{
  "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": 5.807862605146424,
      "learning_rate": 8e-05,
      "loss": 0.8567,
      "step": 1
    },
    {
      "epoch": 0.02165087956698241,
      "grad_norm": 58.71727183985869,
      "learning_rate": 8e-05,
      "loss": 2.1738,
      "step": 2
    },
    {
      "epoch": 0.03247631935047361,
      "grad_norm": 23.029977458084364,
      "learning_rate": 8e-05,
      "loss": 1.5416,
      "step": 3
    },
    {
      "epoch": 0.04330175913396482,
      "grad_norm": 91.8466319126991,
      "learning_rate": 8e-05,
      "loss": 1.7788,
      "step": 4
    },
    {
      "epoch": 0.05412719891745602,
      "grad_norm": 40.276807426577086,
      "learning_rate": 8e-05,
      "loss": 1.4445,
      "step": 5
    },
    {
      "epoch": 0.06495263870094722,
      "grad_norm": 6.1141993541568445,
      "learning_rate": 8e-05,
      "loss": 1.0873,
      "step": 6
    },
    {
      "epoch": 0.07577807848443843,
      "grad_norm": 17.223396794470588,
      "learning_rate": 8e-05,
      "loss": 1.1336,
      "step": 7
    },
    {
      "epoch": 0.08660351826792964,
      "grad_norm": 6.729456865377028,
      "learning_rate": 8e-05,
      "loss": 0.9486,
      "step": 8
    },
    {
      "epoch": 0.09742895805142084,
      "grad_norm": 3.6709641691137196,
      "learning_rate": 8e-05,
      "loss": 0.8582,
      "step": 9
    },
    {
      "epoch": 0.10825439783491204,
      "grad_norm": 9.678727014259207,
      "learning_rate": 8e-05,
      "loss": 0.8317,
      "step": 10
    },
    {
      "epoch": 0.11907983761840325,
      "grad_norm": 312.89235993043997,
      "learning_rate": 8e-05,
      "loss": 1.8099,
      "step": 11
    },
    {
      "epoch": 0.12990527740189445,
      "grad_norm": 93.53676257895965,
      "learning_rate": 8e-05,
      "loss": 1.0518,
      "step": 12
    },
    {
      "epoch": 0.14073071718538566,
      "grad_norm": 5.311746651920042,
      "learning_rate": 8e-05,
      "loss": 0.9205,
      "step": 13
    },
    {
      "epoch": 0.15155615696887687,
      "grad_norm": 2.343109143712556,
      "learning_rate": 8e-05,
      "loss": 0.7999,
      "step": 14
    },
    {
      "epoch": 0.16238159675236807,
      "grad_norm": 1.9769370221119875,
      "learning_rate": 8e-05,
      "loss": 0.7662,
      "step": 15
    },
    {
      "epoch": 0.17320703653585928,
      "grad_norm": 1.753435149017759,
      "learning_rate": 8e-05,
      "loss": 0.7253,
      "step": 16
    },
    {
      "epoch": 0.18403247631935046,
      "grad_norm": 1.17138216540761,
      "learning_rate": 8e-05,
      "loss": 0.7021,
      "step": 17
    },
    {
      "epoch": 0.19485791610284167,
      "grad_norm": 2.0357928367310967,
      "learning_rate": 8e-05,
      "loss": 0.6775,
      "step": 18
    },
    {
      "epoch": 0.20568335588633288,
      "grad_norm": 1.4012193348193651,
      "learning_rate": 8e-05,
      "loss": 0.6562,
      "step": 19
    },
    {
      "epoch": 0.2165087956698241,
      "grad_norm": 1.1143256959438492,
      "learning_rate": 8e-05,
      "loss": 0.6493,
      "step": 20
    },
    {
      "epoch": 0.2273342354533153,
      "grad_norm": 1.7568615381395538,
      "learning_rate": 8e-05,
      "loss": 0.6413,
      "step": 21
    },
    {
      "epoch": 0.2381596752368065,
      "grad_norm": 1.2755189015947674,
      "learning_rate": 8e-05,
      "loss": 0.6327,
      "step": 22
    },
    {
      "epoch": 0.2489851150202977,
      "grad_norm": 1.5788360468760065,
      "learning_rate": 8e-05,
      "loss": 0.6203,
      "step": 23
    },
    {
      "epoch": 0.2598105548037889,
      "grad_norm": 1.4935275144854725,
      "learning_rate": 8e-05,
      "loss": 0.6164,
      "step": 24
    },
    {
      "epoch": 0.2706359945872801,
      "grad_norm": 1.0699682687787953,
      "learning_rate": 8e-05,
      "loss": 0.6026,
      "step": 25
    },
    {
      "epoch": 0.2814614343707713,
      "grad_norm": 1.3768346103000058,
      "learning_rate": 8e-05,
      "loss": 0.5784,
      "step": 26
    },
    {
      "epoch": 0.2922868741542625,
      "grad_norm": 0.7992412486936178,
      "learning_rate": 8e-05,
      "loss": 0.5776,
      "step": 27
    },
    {
      "epoch": 0.30311231393775373,
      "grad_norm": 1.086822089991311,
      "learning_rate": 8e-05,
      "loss": 0.5768,
      "step": 28
    },
    {
      "epoch": 0.31393775372124494,
      "grad_norm": 1.1871491270787098,
      "learning_rate": 8e-05,
      "loss": 0.5752,
      "step": 29
    },
    {
      "epoch": 0.32476319350473615,
      "grad_norm": 1.1424432962764526,
      "learning_rate": 8e-05,
      "loss": 0.5631,
      "step": 30
    },
    {
      "epoch": 0.33558863328822736,
      "grad_norm": 1.1716919179777008,
      "learning_rate": 8e-05,
      "loss": 0.5633,
      "step": 31
    },
    {
      "epoch": 0.34641407307171856,
      "grad_norm": 0.7992428918624372,
      "learning_rate": 8e-05,
      "loss": 0.5564,
      "step": 32
    },
    {
      "epoch": 0.3572395128552097,
      "grad_norm": 0.5804641247487,
      "learning_rate": 8e-05,
      "loss": 0.5549,
      "step": 33
    },
    {
      "epoch": 0.3680649526387009,
      "grad_norm": 0.7936512257261882,
      "learning_rate": 8e-05,
      "loss": 0.5596,
      "step": 34
    },
    {
      "epoch": 0.37889039242219213,
      "grad_norm": 1.4160947295381634,
      "learning_rate": 8e-05,
