{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.4557575757575758,
  "eval_steps": 618,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0024242424242424242,
      "grad_norm": 1.7425179481506348,
      "learning_rate": 4e-05,
      "loss": 1.7657,
      "step": 1
    },
    {
      "epoch": 0.0048484848484848485,
      "grad_norm": 1.6909098625183105,
      "learning_rate": 8e-05,
      "loss": 1.7918,
      "step": 2
    },
    {
      "epoch": 0.007272727272727273,
      "grad_norm": 1.2282295227050781,
      "learning_rate": 0.00012,
      "loss": 1.7756,
      "step": 3
    },
    {
      "epoch": 0.009696969696969697,
      "grad_norm": 1.8810029029846191,
      "learning_rate": 0.00016,
      "loss": 1.6995,
      "step": 4
    },
    {
      "epoch": 0.012121212121212121,
      "grad_norm": 0.9939211010932922,
      "learning_rate": 0.0002,
      "loss": 1.4088,
      "step": 5
    },
    {
      "epoch": 0.014545454545454545,
      "grad_norm": 1.343316912651062,
      "learning_rate": 0.00019990267639902678,
      "loss": 1.2618,
      "step": 6
    },
    {
      "epoch": 0.01696969696969697,
      "grad_norm": 1.3122458457946777,
      "learning_rate": 0.00019980535279805355,
      "loss": 1.0503,
      "step": 7
    },
    {
      "epoch": 0.019393939393939394,
      "grad_norm": 1.8026890754699707,
      "learning_rate": 0.0001997080291970803,
      "loss": 1.071,
      "step": 8
    },
    {
      "epoch": 0.02181818181818182,
      "grad_norm": 0.8950812816619873,
      "learning_rate": 0.00019961070559610706,
      "loss": 0.9272,
      "step": 9
    },
    {
      "epoch": 0.024242424242424242,
      "grad_norm": 0.6290344595909119,
      "learning_rate": 0.00019951338199513383,
      "loss": 0.8546,
      "step": 10
    },
    {
      "epoch": 0.02666666666666667,
      "grad_norm": 1.0111929178237915,
      "learning_rate": 0.0001994160583941606,
      "loss": 0.8405,
      "step": 11
    },
    {
      "epoch": 0.02909090909090909,
      "grad_norm": 0.9520079493522644,
      "learning_rate": 0.00019931873479318737,
      "loss": 0.734,
      "step": 12
    },
    {
      "epoch": 0.03151515151515152,
      "grad_norm": 0.36593878269195557,
      "learning_rate": 0.00019922141119221412,
      "loss": 0.6875,
      "step": 13
    },
    {
      "epoch": 0.03393939393939394,
      "grad_norm": 0.12287554889917374,
      "learning_rate": 0.0001991240875912409,
      "loss": 0.7272,
      "step": 14
    },
    {
      "epoch": 0.03636363636363636,
      "grad_norm": 0.18190374970436096,
      "learning_rate": 0.00019902676399026766,
      "loss": 0.715,
      "step": 15
    },
    {
      "epoch": 0.03878787878787879,
      "grad_norm": 0.17419151961803436,
      "learning_rate": 0.00019892944038929443,
      "loss": 0.7569,
      "step": 16
    },
    {
      "epoch": 0.041212121212121214,
      "grad_norm": 0.2105356752872467,
      "learning_rate": 0.0001988321167883212,
      "loss": 0.7141,
      "step": 17
    },
    {
      "epoch": 0.04363636363636364,
      "grad_norm": 0.1196451410651207,
      "learning_rate": 0.00019873479318734794,
      "loss": 0.667,
      "step": 18
    },
    {
      "epoch": 0.04606060606060606,
      "grad_norm": 0.14296391606330872,
      "learning_rate": 0.0001986374695863747,
      "loss": 0.6317,
      "step": 19
    },
    {
      "epoch": 0.048484848484848485,
      "grad_norm": 0.11963274329900742,
      "learning_rate": 0.00019854014598540148,
      "loss": 0.6304,
      "step": 20
    },
    {
      "epoch": 0.05090909090909091,
