
      "epoch": 1.3098782138024356,
      "grad_norm": 0.5075274892323212,
      "learning_rate": 0.00011313708,
      "loss": 0.4524,
      "step": 121
    },
    {
      "epoch": 1.320703653585927,
      "grad_norm": 0.5558276553466879,
      "learning_rate": 0.00011313708,
      "loss": 0.4485,
      "step": 122
    },
    {
      "epoch": 1.3315290933694182,
      "grad_norm": 0.6438827651117811,
      "learning_rate": 0.00011313708,
      "loss": 0.4508,
      "step": 123
    },
    {
      "epoch": 1.3423545331529092,
      "grad_norm": 0.6922826496431984,
      "learning_rate": 0.00011313708,
      "loss": 0.4469,
      "step": 124
    },
    {
      "epoch": 1.3531799729364005,
      "grad_norm": 0.668073491187081,
      "learning_rate": 0.00011313708,
      "loss": 0.4469,
      "step": 125
    },
    {
      "epoch": 1.3640054127198917,
      "grad_norm": 0.6027976409626009,
      "learning_rate": 0.00011313708,
      "loss": 0.4461,
      "step": 126
    },
    {
      "epoch": 1.374830852503383,
      "grad_norm": 0.5563667187131077,
      "learning_rate": 0.00011313708,
      "loss": 0.4385,
      "step": 127
    },
    {
      "epoch": 1.3856562922868743,
      "grad_norm": 0.4850461016138089,
      "learning_rate": 0.00011313708,
      "loss": 0.4396,
      "step": 128
    },
    {
      "epoch": 1.3964817320703653,
      "grad_norm": 0.6549741240199226,
      "learning_rate": 0.00011313708,
      "loss": 0.4399,
      "step": 129
    },
    {
      "epoch": 1.4073071718538566,
      "grad_norm": 0.850032181228161,
      "learning_rate": 0.00011313708,
      "loss": 0.4459,
      "step": 130
    },
    {
      "epoch": 1.4181326116373478,
      "grad_norm": 0.9236462579600792,
      "learning_rate": 0.00011313708,
      "loss": 0.4479,
      "step": 131
    },
    {
      "epoch": 1.4289580514208389,
      "grad_norm": 1.1089061426006435,
      "learning_rate": 0.00011313708,
      "loss": 0.4513,
      "step": 132
    },
    {
      "epoch": 1.4397834912043301,
      "grad_norm": 1.093314412371868,
      "learning_rate": 0.00011313708,
      "loss": 0.4438,
      "step": 133
    },
    {
      "epoch": 1.4506089309878214,
      "grad_norm": 0.8712269811026563,
      "learning_rate": 0.00011313708,
      "loss": 0.4432,
      "step": 134
    },
    {
      "epoch": 1.4614343707713127,
      "grad_norm": 0.6984610983978257,
      "learning_rate": 0.00011313708,
      "loss": 0.4439,
      "step": 135
    },
    {
      "epoch": 1.472259810554804,
      "grad_norm": 0.5128292895463328,
      "learning_rate": 0.00011313708,
      "loss": 0.4418,
      "step": 136
    },
    {
      "epoch": 1.483085250338295,
      "grad_norm": 0.5656470106557929,
      "learning_rate": 0.00011313708,
      "loss": 0.439,
      "step": 137
    },
    {
      "epoch": 1.4939106901217862,
      "grad_norm": 0.5195979816485148,
      "learning_rate": 0.00011313708,
      "loss": 0.4451,
      "step": 138
    },
    {
      "epoch": 1.5047361299052775,
      "grad_norm": 0.48686356154892607,
      "learning_rate": 0.00011313708,
      "loss": 0.4434,
      "step": 139
    },
    {
      "epoch": 1.5155615696887685,
      "grad_norm": 0.5179254396185354,
      "learning_rate": 0.00011313708,
      "loss": 0.4429,
      "step": 140
    },
    {
      "epoch": 1.5263870094722598,
      "grad_norm": 0.4161882150019228,
      "learning_rate": 0.00011313708,
      "loss": 0.4387,
      "step": 141
    },
    {
      "epoch": 1.537212449255751,
      "grad_norm": 0.3851477110568955,
      "learning_rate": 0.00011313708,
      "loss": 0.4399,
      "step": 142
    },
    {
      "epoch": 1.548037889039242,
      "grad_norm": 0.5650681020018092,
      "learning_rate": 0.00011313708,