      "loss": 0.5519,
      "step": 35
    },
    {
      "epoch": 0.38971583220568334,
      "grad_norm": 0.8718469201491832,
      "learning_rate": 8e-05,
      "loss": 0.5339,
      "step": 36
    },
    {
      "epoch": 0.40054127198917455,
      "grad_norm": 0.6688916986349384,
      "learning_rate": 8e-05,
      "loss": 0.539,
      "step": 37
    },
    {
      "epoch": 0.41136671177266576,
      "grad_norm": 0.8292847912664534,
      "learning_rate": 8e-05,
      "loss": 0.5298,
      "step": 38
    },
    {
      "epoch": 0.42219215155615697,
      "grad_norm": 1.0056607552958485,
      "learning_rate": 8e-05,
      "loss": 0.5365,
      "step": 39
    },
    {
      "epoch": 0.4330175913396482,
      "grad_norm": 0.952712338906794,
      "learning_rate": 8e-05,
      "loss": 0.5266,
      "step": 40
    },
    {
      "epoch": 0.4438430311231394,
      "grad_norm": 0.5578883281554611,
      "learning_rate": 8e-05,
      "loss": 0.521,
      "step": 41
    },
    {
      "epoch": 0.4546684709066306,
      "grad_norm": 0.8538947393302606,
      "learning_rate": 8e-05,
      "loss": 0.5164,
      "step": 42
    },
    {
      "epoch": 0.4654939106901218,
      "grad_norm": 0.8838739215969993,
      "learning_rate": 8e-05,
      "loss": 0.5146,
      "step": 43
    },
    {
      "epoch": 0.476319350473613,
      "grad_norm": 0.7758976256435411,
      "learning_rate": 8e-05,
      "loss": 0.5125,
      "step": 44
    },
    {
      "epoch": 0.4871447902571042,
      "grad_norm": 0.7400286284902076,
      "learning_rate": 8e-05,
      "loss": 0.5159,
      "step": 45
    },
    {
      "epoch": 0.4979702300405954,
      "grad_norm": 0.8014230080100426,
      "learning_rate": 8e-05,
      "loss": 0.5107,
      "step": 46
    },
    {
      "epoch": 0.5087956698240866,
      "grad_norm": 0.9594163937814748,
      "learning_rate": 8e-05,
      "loss": 0.5116,
      "step": 47
    },
    {
      "epoch": 0.5196211096075778,
      "grad_norm": 1.3620143009090444,
      "learning_rate": 8e-05,
      "loss": 0.5121,
      "step": 48
    },
    {
      "epoch": 0.530446549391069,
      "grad_norm": 1.0382530499792721,
      "learning_rate": 8e-05,
      "loss": 0.5056,
      "step": 49
    },
    {
      "epoch": 0.5412719891745602,
      "grad_norm": 0.7571998880154939,
      "learning_rate": 8e-05,
      "loss": 0.5035,
      "step": 50
    },
    {
      "epoch": 0.5520974289580515,
      "grad_norm": 0.9280440298365872,
      "learning_rate": 8e-05,
      "loss": 0.5004,
      "step": 51
    },
    {
      "epoch": 0.5629228687415426,
      "grad_norm": 1.1551841696461644,
      "learning_rate": 8e-05,
      "loss": 0.4954,
      "step": 52
    },
    {
      "epoch": 0.5737483085250338,
      "grad_norm": 0.7933104044756524,
      "learning_rate": 8e-05,
      "loss": 0.4931,
      "step": 53
    },
    {
      "epoch": 0.584573748308525,
      "grad_norm": 0.8799462124511651,
      "learning_rate": 8e-05,
      "loss": 0.5058,
      "step": 54
    },
    {
      "epoch": 0.5953991880920162,
      "grad_norm": 1.0072366599252984,
      "learning_rate": 8e-05,
      "loss": 0.4945,
      "step": 55
    },
    {
      "epoch": 0.6062246278755075,
      "grad_norm": 0.9548342512983768,
      "learning_rate": 8e-05,
      "loss": 0.4981,
      "step": 56
    },
    {
      "epoch": 0.6170500676589986,
      "grad_norm": 1.097011041053348,
      "learning_rate": 8e-05,
      "loss": 0.4985,
      "step": 57
    },
    {
      "epoch": 0.6278755074424899,
      "grad_norm": 1.059799220652712,
      "learning_rate": 8e-05,
      "loss": 0.4961,
      "step": 58
    },
    {
      "epoch": 0.638700947225981,
      "grad_norm": 1.0862641558850534,
      "learning_rate": 8e-05,
      "loss": 0.4846,
      "step": 59
    },
    {
      "epoch": 0.6495263870094723,
      "grad_norm": 0.8427037211529642,
      "learning_rate": 8e-05,
      "loss": 0.4898,
      "step": 60
    },
    {
      "epoch": 0.6603518267929634,
      "grad_norm": 0.7858899443205865,
      "learning_rate": 8e-05,
      "loss": 0.5023,
      "step": 61
    },
    {
      "epoch": 0.6711772665764547,
      "grad_norm": 0.6976734783064187,
      "learning_rate": 8e-05,
      "loss": 0.4907,
      "step": 62
    },
    {
      "epoch": 0.6820027063599459,
      "grad_norm": 0.8441669686417473,
      "learning_rate": 8e-05,
      "loss": 0.4978,
      "step": 63
    },
    {
      "epoch": 0.6928281461434371,
      "grad_norm": 1.1798099143520169,
      "learning_rate": 8e-05,
      "loss": 0.4945,
      "step": 64
    },
    {
      "epoch": 0.7036535859269283,
      "grad_norm": 0.8169763304082979,
      "learning_rate": 8e-05,
      "loss": 0.4843,
      "step": 65
    },
    {
      "epoch": 0.7144790257104194,
      "grad_norm": 0.7882733163110064,
      "learning_rate": 8e-05,
      "loss": 0.4927,
      "step": 66
    },
    {
      "epoch": 0.7253044654939107,
      "grad_norm": 0.6841229644046459,
      "learning_rate": 8e-05,
      "loss": 0.4897,
      "step": 67
    },
    {
      "epoch": 0.7361299052774019,
      "grad_norm": 0.7702928394092445,
      "learning_rate": 8e-05,
      "loss": 0.5005,
      "step": 68
    },
    {
      "epoch": 0.7469553450608931,
      "grad_norm": 0.962673096423242,
      "learning_rate": 8e-05,
      "loss": 0.4918,
      "step": 69
    },
    {
      "epoch": 0.7577807848443843,
      "grad_norm": 1.064460746079788,