      "grad_norm": 0.12816332280635834,
      "learning_rate": 0.00019844282238442825,
      "loss": 0.6017,
      "step": 21
    },
    {
      "epoch": 0.05333333333333334,
      "grad_norm": 0.11013495177030563,
      "learning_rate": 0.00019834549878345502,
      "loss": 0.6208,
      "step": 22
    },
    {
      "epoch": 0.055757575757575756,
      "grad_norm": 0.10363325476646423,
      "learning_rate": 0.00019824817518248176,
      "loss": 0.6037,
      "step": 23
    },
    {
      "epoch": 0.05818181818181818,
      "grad_norm": 0.1047598198056221,
      "learning_rate": 0.00019815085158150853,
      "loss": 0.5931,
      "step": 24
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 0.10422267019748688,
      "learning_rate": 0.0001980535279805353,
      "loss": 0.6402,
      "step": 25
    },
    {
      "epoch": 0.06303030303030303,
      "grad_norm": 0.08431805670261383,
      "learning_rate": 0.00019795620437956205,
      "loss": 0.5861,
      "step": 26
    },
    {
      "epoch": 0.06545454545454546,
      "grad_norm": 0.13943104445934296,
      "learning_rate": 0.00019785888077858882,
      "loss": 0.5996,
      "step": 27
    },
    {
      "epoch": 0.06787878787878789,
      "grad_norm": 0.10621320456266403,
      "learning_rate": 0.0001977615571776156,
      "loss": 0.6052,
      "step": 28
    },
    {
      "epoch": 0.0703030303030303,
      "grad_norm": 0.08163227140903473,
      "learning_rate": 0.00019766423357664233,
      "loss": 0.5941,
      "step": 29
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": 0.07070121169090271,
      "learning_rate": 0.0001975669099756691,
      "loss": 0.5825,
      "step": 30
    },
    {
      "epoch": 0.07515151515151515,
      "grad_norm": 0.07085420191287994,
      "learning_rate": 0.00019746958637469587,
      "loss": 0.5675,
      "step": 31
    },
    {
      "epoch": 0.07757575757575758,
      "grad_norm": 0.08051861077547073,
      "learning_rate": 0.00019737226277372262,
      "loss": 0.5848,
      "step": 32
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.08641697466373444,
      "learning_rate": 0.00019727493917274939,
      "loss": 0.6357,
      "step": 33
    },
    {
      "epoch": 0.08242424242424243,
      "grad_norm": 0.07897619158029556,
      "learning_rate": 0.00019717761557177616,
      "loss": 0.6031,
      "step": 34
    },
    {
      "epoch": 0.08484848484848485,
      "grad_norm": 0.0772792249917984,
      "learning_rate": 0.00019708029197080293,
      "loss": 0.6103,
      "step": 35
    },
    {
      "epoch": 0.08727272727272728,
      "grad_norm": 0.07374991476535797,
      "learning_rate": 0.0001969829683698297,
      "loss": 0.6383,
      "step": 36
    },
    {
      "epoch": 0.08969696969696969,
      "grad_norm": 0.0848601683974266,
      "learning_rate": 0.00019688564476885644,
      "loss": 0.5904,
      "step": 37
    },
    {
      "epoch": 0.09212121212121212,
      "grad_norm": 0.15618138015270233,
      "learning_rate": 0.0001967883211678832,
      "loss": 0.6137,
      "step": 38
    },
    {
      "epoch": 0.09454545454545454,
      "grad_norm": 0.08134500682353973,
      "learning_rate": 0.00019669099756690998,
      "loss": 0.5945,
      "step": 39
    },
    {
      "epoch": 0.09696969696969697,
      "grad_norm": 0.06627924740314484,
      "learning_rate": 0.00019659367396593675,
      "loss": 0.5549,
      "step": 40
    },
    {
      "epoch": 0.0993939393939394,
      "grad_norm": 0.0704004094004631,
      "learning_rate": 0.00019649635036496352,
      "loss": 0.5591,
      "step": 41