      "loss": 0.4479,
      "step": 143
    },
    {
      "epoch": 1.5588633288227334,
      "grad_norm": 0.6041365423727687,
      "learning_rate": 0.00011313708,
      "loss": 0.4408,
      "step": 144
    },
    {
      "epoch": 1.5696887686062246,
      "grad_norm": 0.6650541691537162,
      "learning_rate": 0.00011313708,
      "loss": 0.4407,
      "step": 145
    },
    {
      "epoch": 1.5805142083897157,
      "grad_norm": 0.8112703873527826,
      "learning_rate": 0.00011313708,
      "loss": 0.4415,
      "step": 146
    },
    {
      "epoch": 1.5913396481732072,
      "grad_norm": 0.8575782888457318,
      "learning_rate": 0.00011313708,
      "loss": 0.4371,
      "step": 147
    },
    {
      "epoch": 1.6021650879566982,
      "grad_norm": 0.8536780216470099,
      "learning_rate": 0.00011313708,
      "loss": 0.4562,
      "step": 148
    },
    {
      "epoch": 1.6129905277401895,
      "grad_norm": 0.817565627894833,
      "learning_rate": 0.00011313708,
      "loss": 0.4395,
      "step": 149
    },
    {
      "epoch": 1.6238159675236807,
      "grad_norm": 0.6644023012703825,
      "learning_rate": 0.00011313708,
      "loss": 0.4444,
      "step": 150
    },
    {
      "epoch": 1.6346414073071718,
      "grad_norm": 0.4510865278758624,
      "learning_rate": 0.00011313708,
      "loss": 0.4427,
      "step": 151
    },
    {
      "epoch": 1.645466847090663,
      "grad_norm": 0.39518452434132767,
      "learning_rate": 0.00011313708,
      "loss": 0.4363,
      "step": 152
    },
    {
      "epoch": 1.6562922868741543,
      "grad_norm": 0.554101426822033,
      "learning_rate": 0.00011313708,
      "loss": 0.4501,
      "step": 153
    },
    {
      "epoch": 1.6671177266576453,
      "grad_norm": 0.5733701685893817,
      "learning_rate": 0.00011313708,
      "loss": 0.4413,
      "step": 154
    },
    {
      "epoch": 1.6779431664411368,
      "grad_norm": 0.45972928086502884,
      "learning_rate": 0.00011313708,
      "loss": 0.4331,
      "step": 155
    },
    {
      "epoch": 1.6887686062246279,
      "grad_norm": 0.49564640799889237,
      "learning_rate": 0.00011313708,
      "loss": 0.4415,
      "step": 156
    },
    {
      "epoch": 1.699594046008119,
      "grad_norm": 0.6298777784729768,
      "learning_rate": 0.00011313708,
      "loss": 0.4292,
      "step": 157
    },
    {
      "epoch": 1.7104194857916104,
      "grad_norm": 0.4836766818105872,
      "learning_rate": 0.00011313708,
      "loss": 0.4395,
      "step": 158
    },
    {
      "epoch": 1.7212449255751014,
      "grad_norm": 0.3693307925263571,
      "learning_rate": 0.00011313708,
      "loss": 0.4458,
      "step": 159
    },
    {
      "epoch": 1.7320703653585927,
      "grad_norm": 0.6128038324612713,
      "learning_rate": 0.00011313708,
      "loss": 0.4399,
      "step": 160
    },
    {
      "epoch": 1.742895805142084,
      "grad_norm": 0.773769796604131,
      "learning_rate": 0.00011313708,
      "loss": 0.4362,
      "step": 161
    },
    {
      "epoch": 1.753721244925575,
      "grad_norm": 0.8162410617254389,
      "learning_rate": 0.00011313708,
      "loss": 0.4425,
      "step": 162
    },
    {
      "epoch": 1.7645466847090663,
      "grad_norm": 0.9766591838462444,
      "learning_rate": 0.00011313708,
      "loss": 0.4379,
      "step": 163
    },
    {
      "epoch": 1.7753721244925575,
      "grad_norm": 1.437364653250023,
      "learning_rate": 0.00011313708,
      "loss": 0.4411,
      "step": 164
    },
    {
      "epoch": 1.7861975642760486,
      "grad_norm": 0.591274522159979,
      "learning_rate": 0.00011313708,
      "loss": 0.4409,
      "step": 165
    },
    {
      "epoch": 1.79702300405954,