      "learning_rate": 8e-05,
      "loss": 0.4733,
      "step": 70
    },
    {
      "epoch": 0.7686062246278755,
      "grad_norm": 0.7215446372637571,
      "learning_rate": 8e-05,
      "loss": 0.4762,
      "step": 71
    },
    {
      "epoch": 0.7794316644113667,
      "grad_norm": 0.7688037109714595,
      "learning_rate": 8e-05,
      "loss": 0.4878,
      "step": 72
    },
    {
      "epoch": 0.790257104194858,
      "grad_norm": 0.7582925680010606,
      "learning_rate": 8e-05,
      "loss": 0.4928,
      "step": 73
    },
    {
      "epoch": 0.8010825439783491,
      "grad_norm": 0.892747059875913,
      "learning_rate": 8e-05,
      "loss": 0.4879,
      "step": 74
    },
    {
      "epoch": 0.8119079837618404,
      "grad_norm": 1.2127196362313732,
      "learning_rate": 8e-05,
      "loss": 0.4861,
      "step": 75
    },
    {
      "epoch": 0.8227334235453315,
      "grad_norm": 0.8710577761022359,
      "learning_rate": 8e-05,
      "loss": 0.4765,
      "step": 76
    },
    {
      "epoch": 0.8335588633288228,
      "grad_norm": 1.0307465951179782,
      "learning_rate": 8e-05,
      "loss": 0.4751,
      "step": 77
    },
    {
      "epoch": 0.8443843031123139,
      "grad_norm": 0.9424791198068211,
      "learning_rate": 8e-05,
      "loss": 0.4796,
      "step": 78
    },
    {
      "epoch": 0.8552097428958051,
      "grad_norm": 0.7977484412469278,
      "learning_rate": 8e-05,
      "loss": 0.4834,
      "step": 79
    },
    {
      "epoch": 0.8660351826792964,
      "grad_norm": 0.97731826859708,
      "learning_rate": 8e-05,
      "loss": 0.4786,
      "step": 80
    },
    {
      "epoch": 0.8768606224627875,
      "grad_norm": 1.519981578503623,
      "learning_rate": 8e-05,
      "loss": 0.491,
      "step": 81
    },
    {
      "epoch": 0.8876860622462788,
      "grad_norm": 0.8080739054298852,
      "learning_rate": 8e-05,
      "loss": 0.4736,
      "step": 82
    },
    {
      "epoch": 0.8985115020297699,
      "grad_norm": 1.263196598809782,
      "learning_rate": 8e-05,
      "loss": 0.4818,
      "step": 83
    },
    {
      "epoch": 0.9093369418132612,
      "grad_norm": 0.985504424877494,
      "learning_rate": 8e-05,
      "loss": 0.48,
      "step": 84
    },
    {
      "epoch": 0.9201623815967523,
      "grad_norm": 1.8339440946103176,
      "learning_rate": 8e-05,
      "loss": 0.4786,
      "step": 85
    },
    {
      "epoch": 0.9309878213802436,
      "grad_norm": 0.8647158392245718,
      "learning_rate": 8e-05,
      "loss": 0.4835,
      "step": 86
    },
    {
      "epoch": 0.9418132611637348,
      "grad_norm": 2.257477967656125,
      "learning_rate": 8e-05,
      "loss": 0.4864,
      "step": 87
    },
    {
      "epoch": 0.952638700947226,
      "grad_norm": 1.5759666292620995,
      "learning_rate": 8e-05,
      "loss": 0.4754,
      "step": 88
    },
    {
      "epoch": 0.9634641407307172,
      "grad_norm": 2.0639384607130866,
      "learning_rate": 8e-05,
      "loss": 0.4865,
      "step": 89
    },
    {
      "epoch": 0.9742895805142084,
      "grad_norm": 1.5385020306673918,
      "learning_rate": 8e-05,
      "loss": 0.4879,
      "step": 90
    },
    {
      "epoch": 0.9851150202976996,
      "grad_norm": 1.883780425981483,
      "learning_rate": 8e-05,
      "loss": 0.4864,
      "step": 91
    },
    {
      "epoch": 0.9959404600811907,
      "grad_norm": 1.4424158999631977,
      "learning_rate": 8e-05,
      "loss": 0.4882,
      "step": 92
    },
    {
      "epoch": 1.006765899864682,
      "grad_norm": 2.883282279975078,
      "learning_rate": 8e-05,
      "loss": 0.7533,
      "step": 93
    },
    {
      "epoch": 1.0175913396481733,
      "grad_norm": 1.4722734507827835,
      "learning_rate": 8e-05,
      "loss": 0.4609,
      "step": 94
    },
    {
      "epoch": 1.0284167794316643,
      "grad_norm": 1.3103569979043554,
      "learning_rate": 8e-05,
      "loss": 0.4569,
      "step": 95
    },
    {
      "epoch": 1.0392422192151556,
      "grad_norm": 0.9486552650577804,
      "learning_rate": 8e-05,
      "loss": 0.4528,
      "step": 96
    },
    {
      "epoch": 1.0500676589986468,
      "grad_norm": 1.2608048936778298,
      "learning_rate": 8e-05,
      "loss": 0.4457,
      "step": 97
    },
    {
      "epoch": 1.060893098782138,
      "grad_norm": 0.6908040702449758,
      "learning_rate": 8e-05,
      "loss": 0.4518,
      "step": 98
    },
    {
      "epoch": 1.0717185385656292,
      "grad_norm": 1.1027320481628653,
      "learning_rate": 8e-05,
      "loss": 0.4508,
      "step": 99
    },
    {
      "epoch": 1.0825439783491204,
      "grad_norm": 0.6213034134268403,
      "learning_rate": 8e-05,
      "loss": 0.4447,
      "step": 100
    },
    {
      "epoch": 1.0933694181326117,
      "grad_norm": 1.1436966830985928,
      "learning_rate": 8e-05,
      "loss": 0.446,
      "step": 101
    },
    {
      "epoch": 1.104194857916103,
      "grad_norm": 0.5408014494593189,
      "learning_rate": 8e-05,
      "loss": 0.444,
      "step": 102
    },
    {
      "epoch": 1.115020297699594,
      "grad_norm": 1.028568805313108,
      "learning_rate": 8e-05,
      "loss": 0.4489,
      "step": 103
    },
    {
      "epoch": 1.1258457374830853,
      "grad_norm": 0.6048086427564021,
      "learning_rate": 8e-05,
      "loss": 0.4399,
      "step": 104
    },
    {
      "epoch": 1.1366711772665765,
      "grad_norm": 0.6892127966627614,