    },
    {
      "epoch": 0.10181818181818182,
      "grad_norm": 0.6976714134216309,
      "learning_rate": 0.00019639902676399026,
      "loss": 0.6126,
      "step": 42
    },
    {
      "epoch": 0.10424242424242425,
      "grad_norm": 0.07345545291900635,
      "learning_rate": 0.00019630170316301703,
      "loss": 0.6015,
      "step": 43
    },
    {
      "epoch": 0.10666666666666667,
      "grad_norm": 0.25629881024360657,
      "learning_rate": 0.0001962043795620438,
      "loss": 0.5671,
      "step": 44
    },
    {
      "epoch": 0.10909090909090909,
      "grad_norm": 0.17710916697978973,
      "learning_rate": 0.00019610705596107057,
      "loss": 0.6061,
      "step": 45
    },
    {
      "epoch": 0.11151515151515151,
      "grad_norm": 0.06087492033839226,
      "learning_rate": 0.00019600973236009734,
      "loss": 0.5632,
      "step": 46
    },
    {
      "epoch": 0.11393939393939394,
      "grad_norm": 0.11297113448381424,
      "learning_rate": 0.0001959124087591241,
      "loss": 0.5791,
      "step": 47
    },
    {
      "epoch": 0.11636363636363636,
      "grad_norm": 0.06977778673171997,
      "learning_rate": 0.00019581508515815086,
      "loss": 0.5795,
      "step": 48
    },
    {
      "epoch": 0.11878787878787879,
      "grad_norm": 0.07200987637042999,
      "learning_rate": 0.00019571776155717763,
      "loss": 0.6072,
      "step": 49
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 0.08989960700273514,
      "learning_rate": 0.0001956204379562044,
      "loss": 0.5589,
      "step": 50
    },
    {
      "epoch": 0.12363636363636364,
      "grad_norm": 0.5294026136398315,
      "learning_rate": 0.00019552311435523117,
      "loss": 0.5807,
      "step": 51
    },
    {
      "epoch": 0.12606060606060607,
      "grad_norm": 0.08921587467193604,
      "learning_rate": 0.0001954257907542579,
      "loss": 0.5439,
      "step": 52
    },
    {
      "epoch": 0.12848484848484848,
      "grad_norm": 0.07092791050672531,
      "learning_rate": 0.00019532846715328468,
      "loss": 0.5879,
      "step": 53
    },
    {
      "epoch": 0.13090909090909092,
      "grad_norm": 0.07337342947721481,
      "learning_rate": 0.00019523114355231145,
      "loss": 0.5856,
      "step": 54
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 0.5336478352546692,
      "learning_rate": 0.00019513381995133822,
      "loss": 1.679,
      "step": 55
    },
    {
      "epoch": 0.13575757575757577,
      "grad_norm": 0.06451793015003204,
      "learning_rate": 0.000195036496350365,
      "loss": 0.5831,
      "step": 56
    },
    {
      "epoch": 0.13818181818181818,
      "grad_norm": 0.06546330451965332,
      "learning_rate": 0.00019493917274939173,
      "loss": 0.529,
      "step": 57
    },
    {
      "epoch": 0.1406060606060606,
      "grad_norm": 0.06920003890991211,
      "learning_rate": 0.0001948418491484185,
      "loss": 0.5711,
      "step": 58
    },
    {
      "epoch": 0.14303030303030304,
      "grad_norm": 3.3777191638946533,
      "learning_rate": 0.00019474452554744528,
      "loss": 0.5884,
      "step": 59
    },
    {
      "epoch": 0.14545454545454545,
      "grad_norm": 0.09820184111595154,
      "learning_rate": 0.00019464720194647205,
      "loss": 0.5955,
      "step": 60
    },
    {
      "epoch": 0.1478787878787879,
      "grad_norm": 0.06972799450159073,
      "learning_rate": 0.00019454987834549882,
      "loss": 0.608,
      "step": 61
    },
    {
      "epoch": 0.1503030303030303,
      "grad_norm": 0.08447355777025223,