      "grad_norm": 0.7512249664927566,
      "learning_rate": 0.00011313708,
      "loss": 0.4351,
      "step": 166
    },
    {
      "epoch": 1.8078484438430311,
      "grad_norm": 0.9996805711719177,
      "learning_rate": 0.00011313708,
      "loss": 0.4439,
      "step": 167
    },
    {
      "epoch": 1.8186738836265224,
      "grad_norm": 1.0731207064166486,
      "learning_rate": 0.00011313708,
      "loss": 0.4415,
      "step": 168
    },
    {
      "epoch": 1.8294993234100136,
      "grad_norm": 0.9144207296596163,
      "learning_rate": 0.00011313708,
      "loss": 0.4461,
      "step": 169
    },
    {
      "epoch": 1.8403247631935047,
      "grad_norm": 0.7971202683482035,
      "learning_rate": 0.00011313708,
      "loss": 0.4386,
      "step": 170
    },
    {
      "epoch": 1.851150202976996,
      "grad_norm": 0.6114648055756041,
      "learning_rate": 0.00011313708,
      "loss": 0.4361,
      "step": 171
    },
    {
      "epoch": 1.8619756427604872,
      "grad_norm": 0.6056335877049899,
      "learning_rate": 0.00011313708,
      "loss": 0.4347,
      "step": 172
    },
    {
      "epoch": 1.8728010825439783,
      "grad_norm": 0.7381265519491766,
      "learning_rate": 0.00011313708,
      "loss": 0.4301,
      "step": 173
    },
    {
      "epoch": 1.8836265223274695,
      "grad_norm": 0.5657452557034925,
      "learning_rate": 0.00011313708,
      "loss": 0.4436,
      "step": 174
    },
    {
      "epoch": 1.8944519621109608,
      "grad_norm": 0.5295184999946942,
      "learning_rate": 0.00011313708,
      "loss": 0.4356,
      "step": 175
    },
    {
      "epoch": 1.9052774018944518,
      "grad_norm": 0.5298018845836144,
      "learning_rate": 0.00011313708,
      "loss": 0.4301,
      "step": 176
    },
    {
      "epoch": 1.9161028416779433,
      "grad_norm": 0.5685927450375129,
      "learning_rate": 0.00011313708,
      "loss": 0.4319,
      "step": 177
    },
    {
      "epoch": 1.9269282814614344,
      "grad_norm": 0.5723613931787559,
      "learning_rate": 0.00011313708,
      "loss": 0.4406,
      "step": 178
    },
    {
      "epoch": 1.9377537212449256,
      "grad_norm": 0.5248062336240255,
      "learning_rate": 0.00011313708,
      "loss": 0.435,
      "step": 179
    },
    {
      "epoch": 1.9485791610284169,
      "grad_norm": 0.3975537461690098,
      "learning_rate": 0.00011313708,
      "loss": 0.436,
      "step": 180
    },
    {
      "epoch": 1.959404600811908,
      "grad_norm": 0.5085468359229455,
      "learning_rate": 0.00011313708,
      "loss": 0.4357,
      "step": 181
    },
    {
      "epoch": 1.9702300405953992,
      "grad_norm": 0.4970340500397168,
      "learning_rate": 0.00011313708,
      "loss": 0.4312,
      "step": 182
    },
    {
      "epoch": 1.9810554803788905,
      "grad_norm": 0.39536525078419044,
      "learning_rate": 0.00011313708,
      "loss": 0.4391,
      "step": 183
    },
    {
      "epoch": 1.9918809201623815,
      "grad_norm": 0.41002190272925765,
      "learning_rate": 0.00011313708,
      "loss": 0.4394,
      "step": 184
    },
    {
      "epoch": 2.002706359945873,
      "grad_norm": 0.7035286306625309,
      "learning_rate": 0.00011313708,
      "loss": 0.6873,
      "step": 185
    },
    {
      "epoch": 2.013531799729364,
      "grad_norm": 1.2601618878091794,
      "learning_rate": 0.00011313708,
      "loss": 0.4128,
      "step": 186
    },
    {
      "epoch": 2.024357239512855,
      "grad_norm": 1.1934817349245597,
      "learning_rate": 0.00011313708,
      "loss": 0.407,
      "step": 187
    },
    {
      "epoch": 2.0351826792963466,
      "grad_norm": 0.9350836669237442,
      "learning_rate": 0.00011313708,
      "loss": 0.4024,
      "step": 188