      "learning_rate": 8e-05,
      "loss": 0.4466,
      "step": 105
    },
    {
      "epoch": 1.1474966170500678,
      "grad_norm": 0.9349533975260447,
      "learning_rate": 8e-05,
      "loss": 0.4549,
      "step": 106
    },
    {
      "epoch": 1.1583220568335588,
      "grad_norm": 1.1966306014967134,
      "learning_rate": 8e-05,
      "loss": 0.4576,
      "step": 107
    },
    {
      "epoch": 1.16914749661705,
      "grad_norm": 0.8219490051787685,
      "learning_rate": 8e-05,
      "loss": 0.4414,
      "step": 108
    },
    {
      "epoch": 1.1799729364005414,
      "grad_norm": 0.9666633349115288,
      "learning_rate": 8e-05,
      "loss": 0.4478,
      "step": 109
    },
    {
      "epoch": 1.1907983761840324,
      "grad_norm": 0.8780218733561178,
      "learning_rate": 8e-05,
      "loss": 0.4571,
      "step": 110
    },
    {
      "epoch": 1.2016238159675237,
      "grad_norm": 0.6971379135375524,
      "learning_rate": 8e-05,
      "loss": 0.451,
      "step": 111
    },
    {
      "epoch": 1.212449255751015,
      "grad_norm": 0.7317469338246573,
      "learning_rate": 8e-05,
      "loss": 0.4473,
      "step": 112
    },
    {
      "epoch": 1.2232746955345062,
      "grad_norm": 0.7497482386866777,
      "learning_rate": 8e-05,
      "loss": 0.4443,
      "step": 113
    },
    {
      "epoch": 1.2341001353179972,
      "grad_norm": 0.635953613977554,
      "learning_rate": 8e-05,
      "loss": 0.4484,
      "step": 114
    },
    {
      "epoch": 1.2449255751014885,
      "grad_norm": 0.6613340364389511,
      "learning_rate": 8e-05,
      "loss": 0.4541,
      "step": 115
    },
    {
      "epoch": 1.2557510148849798,
      "grad_norm": 0.5741765080204513,
      "learning_rate": 8e-05,
      "loss": 0.4453,
      "step": 116
    },
    {
      "epoch": 1.266576454668471,
      "grad_norm": 0.6470126255467455,
      "learning_rate": 8e-05,
      "loss": 0.4432,
      "step": 117
    },
    {
      "epoch": 1.277401894451962,
      "grad_norm": 0.6316348276542192,
      "learning_rate": 8e-05,
      "loss": 0.4429,
      "step": 118
    },
    {
      "epoch": 1.2882273342354533,
      "grad_norm": 0.703602890574505,
      "learning_rate": 8e-05,
      "loss": 0.4466,
      "step": 119
    },
    {
      "epoch": 1.2990527740189446,
      "grad_norm": 0.6017341954442595,
      "learning_rate": 8e-05,
      "loss": 0.4379,
      "step": 120
    },
    {
      "epoch": 1.3098782138024356,
      "grad_norm": 0.55704690193763,
      "learning_rate": 8e-05,
      "loss": 0.445,
      "step": 121
    },
    {
      "epoch": 1.320703653585927,
      "grad_norm": 0.5491675378275981,
      "learning_rate": 8e-05,
      "loss": 0.4406,
      "step": 122
    },
    {
      "epoch": 1.3315290933694182,
      "grad_norm": 0.5241794571136478,
      "learning_rate": 8e-05,
      "loss": 0.4437,
      "step": 123
    },
    {
      "epoch": 1.3423545331529092,
      "grad_norm": 0.4536573165272901,
      "learning_rate": 8e-05,
      "loss": 0.4404,
      "step": 124
    },
    {
      "epoch": 1.3531799729364005,
      "grad_norm": 0.5329307279939178,
      "learning_rate": 8e-05,
      "loss": 0.4411,
      "step": 125
    },
    {
      "epoch": 1.3640054127198917,
      "grad_norm": 0.6647085512781905,
      "learning_rate": 8e-05,
      "loss": 0.4403,
      "step": 126
    },
    {
      "epoch": 1.374830852503383,
      "grad_norm": 0.7950434375613059,
      "learning_rate": 8e-05,
      "loss": 0.4339,
      "step": 127
    },
    {
      "epoch": 1.3856562922868743,
      "grad_norm": 0.986996732307652,
      "learning_rate": 8e-05,
      "loss": 0.438,
      "step": 128
    },
    {
      "epoch": 1.3964817320703653,
      "grad_norm": 1.4507252385449585,
      "learning_rate": 8e-05,
      "loss": 0.4396,
      "step": 129
    },
    {
      "epoch": 1.4073071718538566,
      "grad_norm": 0.5584849928666911,
      "learning_rate": 8e-05,
      "loss": 0.4403,
      "step": 130
    },
    {
      "epoch": 1.4181326116373478,
      "grad_norm": 0.7205867424761765,
      "learning_rate": 8e-05,
      "loss": 0.4428,
      "step": 131
    },
    {
      "epoch": 1.4289580514208389,
      "grad_norm": 1.415100203832816,
      "learning_rate": 8e-05,
      "loss": 0.4478,
      "step": 132
    },
    {
      "epoch": 1.4397834912043301,
      "grad_norm": 0.57158230390258,
      "learning_rate": 8e-05,
      "loss": 0.4368,
      "step": 133
    },
    {
      "epoch": 1.4506089309878214,
      "grad_norm": 0.8961123339248364,
      "learning_rate": 8e-05,
      "loss": 0.4411,
      "step": 134
    },
    {
      "epoch": 1.4614343707713127,
      "grad_norm": 1.2354142003482231,
      "learning_rate": 8e-05,
      "loss": 0.4448,
      "step": 135
    },
    {
      "epoch": 1.472259810554804,
      "grad_norm": 0.46843886234292237,
      "learning_rate": 8e-05,
      "loss": 0.438,
      "step": 136
    },
    {
      "epoch": 1.483085250338295,
      "grad_norm": 1.059724991222621,
      "learning_rate": 8e-05,
      "loss": 0.4382,
      "step": 137
    },
    {
      "epoch": 1.4939106901217862,
      "grad_norm": 0.9466492713087674,
      "learning_rate": 8e-05,
      "loss": 0.4447,
      "step": 138
    },
    {
      "epoch": 1.5047361299052775,
      "grad_norm": 0.6229658071617709,
      "learning_rate": 8e-05,
      "loss": 0.4407,
      "step": 139
    },
    {