      "learning_rate": 0.00019445255474452556,
      "loss": 0.5647,
      "step": 62
    },
    {
      "epoch": 0.15272727272727274,
      "grad_norm": 0.06691451370716095,
      "learning_rate": 0.00019435523114355233,
      "loss": 0.6071,
      "step": 63
    },
    {
      "epoch": 0.15515151515151515,
      "grad_norm": 0.07997488230466843,
      "learning_rate": 0.0001942579075425791,
      "loss": 0.55,
      "step": 64
    },
    {
      "epoch": 0.15757575757575756,
      "grad_norm": 0.09458561986684799,
      "learning_rate": 0.00019416058394160587,
      "loss": 0.5669,
      "step": 65
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.0648735761642456,
      "learning_rate": 0.0001940632603406326,
      "loss": 0.5622,
      "step": 66
    },
    {
      "epoch": 0.16242424242424242,
      "grad_norm": 0.06812532991170883,
      "learning_rate": 0.00019396593673965938,
      "loss": 0.5565,
      "step": 67
    },
    {
      "epoch": 0.16484848484848486,
      "grad_norm": 0.0666588842868805,
      "learning_rate": 0.00019386861313868615,
      "loss": 0.6002,
      "step": 68
    },
    {
      "epoch": 0.16727272727272727,
      "grad_norm": 0.06052225083112717,
      "learning_rate": 0.0001937712895377129,
      "loss": 0.5874,
      "step": 69
    },
    {
      "epoch": 0.1696969696969697,
      "grad_norm": 0.06878744065761566,
      "learning_rate": 0.00019367396593673967,
      "loss": 0.5814,
      "step": 70
    },
    {
      "epoch": 0.17212121212121212,
      "grad_norm": 0.0665239542722702,
      "learning_rate": 0.00019357664233576644,
      "loss": 0.5692,
      "step": 71
    },
    {
      "epoch": 0.17454545454545456,
      "grad_norm": 0.07615058124065399,
      "learning_rate": 0.00019347931873479318,
      "loss": 0.593,
      "step": 72
    },
    {
      "epoch": 0.17696969696969697,
      "grad_norm": 0.100388303399086,
      "learning_rate": 0.00019338199513381995,
      "loss": 0.6094,
      "step": 73
    },
    {
      "epoch": 0.17939393939393938,
      "grad_norm": 0.06404981017112732,
      "learning_rate": 0.00019328467153284672,
      "loss": 0.5648,
      "step": 74
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.0599268339574337,
      "learning_rate": 0.0001931873479318735,
      "loss": 0.5705,
      "step": 75
    },
    {
      "epoch": 0.18424242424242424,
      "grad_norm": 0.07185366749763489,
      "learning_rate": 0.00019309002433090023,
      "loss": 0.5706,
      "step": 76
    },
    {
      "epoch": 0.18666666666666668,
      "grad_norm": 0.07109599560499191,
      "learning_rate": 0.000192992700729927,
      "loss": 0.5911,
      "step": 77
    },
    {
      "epoch": 0.1890909090909091,
      "grad_norm": 0.0685252696275711,
      "learning_rate": 0.00019289537712895377,
      "loss": 0.5534,
      "step": 78
    },
    {
      "epoch": 0.19151515151515153,
      "grad_norm": 0.06272438168525696,
      "learning_rate": 0.00019279805352798054,
      "loss": 0.5589,
      "step": 79
    },
    {
      "epoch": 0.19393939393939394,
      "grad_norm": 0.07795873284339905,
      "learning_rate": 0.00019270072992700731,
      "loss": 0.573,
      "step": 80
    },
    {
      "epoch": 0.19636363636363635,
      "grad_norm": 0.07623926550149918,
      "learning_rate": 0.00019260340632603406,
      "loss": 0.579,
      "step": 81
    },
    {
      "epoch": 0.1987878787878788,
      "grad_norm": 0.08499354869127274,
      "learning_rate": 0.00019250608272506083,
      "loss": 0.5803,
      "step": 82
    },
    {
      "epoch": 0.2012121212121212,