    },
    {
      "epoch": 2.0460081190798376,
      "grad_norm": 1.0540794842342625,
      "learning_rate": 0.00011313708,
      "loss": 0.397,
      "step": 189
    },
    {
      "epoch": 2.0568335588633286,
      "grad_norm": 1.0796190643737174,
      "learning_rate": 0.00011313708,
      "loss": 0.4009,
      "step": 190
    },
    {
      "epoch": 2.06765899864682,
      "grad_norm": 1.0855174576864264,
      "learning_rate": 0.00011313708,
      "loss": 0.4046,
      "step": 191
    },
    {
      "epoch": 2.078484438430311,
      "grad_norm": 0.6218910349228782,
      "learning_rate": 0.00011313708,
      "loss": 0.4051,
      "step": 192
    },
    {
      "epoch": 2.089309878213802,
      "grad_norm": 0.6442533268394706,
      "learning_rate": 0.00011313708,
      "loss": 0.3948,
      "step": 193
    },
    {
      "epoch": 2.1001353179972937,
      "grad_norm": 0.6533095289247332,
      "learning_rate": 0.00011313708,
      "loss": 0.3876,
      "step": 194
    },
    {
      "epoch": 2.1109607577807847,
      "grad_norm": 0.5200551609572114,
      "learning_rate": 0.00011313708,
      "loss": 0.3957,
      "step": 195
    },
    {
      "epoch": 2.121786197564276,
      "grad_norm": 0.5916239741309629,
      "learning_rate": 0.00011313708,
      "loss": 0.3938,
      "step": 196
    },
    {
      "epoch": 2.1326116373477673,
      "grad_norm": 0.49363537236156163,
      "learning_rate": 0.00011313708,
      "loss": 0.3895,
      "step": 197
    },
    {
      "epoch": 2.1434370771312583,
      "grad_norm": 0.40884004242019406,
      "learning_rate": 0.00011313708,
      "loss": 0.3862,
      "step": 198
    },
    {
      "epoch": 2.15426251691475,
      "grad_norm": 0.5565916042513704,
      "learning_rate": 0.00011313708,
      "loss": 0.3939,
      "step": 199
    },
    {
      "epoch": 2.165087956698241,
      "grad_norm": 0.4975891082315616,
      "learning_rate": 0.00011313708,
      "loss": 0.395,
      "step": 200
    },
    {
      "epoch": 2.175913396481732,
      "grad_norm": 0.38139997266197667,
      "learning_rate": 0.00011313708,
      "loss": 0.3899,
      "step": 201
    },
    {
      "epoch": 2.1867388362652234,
      "grad_norm": 0.4059589535202566,
      "learning_rate": 0.00011313708,
      "loss": 0.3871,
      "step": 202
    },
    {
      "epoch": 2.1975642760487144,
      "grad_norm": 0.33976403070902733,
      "learning_rate": 0.00011313708,
      "loss": 0.3933,
      "step": 203
    },
    {
      "epoch": 2.208389715832206,
      "grad_norm": 0.3474100028276814,
      "learning_rate": 0.00011313708,
      "loss": 0.3915,
      "step": 204
    },
    {
      "epoch": 2.219215155615697,
      "grad_norm": 0.401741921901795,
      "learning_rate": 0.00011313708,
      "loss": 0.3889,
      "step": 205
    },
    {
      "epoch": 2.230040595399188,
      "grad_norm": 0.4015827970844881,
      "learning_rate": 0.00011313708,
      "loss": 0.3897,
      "step": 206
    },
    {
      "epoch": 2.2408660351826795,
      "grad_norm": 0.3571287792331978,
      "learning_rate": 0.00011313708,
      "loss": 0.3933,
      "step": 207
    },
    {
      "epoch": 2.2516914749661705,
      "grad_norm": 0.3424799921141956,
      "learning_rate": 0.00011313708,
      "loss": 0.3856,
      "step": 208
    },
    {
      "epoch": 2.2625169147496615,
      "grad_norm": 0.34837152451561204,
      "learning_rate": 0.00011313708,
      "loss": 0.3896,
      "step": 209
    },
    {
      "epoch": 2.273342354533153,
      "grad_norm": 0.3886531438089093,
      "learning_rate": 0.00011313708,
      "loss": 0.3855,
      "step": 210
    },
    {
      "epoch": 2.284167794316644,
      "grad_norm": 0.4718425953135714,
      "learning_rate": 0.00011313708,