      "epoch": 1.5155615696887685,
      "grad_norm": 0.8567824556473228,
      "learning_rate": 8e-05,
      "loss": 0.4424,
      "step": 140
    },
    {
      "epoch": 1.5263870094722598,
      "grad_norm": 0.8016344501578274,
      "learning_rate": 8e-05,
      "loss": 0.4362,
      "step": 141
    },
    {
      "epoch": 1.537212449255751,
      "grad_norm": 0.5410578400249679,
      "learning_rate": 8e-05,
      "loss": 0.4375,
      "step": 142
    },
    {
      "epoch": 1.548037889039242,
      "grad_norm": 0.6462244120091978,
      "learning_rate": 8e-05,
      "loss": 0.4438,
      "step": 143
    },
    {
      "epoch": 1.5588633288227334,
      "grad_norm": 0.7575741468776858,
      "learning_rate": 8e-05,
      "loss": 0.4357,
      "step": 144
    },
    {
      "epoch": 1.5696887686062246,
      "grad_norm": 0.897856888158702,
      "learning_rate": 8e-05,
      "loss": 0.4342,
      "step": 145
    },
    {
      "epoch": 1.5805142083897157,
      "grad_norm": 1.0044331730101272,
      "learning_rate": 8e-05,
      "loss": 0.4351,
      "step": 146
    },
    {
      "epoch": 1.5913396481732072,
      "grad_norm": 1.2712493499695616,
      "learning_rate": 8e-05,
      "loss": 0.4346,
      "step": 147
    },
    {
      "epoch": 1.6021650879566982,
      "grad_norm": 0.7798725244323435,
      "learning_rate": 8e-05,
      "loss": 0.4506,
      "step": 148
    },
    {
      "epoch": 1.6129905277401895,
      "grad_norm": 0.5898580703758284,
      "learning_rate": 8e-05,
      "loss": 0.4326,
      "step": 149
    },
    {
      "epoch": 1.6238159675236807,
      "grad_norm": 0.9212323795966566,
      "learning_rate": 8e-05,
      "loss": 0.4391,
      "step": 150
    },
    {
      "epoch": 1.6346414073071718,
      "grad_norm": 1.3820718707346096,
      "learning_rate": 8e-05,
      "loss": 0.4425,
      "step": 151
    },
    {
      "epoch": 1.645466847090663,
      "grad_norm": 0.42655554033967763,
      "learning_rate": 8e-05,
      "loss": 0.4327,
      "step": 152
    },
    {
      "epoch": 1.6562922868741543,
      "grad_norm": 0.8274694728971709,
      "learning_rate": 8e-05,
      "loss": 0.4466,
      "step": 153
    },
    {
      "epoch": 1.6671177266576453,
      "grad_norm": 1.1944486387585824,
      "learning_rate": 8e-05,
      "loss": 0.4398,
      "step": 154
    },
    {
      "epoch": 1.6779431664411368,
      "grad_norm": 0.799774405221891,
      "learning_rate": 8e-05,
      "loss": 0.4318,
      "step": 155
    },
    {
      "epoch": 1.6887686062246279,
      "grad_norm": 0.6299578633527598,
      "learning_rate": 8e-05,
      "loss": 0.4405,
      "step": 156
    },
    {
      "epoch": 1.699594046008119,
      "grad_norm": 0.8152936753724142,
      "learning_rate": 8e-05,
      "loss": 0.4275,
      "step": 157
    },
    {
      "epoch": 1.7104194857916104,
      "grad_norm": 0.9822927904890273,
      "learning_rate": 8e-05,
      "loss": 0.4402,
      "step": 158
    },
    {
      "epoch": 1.7212449255751014,
      "grad_norm": 1.022705070161478,
      "learning_rate": 8e-05,
      "loss": 0.4464,
      "step": 159
    },
    {
      "epoch": 1.7320703653585927,
      "grad_norm": 1.2675351037559754,
      "learning_rate": 8e-05,
      "loss": 0.4425,
      "step": 160
    },
    {
      "epoch": 1.742895805142084,
      "grad_norm": 0.9122564954364916,
      "learning_rate": 8e-05,
      "loss": 0.4349,
      "step": 161
    },
    {
      "epoch": 1.753721244925575,
      "grad_norm": 1.154892475800215,
      "learning_rate": 8e-05,
      "loss": 0.4428,
      "step": 162
    },
    {
      "epoch": 1.7645466847090663,
      "grad_norm": 0.6569204291458755,
      "learning_rate": 8e-05,
      "loss": 0.4347,
      "step": 163
    },
    {
      "epoch": 1.7753721244925575,
      "grad_norm": 0.9001569379782519,
      "learning_rate": 8e-05,
      "loss": 0.4334,
      "step": 164
    },
    {
      "epoch": 1.7861975642760486,
      "grad_norm": 1.1059374902476302,
      "learning_rate": 8e-05,
      "loss": 0.441,
      "step": 165
    },
    {
      "epoch": 1.79702300405954,
      "grad_norm": 0.721265285208006,
      "learning_rate": 8e-05,
      "loss": 0.4312,
      "step": 166
    },
    {
      "epoch": 1.8078484438430311,
      "grad_norm": 0.7828337823334162,
      "learning_rate": 8e-05,
      "loss": 0.4384,
      "step": 167
    },
    {
      "epoch": 1.8186738836265224,
      "grad_norm": 0.6716345586231823,
      "learning_rate": 8e-05,
      "loss": 0.4342,
      "step": 168
    },
    {
      "epoch": 1.8294993234100136,
      "grad_norm": 0.5618306718894094,
      "learning_rate": 8e-05,
      "loss": 0.4421,
      "step": 169
    },
    {
      "epoch": 1.8403247631935047,
      "grad_norm": 0.6741245103863261,
      "learning_rate": 8e-05,
      "loss": 0.4338,
      "step": 170
    },
    {
      "epoch": 1.851150202976996,
      "grad_norm": 0.5703745915881904,
      "learning_rate": 8e-05,
      "loss": 0.4284,
      "step": 171
    },
    {
      "epoch": 1.8619756427604872,
      "grad_norm": 0.5088921121260613,
      "learning_rate": 8e-05,
      "loss": 0.429,
      "step": 172
    },
    {
      "epoch": 1.8728010825439783,
      "grad_norm": 0.5344910239314175,
      "learning_rate": 8e-05,
      "loss": 0.4233,
      "step": 173
    },
    {
      "epoch": 1.8836265223274695,
      "grad_norm": 0.5172061994163051,
      "learning_rate": 8e-05,
      "loss": 0.4365,