      "grad_norm": 0.0631449818611145,
      "learning_rate": 0.0001924087591240876,
      "loss": 0.5462,
      "step": 83
    },
    {
      "epoch": 0.20363636363636364,
      "grad_norm": 0.06587008386850357,
      "learning_rate": 0.00019231143552311437,
      "loss": 0.555,
      "step": 84
    },
    {
      "epoch": 0.20606060606060606,
      "grad_norm": 0.0610431507229805,
      "learning_rate": 0.00019221411192214114,
      "loss": 0.5618,
      "step": 85
    },
    {
      "epoch": 0.2084848484848485,
      "grad_norm": 0.07323484122753143,
      "learning_rate": 0.00019211678832116788,
      "loss": 0.5598,
      "step": 86
    },
    {
      "epoch": 0.2109090909090909,
      "grad_norm": 0.06744620203971863,
      "learning_rate": 0.00019201946472019465,
      "loss": 0.5689,
      "step": 87
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 0.06995084136724472,
      "learning_rate": 0.00019192214111922142,
      "loss": 0.5544,
      "step": 88
    },
    {
      "epoch": 0.21575757575757576,
      "grad_norm": 0.06571096181869507,
      "learning_rate": 0.0001918248175182482,
      "loss": 0.5606,
      "step": 89
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 0.060402851551771164,
      "learning_rate": 0.00019172749391727496,
      "loss": 0.5732,
      "step": 90
    },
    {
      "epoch": 0.2206060606060606,
      "grad_norm": 0.070176862180233,
      "learning_rate": 0.0001916301703163017,
      "loss": 0.5872,
      "step": 91
    },
    {
      "epoch": 0.22303030303030302,
      "grad_norm": 0.0692034438252449,
      "learning_rate": 0.00019153284671532847,
      "loss": 0.5976,
      "step": 92
    },
    {
      "epoch": 0.22545454545454546,
      "grad_norm": 0.06749644130468369,
      "learning_rate": 0.00019143552311435524,
      "loss": 0.5625,
      "step": 93
    },
    {
      "epoch": 0.22787878787878788,
      "grad_norm": 0.06651509553194046,
      "learning_rate": 0.00019133819951338202,
      "loss": 0.5408,
      "step": 94
    },
    {
      "epoch": 0.23030303030303031,
      "grad_norm": 0.06177860498428345,
      "learning_rate": 0.00019124087591240879,
      "loss": 0.5678,
      "step": 95
    },
    {
      "epoch": 0.23272727272727273,
      "grad_norm": 0.06545785069465637,
      "learning_rate": 0.00019114355231143553,
      "loss": 0.5383,
      "step": 96
    },
    {
      "epoch": 0.23515151515151514,
      "grad_norm": 0.06618417799472809,
      "learning_rate": 0.0001910462287104623,
      "loss": 0.5664,
      "step": 97
    },
    {
      "epoch": 0.23757575757575758,
      "grad_norm": 0.061648230999708176,
      "learning_rate": 0.00019094890510948907,
      "loss": 0.5498,
      "step": 98
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.06203509122133255,
      "learning_rate": 0.00019085158150851584,
      "loss": 0.5755,
      "step": 99
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 0.06885362416505814,
      "learning_rate": 0.00019075425790754258,
      "loss": 0.5642,
      "step": 100
    },
    {
      "epoch": 0.24484848484848484,
      "grad_norm": 0.06191356107592583,
      "learning_rate": 0.00019065693430656935,
      "loss": 0.5454,
      "step": 101
    },
    {
      "epoch": 0.24727272727272728,
      "grad_norm": 0.15593962371349335,
      "learning_rate": 0.00019055961070559612,
      "loss": 0.5988,
      "step": 102
    },
    {
      "epoch": 0.2496969696969697,
      "grad_norm": 0.06816019117832184,
      "learning_rate": 0.0001904622871046229,
      "loss": 0.6034,
      "step": 103
    },