      "loss": 0.3873,
      "step": 211
    },
    {
      "epoch": 2.2949932341001356,
      "grad_norm": 0.534737459687887,
      "learning_rate": 0.00011313708,
      "loss": 0.3881,
      "step": 212
    },
    {
      "epoch": 2.3058186738836266,
      "grad_norm": 0.6820549715415719,
      "learning_rate": 0.00011313708,
      "loss": 0.396,
      "step": 213
    },
    {
      "epoch": 2.3166441136671176,
      "grad_norm": 0.8634654583485604,
      "learning_rate": 0.00011313708,
      "loss": 0.3922,
      "step": 214
    },
    {
      "epoch": 2.3274695534506087,
      "grad_norm": 1.0330217898090133,
      "learning_rate": 0.00011313708,
      "loss": 0.3959,
      "step": 215
    },
    {
      "epoch": 2.3382949932341,
      "grad_norm": 1.1688285921547568,
      "learning_rate": 0.00011313708,
      "loss": 0.4048,
      "step": 216
    },
    {
      "epoch": 2.349120433017591,
      "grad_norm": 0.690398923170262,
      "learning_rate": 0.00011313708,
      "loss": 0.3914,
      "step": 217
    },
    {
      "epoch": 2.3599458728010827,
      "grad_norm": 0.43396309212372614,
      "learning_rate": 0.00011313708,
      "loss": 0.3982,
      "step": 218
    },
    {
      "epoch": 2.3707713125845737,
      "grad_norm": 0.6658622132891707,
      "learning_rate": 0.00011313708,
      "loss": 0.3981,
      "step": 219
    },
    {
      "epoch": 2.381596752368065,
      "grad_norm": 0.7512871618530845,
      "learning_rate": 0.00011313708,
      "loss": 0.3873,
      "step": 220
    },
    {
      "epoch": 2.3924221921515563,
      "grad_norm": 0.5248973752549382,
      "learning_rate": 0.00011313708,
      "loss": 0.3914,
      "step": 221
    },
    {
      "epoch": 2.4032476319350473,
      "grad_norm": 0.3684987295942111,
      "learning_rate": 0.00011313708,
      "loss": 0.3981,
      "step": 222
    },
    {
      "epoch": 2.414073071718539,
      "grad_norm": 0.5386324229655013,
      "learning_rate": 0.00011313708,
      "loss": 0.3982,
      "step": 223
    },
    {
      "epoch": 2.42489851150203,
      "grad_norm": 0.5989350689241424,
      "learning_rate": 0.00011313708,
      "loss": 0.3967,
      "step": 224
    },
    {
      "epoch": 2.435723951285521,
      "grad_norm": 0.49358596591679665,
      "learning_rate": 0.00011313708,
      "loss": 0.3961,
      "step": 225
    },
    {
      "epoch": 2.4465493910690124,
      "grad_norm": 0.5297285165667454,
      "learning_rate": 0.00011313708,
      "loss": 0.3997,
      "step": 226
    },
    {
      "epoch": 2.4573748308525034,
      "grad_norm": 0.6287539604833966,
      "learning_rate": 0.00011313708,
      "loss": 0.3935,
      "step": 227
    },
    {
      "epoch": 2.4682002706359945,
      "grad_norm": 0.6767528703613279,
      "learning_rate": 0.00011313708,
      "loss": 0.3935,
      "step": 228
    },
    {
      "epoch": 2.479025710419486,
      "grad_norm": 0.5935593685013462,
      "learning_rate": 0.00011313708,
      "loss": 0.3911,
      "step": 229
    },
    {
      "epoch": 2.489851150202977,
      "grad_norm": 0.4597540548275792,
      "learning_rate": 0.00011313708,
      "loss": 0.3917,
      "step": 230
    },
    {
      "epoch": 2.500676589986468,
      "grad_norm": 0.5373235791755535,
      "learning_rate": 0.00011313708,
      "loss": 0.4005,
      "step": 231
    },
    {
      "epoch": 2.5115020297699595,
      "grad_norm": 0.6832033152824111,
      "learning_rate": 0.00011313708,
      "loss": 0.3974,
      "step": 232
    },
    {
      "epoch": 2.5223274695534506,
      "grad_norm": 0.6146990010718386,
      "learning_rate": 0.00011313708,
      "loss": 0.3925,
      "step": 233
    },
    {
      "epoch": 2.533152909336942,