      "step": 174
    },
    {
      "epoch": 1.8944519621109608,
      "grad_norm": 0.6797669896449423,
      "learning_rate": 8e-05,
      "loss": 0.4297,
      "step": 175
    },
    {
      "epoch": 1.9052774018944518,
      "grad_norm": 0.6995574010157394,
      "learning_rate": 8e-05,
      "loss": 0.4245,
      "step": 176
    },
    {
      "epoch": 1.9161028416779433,
      "grad_norm": 0.4326288705344002,
      "learning_rate": 8e-05,
      "loss": 0.4257,
      "step": 177
    },
    {
      "epoch": 1.9269282814614344,
      "grad_norm": 0.44585677908376153,
      "learning_rate": 8e-05,
      "loss": 0.4368,
      "step": 178
    },
    {
      "epoch": 1.9377537212449256,
      "grad_norm": 0.6422932545928178,
      "learning_rate": 8e-05,
      "loss": 0.4327,
      "step": 179
    },
    {
      "epoch": 1.9485791610284169,
      "grad_norm": 0.9596282943394747,
      "learning_rate": 8e-05,
      "loss": 0.4401,
      "step": 180
    },
    {
      "epoch": 1.959404600811908,
      "grad_norm": 1.3180001416459295,
      "learning_rate": 8e-05,
      "loss": 0.4462,
      "step": 181
    },
    {
      "epoch": 1.9702300405953992,
      "grad_norm": 0.7257740568661001,
      "learning_rate": 8e-05,
      "loss": 0.4311,
      "step": 182
    },
    {
      "epoch": 1.9810554803788905,
      "grad_norm": 0.91213381307814,
      "learning_rate": 8e-05,
      "loss": 0.444,
      "step": 183
    },
    {
      "epoch": 1.9918809201623815,
      "grad_norm": 1.006369192892929,
      "learning_rate": 8e-05,
      "loss": 0.4445,
      "step": 184
    },
    {
      "epoch": 2.002706359945873,
      "grad_norm": 1.2255628177528402,
      "learning_rate": 8e-05,
      "loss": 0.6908,
      "step": 185
    },
    {
      "epoch": 2.013531799729364,
      "grad_norm": 1.2000777010705082,
      "learning_rate": 8e-05,
      "loss": 0.4058,
      "step": 186
    },
    {
      "epoch": 2.024357239512855,
      "grad_norm": 0.7667334718189589,
      "learning_rate": 8e-05,
      "loss": 0.3981,
      "step": 187
    },
    {
      "epoch": 2.0351826792963466,
      "grad_norm": 1.0236225784773203,
      "learning_rate": 8e-05,
      "loss": 0.4023,
      "step": 188
    },
    {
      "epoch": 2.0460081190798376,
      "grad_norm": 0.8106200546613148,
      "learning_rate": 8e-05,
      "loss": 0.3925,
      "step": 189
    },
    {
      "epoch": 2.0568335588633286,
      "grad_norm": 0.7317570304605234,
      "learning_rate": 8e-05,
      "loss": 0.3979,
      "step": 190
    },
    {
      "epoch": 2.06765899864682,
      "grad_norm": 0.9305071367933562,
      "learning_rate": 8e-05,
      "loss": 0.4022,
      "step": 191
    },
    {
      "epoch": 2.078484438430311,
      "grad_norm": 0.7930690893265405,
      "learning_rate": 8e-05,
      "loss": 0.4062,
      "step": 192
    },
    {
      "epoch": 2.089309878213802,
      "grad_norm": 0.9400228430220682,
      "learning_rate": 8e-05,
      "loss": 0.3988,
      "step": 193
    },
    {
      "epoch": 2.1001353179972937,
      "grad_norm": 1.4039534797235795,
      "learning_rate": 8e-05,
      "loss": 0.3939,
      "step": 194
    },
    {
      "epoch": 2.1109607577807847,
      "grad_norm": 0.5779559622955999,
      "learning_rate": 8e-05,
      "loss": 0.3979,
      "step": 195
    },
    {
      "epoch": 2.121786197564276,
      "grad_norm": 0.9372014257132301,
      "learning_rate": 8e-05,
      "loss": 0.3986,
      "step": 196
    },
    {
      "epoch": 2.1326116373477673,
      "grad_norm": 1.3846207460387259,
      "learning_rate": 8e-05,
      "loss": 0.396,
      "step": 197
    },
    {
      "epoch": 2.1434370771312583,
      "grad_norm": 0.5368857232972116,
      "learning_rate": 8e-05,
      "loss": 0.3904,
      "step": 198
    },
    {
      "epoch": 2.15426251691475,
      "grad_norm": 1.3270911589780856,
      "learning_rate": 8e-05,
      "loss": 0.4008,
      "step": 199
    },
    {
      "epoch": 2.165087956698241,
      "grad_norm": 0.6428402239375345,
      "learning_rate": 8e-05,
      "loss": 0.3995,
      "step": 200
    },
    {
      "epoch": 2.175913396481732,
      "grad_norm": 0.8841538069984701,
      "learning_rate": 8e-05,
      "loss": 0.3971,
      "step": 201
    },
    {
      "epoch": 2.1867388362652234,
      "grad_norm": 0.7935462265921484,
      "learning_rate": 8e-05,
      "loss": 0.3932,
      "step": 202
    },
    {
      "epoch": 2.1975642760487144,
      "grad_norm": 0.4549601714356735,
      "learning_rate": 8e-05,
      "loss": 0.3999,
      "step": 203
    },
    {
      "epoch": 2.208389715832206,
      "grad_norm": 0.763729115288534,
      "learning_rate": 8e-05,
      "loss": 0.3988,
      "step": 204
    },
    {
      "epoch": 2.219215155615697,
      "grad_norm": 0.7144305002132605,
      "learning_rate": 8e-05,
      "loss": 0.3954,
      "step": 205
    },
    {
      "epoch": 2.230040595399188,
      "grad_norm": 0.6657891408243943,
      "learning_rate": 8e-05,
      "loss": 0.3954,
      "step": 206
    },
    {
      "epoch": 2.2408660351826795,
      "grad_norm": 0.8459834817385382,
      "learning_rate": 8e-05,
      "loss": 0.3997,
      "step": 207
    },
    {
      "epoch": 2.2516914749661705,
      "grad_norm": 0.8738704004615443,
      "learning_rate": 8e-05,
      "loss": 0.3911,
      "step": 208
    },
    {
      "epoch": 2.2625169147496615,
      "grad_norm": 0.8280258828543996,