      "grad_norm": 0.4400139790155015,
      "learning_rate": 0.00011313708,
      "loss": 0.3942,
      "step": 234
    },
    {
      "epoch": 2.543978349120433,
      "grad_norm": 0.43037592136490715,
      "learning_rate": 0.00011313708,
      "loss": 0.3883,
      "step": 235
    },
    {
      "epoch": 2.554803788903924,
      "grad_norm": 0.4276306579853105,
      "learning_rate": 0.00011313708,
      "loss": 0.3869,
      "step": 236
    },
    {
      "epoch": 2.565629228687415,
      "grad_norm": 0.5171199962772047,
      "learning_rate": 0.00011313708,
      "loss": 0.3944,
      "step": 237
    },
    {
      "epoch": 2.5764546684709067,
      "grad_norm": 0.444481675091458,
      "learning_rate": 0.00011313708,
      "loss": 0.3929,
      "step": 238
    },
    {
      "epoch": 2.5872801082543977,
      "grad_norm": 0.3073427063229655,
      "learning_rate": 0.00011313708,
      "loss": 0.3891,
      "step": 239
    },
    {
      "epoch": 2.598105548037889,
      "grad_norm": 0.3440960561111227,
      "learning_rate": 0.00011313708,
      "loss": 0.3964,
      "step": 240
    },
    {
      "epoch": 2.60893098782138,
      "grad_norm": 0.311289137160871,
      "learning_rate": 0.00011313708,
      "loss": 0.3981,
      "step": 241
    },
    {
      "epoch": 2.6197564276048713,
      "grad_norm": 0.3282812756717315,
      "learning_rate": 0.00011313708,
      "loss": 0.3976,
      "step": 242
    },
    {
      "epoch": 2.6305818673883627,
      "grad_norm": 0.3215910247334391,
      "learning_rate": 0.00011313708,
      "loss": 0.3886,
      "step": 243
    },
    {
      "epoch": 2.641407307171854,
      "grad_norm": 0.30972603515312513,
      "learning_rate": 0.00011313708,
      "loss": 0.3873,
      "step": 244
    },
    {
      "epoch": 2.6522327469553453,
      "grad_norm": 0.3504247025214314,
      "learning_rate": 0.00011313708,
      "loss": 0.3876,
      "step": 245
    },
    {
      "epoch": 2.6630581867388363,
      "grad_norm": 0.344570447514371,
      "learning_rate": 0.00011313708,
      "loss": 0.3894,
      "step": 246
    },
    {
      "epoch": 2.6738836265223274,
      "grad_norm": 0.3625722474313937,
      "learning_rate": 0.00011313708,
      "loss": 0.3944,
      "step": 247
    },
    {
      "epoch": 2.6847090663058184,
      "grad_norm": 0.40496419053811256,
      "learning_rate": 0.00011313708,
      "loss": 0.3895,
      "step": 248
    },
    {
      "epoch": 2.69553450608931,
      "grad_norm": 0.48340857634806206,
      "learning_rate": 0.00011313708,
      "loss": 0.3865,
      "step": 249
    },
    {
      "epoch": 2.706359945872801,
      "grad_norm": 0.5727538920865917,
      "learning_rate": 0.00011313708,
      "loss": 0.3973,
      "step": 250
    },
    {
      "epoch": 2.7171853856562924,
      "grad_norm": 0.6170420055329149,
      "learning_rate": 0.00011313708,
      "loss": 0.3939,
      "step": 251
    },
    {
      "epoch": 2.7280108254397835,
      "grad_norm": 0.6634364834066814,
      "learning_rate": 0.00011313708,
      "loss": 0.3978,
      "step": 252
    },
    {
      "epoch": 2.7388362652232745,
      "grad_norm": 0.8114230218434052,
      "learning_rate": 0.00011313708,
      "loss": 0.3979,
      "step": 253
    },
    {
      "epoch": 2.749661705006766,
      "grad_norm": 0.9661656561914463,
      "learning_rate": 0.00011313708,
      "loss": 0.3935,
      "step": 254
    },
    {
      "epoch": 2.760487144790257,
      "grad_norm": 0.9537551796961219,
      "learning_rate": 0.00011313708,
      "loss": 0.3921,
      "step": 255
    },
    {
      "epoch": 2.7713125845737485,
      "grad_norm": 0.7118073774232508,
      "learning_rate": 0.00011313708,
      "loss": 0.3904,
      "step": 256
    },