      "learning_rate": 8e-05,
      "loss": 0.3944,
      "step": 209
    },
    {
      "epoch": 2.273342354533153,
      "grad_norm": 0.5623034500552045,
      "learning_rate": 8e-05,
      "loss": 0.3903,
      "step": 210
    },
    {
      "epoch": 2.284167794316644,
      "grad_norm": 0.41234012563365113,
      "learning_rate": 8e-05,
      "loss": 0.3913,
      "step": 211
    },
    {
      "epoch": 2.2949932341001356,
      "grad_norm": 0.4775139696396058,
      "learning_rate": 8e-05,
      "loss": 0.3914,
      "step": 212
    },
    {
      "epoch": 2.3058186738836266,
      "grad_norm": 0.5029596598230981,
      "learning_rate": 8e-05,
      "loss": 0.3988,
      "step": 213
    },
    {
      "epoch": 2.3166441136671176,
      "grad_norm": 0.5030432186496101,
      "learning_rate": 8e-05,
      "loss": 0.3932,
      "step": 214
    },
    {
      "epoch": 2.3274695534506087,
      "grad_norm": 0.4801703549991224,
      "learning_rate": 8e-05,
      "loss": 0.3939,
      "step": 215
    },
    {
      "epoch": 2.3382949932341,
      "grad_norm": 0.4645088513663148,
      "learning_rate": 8e-05,
      "loss": 0.3996,
      "step": 216
    },
    {
      "epoch": 2.349120433017591,
      "grad_norm": 0.45428781139708957,
      "learning_rate": 8e-05,
      "loss": 0.3928,
      "step": 217
    },
    {
      "epoch": 2.3599458728010827,
      "grad_norm": 0.4099893977750919,
      "learning_rate": 8e-05,
      "loss": 0.4006,
      "step": 218
    },
    {
      "epoch": 2.3707713125845737,
      "grad_norm": 0.34016096548417685,
      "learning_rate": 8e-05,
      "loss": 0.3971,
      "step": 219
    },
    {
      "epoch": 2.381596752368065,
      "grad_norm": 0.3802639440292822,
      "learning_rate": 8e-05,
      "loss": 0.3855,
      "step": 220
    },
    {
      "epoch": 2.3924221921515563,
      "grad_norm": 0.4871879170196444,
      "learning_rate": 8e-05,
      "loss": 0.3925,
      "step": 221
    },
    {
      "epoch": 2.4032476319350473,
      "grad_norm": 0.5083431061111152,
      "learning_rate": 8e-05,
      "loss": 0.3995,
      "step": 222
    },
    {
      "epoch": 2.414073071718539,
      "grad_norm": 0.5760449323294583,
      "learning_rate": 8e-05,
      "loss": 0.3991,
      "step": 223
    },
    {
      "epoch": 2.42489851150203,
      "grad_norm": 0.635143402451684,
      "learning_rate": 8e-05,
      "loss": 0.3967,
      "step": 224
    },
    {
      "epoch": 2.435723951285521,
      "grad_norm": 0.8363791843448851,
      "learning_rate": 8e-05,
      "loss": 0.3961,
      "step": 225
    },
    {
      "epoch": 2.4465493910690124,
      "grad_norm": 0.9466677198233424,
      "learning_rate": 8e-05,
      "loss": 0.3994,
      "step": 226
    },
    {
      "epoch": 2.4573748308525034,
      "grad_norm": 0.9251393824517644,
      "learning_rate": 8e-05,
      "loss": 0.3931,
      "step": 227
    },
    {
      "epoch": 2.4682002706359945,
      "grad_norm": 0.7794567555727502,
      "learning_rate": 8e-05,
      "loss": 0.3936,
      "step": 228
    },
    {
      "epoch": 2.479025710419486,
      "grad_norm": 0.6447216730354077,
      "learning_rate": 8e-05,
      "loss": 0.3896,
      "step": 229
    },
    {
      "epoch": 2.489851150202977,
      "grad_norm": 0.5251441182452614,
      "learning_rate": 8e-05,
      "loss": 0.392,
      "step": 230
    },
    {
      "epoch": 2.500676589986468,
      "grad_norm": 0.5338620797791087,
      "learning_rate": 8e-05,
      "loss": 0.4018,
      "step": 231
    },
    {
      "epoch": 2.5115020297699595,
      "grad_norm": 0.6154775138754839,
      "learning_rate": 8e-05,
      "loss": 0.3989,
      "step": 232
    },
    {
      "epoch": 2.5223274695534506,
      "grad_norm": 0.6470653223908617,
      "learning_rate": 8e-05,
      "loss": 0.3942,
      "step": 233
    },
    {
      "epoch": 2.533152909336942,
      "grad_norm": 0.7642770319813473,
      "learning_rate": 8e-05,
      "loss": 0.3971,
      "step": 234
    },
    {
      "epoch": 2.543978349120433,
      "grad_norm": 0.7694403741692109,
      "learning_rate": 8e-05,
      "loss": 0.3918,
      "step": 235
    },
    {
      "epoch": 2.554803788903924,
      "grad_norm": 0.5922468400912506,
      "learning_rate": 8e-05,
      "loss": 0.3899,
      "step": 236
    },
    {
      "epoch": 2.565629228687415,
      "grad_norm": 0.5964604536454737,
      "learning_rate": 8e-05,
      "loss": 0.3961,
      "step": 237
    },
    {
      "epoch": 2.5764546684709067,
      "grad_norm": 0.7061789839524584,
      "learning_rate": 8e-05,
      "loss": 0.3949,
      "step": 238
    },
    {
      "epoch": 2.5872801082543977,
      "grad_norm": 0.8866775418922312,
      "learning_rate": 8e-05,
      "loss": 0.3948,
      "step": 239
    },
    {
      "epoch": 2.598105548037889,
      "grad_norm": 0.9520014428818128,
      "learning_rate": 8e-05,
      "loss": 0.4028,
      "step": 240
    },
    {
      "epoch": 2.60893098782138,
      "grad_norm": 0.7888764328209086,
      "learning_rate": 8e-05,
      "loss": 0.4048,
      "step": 241
    },
    {
      "epoch": 2.6197564276048713,
      "grad_norm": 0.6524059590233521,
      "learning_rate": 8e-05,
      "loss": 0.4037,
      "step": 242
    },
    {
      "epoch": 2.6305818673883627,
      "grad_norm": 0.5469041163109016,
      "learning_rate": 8e-05,
      "loss": 0.3944,
      "step": 243
    },
    {
      "epoch": 2.641407307171854,
      "grad_norm": 0.5174111580942308,
      "learning_rate": 8e-05,
      "loss": 0.3919,
      "step": 244
    },
    {
      "epoch": 2.6522327469553453,
      "grad_norm": 0.6080799187996141,
      "learning_rate": 8e-05,
      "loss": 0.3928,
      "step": 245
    },
    {
      "epoch": 2.6630581867388363,
      "grad_norm": 0.5503770034246838,
      "learning_rate": 8e-05,
      "loss": 0.3935,
      "step": 246
    },
    {
      "epoch": 2.6738836265223274,
      "grad_norm": 0.7421867800180407,
      "learning_rate": 8e-05,
      "loss": 0.3989,
      "step": 247
    },
    {
      "epoch": 2.6847090663058184,
      "grad_norm": 0.832508761134136,
      "learning_rate": 8e-05,
      "loss": 0.3938,
      "step": 248
    },
    {
      "epoch": 2.69553450608931,
      "grad_norm": 0.6596210825904264,
      "learning_rate": 8e-05,
      "loss": 0.39,
      "step": 249
    },
    {
      "epoch": 2.706359945872801,
      "grad_norm": 0.6285599627532429,
      "learning_rate": 8e-05,
      "loss": 0.4007,
      "step": 250
    },
    {
      "epoch": 2.7171853856562924,
      "grad_norm": 0.5760125809095306,
      "learning_rate": 8e-05,
      "loss": 0.3964,
      "step": 251
    },
    {
      "epoch": 2.7280108254397835,
      "grad_norm": 0.3609858997834312,
      "learning_rate": 8e-05,
      "loss": 0.3998,
      "step": 252
    },
    {
      "epoch": 2.7388362652232745,
      "grad_norm": 0.4776027969483358,
      "learning_rate": 8e-05,
      "loss": 0.3983,
      "step": 253
    },
    {
      "epoch": 2.749661705006766,
      "grad_norm": 0.5587204073568423,
      "learning_rate": 8e-05,
      "loss": 0.3926,
      "step": 254
    },
    {
      "epoch": 2.760487144790257,
      "grad_norm": 0.4726856195122079,
      "learning_rate": 8e-05,
      "loss": 0.389,
      "step": 255
    },
    {
      "epoch": 2.7713125845737485,
      "grad_norm": 0.40776565623584726,
      "learning_rate": 8e-05,
      "loss": 0.387,
      "step": 256
    },
    {
      "epoch": 2.7821380243572396,
      "grad_norm": 0.4720916217468958,
      "learning_rate": 8e-05,
      "loss": 0.4006,
      "step": 257
    },
    {
      "epoch": 2.7929634641407306,
      "grad_norm": 0.38138341344774684,
      "learning_rate": 8e-05,
      "loss": 0.3936,
      "step": 258
    },
    {
      "epoch": 2.803788903924222,
      "grad_norm": 0.35206569982007563,
      "learning_rate": 8e-05,
      "loss": 0.3923,
      "step": 259
    },
    {
      "epoch": 2.814614343707713,
      "grad_norm": 0.34420663245480054,
      "learning_rate": 8e-05,
      "loss": 0.3973,
      "step": 260
    },
    {
      "epoch": 2.825439783491204,
      "grad_norm": 0.3746770658244233,
      "learning_rate": 8e-05,
      "loss": 0.3877,
      "step": 261
    },
    {
      "epoch": 2.8362652232746957,
      "grad_norm": 0.40998736452760093,
      "learning_rate": 8e-05,
      "loss": 0.3929,
      "step": 262
    },
    {
      "epoch": 2.8470906630581867,
      "grad_norm": 0.5668861631407464,
      "learning_rate": 8e-05,
      "loss": 0.3969,
      "step": 263
    },
    {
      "epoch": 2.8579161028416777,
      "grad_norm": 0.6103163114449736,
      "learning_rate": 8e-05,
      "loss": 0.3944,
      "step": 264
    },
    {
      "epoch": 2.8687415426251692,
      "grad_norm": 0.6928050432011605,
      "learning_rate": 8e-05,
      "loss": 0.3988,
      "step": 265
    },
    {
      "epoch": 2.8795669824086603,
      "grad_norm": 0.9598469526386861,
      "learning_rate": 8e-05,
      "loss": 0.398,
      "step": 266
    },
    {
      "epoch": 2.8903924221921518,
      "grad_norm": 1.3233845107483573,
      "learning_rate": 8e-05,
      "loss": 0.3967,
      "step": 267
    },
    {
      "epoch": 2.901217861975643,
      "grad_norm": 0.4812047834015932,
      "learning_rate": 8e-05,
      "loss": 0.3939,
      "step": 268
    },
    {
      "epoch": 2.912043301759134,
      "grad_norm": 0.8007412346439379,
      "learning_rate": 8e-05,
      "loss": 0.3964,
      "step": 269
    },
    {
      "epoch": 2.9228687415426253,
      "grad_norm": 1.3177807016197527,
      "learning_rate": 8e-05,
      "loss": 0.3998,
      "step": 270
    },
    {
      "epoch": 2.9336941813261164,
      "grad_norm": 0.46546006266891304,
      "learning_rate": 8e-05,
      "loss": 0.3935,
      "step": 271
    },
    {
      "epoch": 2.944519621109608,
      "grad_norm": 0.8477498917792659,
      "learning_rate": 8e-05,
      "loss": 0.4018,
      "step": 272
    },
    {
      "epoch": 2.955345060893099,
      "grad_norm": 1.2402314376056842,
      "learning_rate": 8e-05,
      "loss": 0.4006,
      "step": 273
    },
    {
      "epoch": 2.96617050067659,
      "grad_norm": 0.4786991677880001,
      "learning_rate": 8e-05,
      "loss": 0.3949,
      "step": 274
    },
    {
      "epoch": 2.976995940460081,
      "grad_norm": 0.8912526436279338,
      "learning_rate": 8e-05,
      "loss": 0.405,
      "step": 275
    },
    {
      "epoch": 2.9878213802435725,
      "grad_norm": 1.0125291740331552,
      "learning_rate": 8e-05,
      "loss": 0.393,
      "step": 276
    },
    {
      "epoch": 2.9878213802435725,
      "step": 276,
      "total_flos": 6.629121904995205e+18,
      "train_loss": 0.49312817910011264,
      "train_runtime": 27073.2462,
      "train_samples_per_second": 5.24,
      "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
}