    {
      "epoch": 2.7821380243572396,
      "grad_norm": 0.530702879529185,
      "learning_rate": 0.00011313708,
      "loss": 0.4021,
      "step": 257
    },
    {
      "epoch": 2.7929634641407306,
      "grad_norm": 0.7888597039445533,
      "learning_rate": 0.00011313708,
      "loss": 0.3945,
      "step": 258
    },
    {
      "epoch": 2.803788903924222,
      "grad_norm": 1.0708910197336536,
      "learning_rate": 0.00011313708,
      "loss": 0.3948,
      "step": 259
    },
    {
      "epoch": 2.814614343707713,
      "grad_norm": 0.7165081300349893,
      "learning_rate": 0.00011313708,
      "loss": 0.3987,
      "step": 260
    },
    {
      "epoch": 2.825439783491204,
      "grad_norm": 0.36537539402867947,
      "learning_rate": 0.00011313708,
      "loss": 0.387,
      "step": 261
    },
    {
      "epoch": 2.8362652232746957,
      "grad_norm": 0.3199426248854634,
      "learning_rate": 0.00011313708,
      "loss": 0.3914,
      "step": 262
    },
    {
      "epoch": 2.8470906630581867,
      "grad_norm": 0.3764840184700109,
      "learning_rate": 0.00011313708,
      "loss": 0.3949,
      "step": 263
    },
    {
      "epoch": 2.8579161028416777,
      "grad_norm": 0.41997789270218483,
      "learning_rate": 0.00011313708,
      "loss": 0.3908,
      "step": 264
    },
    {
      "epoch": 2.8687415426251692,
      "grad_norm": 0.454015122462399,
      "learning_rate": 0.00011313708,
      "loss": 0.395,
      "step": 265
    },
    {
      "epoch": 2.8795669824086603,
      "grad_norm": 0.3679834015715816,
      "learning_rate": 0.00011313708,
      "loss": 0.3924,
      "step": 266
    },
    {
      "epoch": 2.8903924221921518,
      "grad_norm": 0.2754839359173836,
      "learning_rate": 0.00011313708,
      "loss": 0.389,
      "step": 267
    },
    {
      "epoch": 2.901217861975643,
      "grad_norm": 0.48201781080594774,
      "learning_rate": 0.00011313708,
      "loss": 0.3908,
      "step": 268
    },
    {
      "epoch": 2.912043301759134,
      "grad_norm": 0.534246124962904,
      "learning_rate": 0.00011313708,
      "loss": 0.3926,
      "step": 269
    },
    {
      "epoch": 2.9228687415426253,
      "grad_norm": 0.49494875659935805,
      "learning_rate": 0.00011313708,
      "loss": 0.3937,
      "step": 270
    },
    {
      "epoch": 2.9336941813261164,
      "grad_norm": 0.3827675909260427,
      "learning_rate": 0.00011313708,
      "loss": 0.3907,
      "step": 271
    },
    {
      "epoch": 2.944519621109608,
      "grad_norm": 0.43245093213108604,
      "learning_rate": 0.00011313708,
      "loss": 0.3966,
      "step": 272
    },
    {
      "epoch": 2.955345060893099,
      "grad_norm": 0.4606256428062521,
      "learning_rate": 0.00011313708,
      "loss": 0.3942,
      "step": 273
    },
    {
      "epoch": 2.96617050067659,
      "grad_norm": 0.4573982738416541,
      "learning_rate": 0.00011313708,
      "loss": 0.3922,
      "step": 274
    },
    {
      "epoch": 2.976995940460081,
      "grad_norm": 0.539338494179114,
      "learning_rate": 0.00011313708,
      "loss": 0.401,
      "step": 275
    },
    {
      "epoch": 2.9878213802435725,
      "grad_norm": 0.7676166025897813,
      "learning_rate": 0.00011313708,
      "loss": 0.3904,
      "step": 276
    },
    {
      "epoch": 2.9878213802435725,
      "step": 276,
      "total_flos": 6.629121904995205e+18,
      "train_loss": 0.6404118469875791,
      "train_runtime": 27418.4627,
      "train_samples_per_second": 5.174,
      "train_steps_per_second": 0.01
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 276,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 6.629121904995205e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}