    {
      "epoch": 0.25212121212121213,
      "grad_norm": 0.060558732599020004,
      "learning_rate": 0.00019036496350364966,
      "loss": 0.5684,
      "step": 104
    },
    {
      "epoch": 0.2545454545454545,
      "grad_norm": 0.059038061648607254,
      "learning_rate": 0.0001902676399026764,
      "loss": 0.5216,
      "step": 105
    },
    {
      "epoch": 0.25696969696969696,
      "grad_norm": 0.06160209700465202,
      "learning_rate": 0.00019017031630170318,
      "loss": 0.5284,
      "step": 106
    },
    {
      "epoch": 0.2593939393939394,
      "grad_norm": 0.05982833728194237,
      "learning_rate": 0.00019007299270072995,
      "loss": 0.5436,
      "step": 107
    },
    {
      "epoch": 0.26181818181818184,
      "grad_norm": 0.08275666832923889,
      "learning_rate": 0.00018997566909975672,
      "loss": 0.5366,
      "step": 108
    },
    {
      "epoch": 0.2642424242424242,
      "grad_norm": 0.06408876925706863,
      "learning_rate": 0.00018987834549878346,
      "loss": 0.5642,
      "step": 109
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.06569265574216843,
      "learning_rate": 0.00018978102189781023,
      "loss": 0.5486,
      "step": 110
    },
    {
      "epoch": 0.2690909090909091,
      "grad_norm": 0.0659552663564682,
      "learning_rate": 0.000189683698296837,
      "loss": 0.5476,
      "step": 111
    },
    {
      "epoch": 0.27151515151515154,
      "grad_norm": 0.06666216254234314,
      "learning_rate": 0.00018958637469586374,
      "loss": 0.5522,
      "step": 112
    },
    {
      "epoch": 0.2739393939393939,
      "grad_norm": 0.064473956823349,
      "learning_rate": 0.0001894890510948905,
      "loss": 0.5607,
      "step": 113
    },
    {
      "epoch": 0.27636363636363637,
      "grad_norm": 0.07233359664678574,
      "learning_rate": 0.00018939172749391728,
      "loss": 0.5706,
      "step": 114
    },
    {
      "epoch": 0.2787878787878788,
      "grad_norm": 0.061200112104415894,
      "learning_rate": 0.00018929440389294403,
      "loss": 0.5442,
      "step": 115
    },
    {
      "epoch": 0.2812121212121212,
      "grad_norm": 0.060941025614738464,
      "learning_rate": 0.0001891970802919708,
      "loss": 0.5378,
      "step": 116
    },
    {
      "epoch": 0.28363636363636363,
      "grad_norm": 0.0607539638876915,
      "learning_rate": 0.00018909975669099757,
      "loss": 0.5365,
      "step": 117
    },
    {
      "epoch": 0.28606060606060607,
      "grad_norm": 0.12834005057811737,
      "learning_rate": 0.00018900243309002434,
      "loss": 0.5524,
      "step": 118
    },
    {
      "epoch": 0.2884848484848485,
      "grad_norm": 0.06871786713600159,
      "learning_rate": 0.0001889051094890511,
      "loss": 0.5603,
      "step": 119
    },
    {
      "epoch": 0.2909090909090909,
      "grad_norm": 0.06357085704803467,
      "learning_rate": 0.00018880778588807785,
      "loss": 0.5376,
      "step": 120
    },
    {
      "epoch": 0.29333333333333333,
      "grad_norm": 0.07983007282018661,
      "learning_rate": 0.00018871046228710462,
      "loss": 0.5754,
      "step": 121
    },
    {
      "epoch": 0.2957575757575758,
      "grad_norm": 0.06719958037137985,
      "learning_rate": 0.0001886131386861314,
      "loss": 0.5762,
      "step": 122
    },
    {
      "epoch": 0.29818181818181816,
      "grad_norm": 0.06584449857473373,
      "learning_rate": 0.00018851581508515816,
      "loss": 0.5525,
      "step": 123
    },
    {
      "epoch": 0.3006060606060606,
      "grad_norm": 0.08049803972244263,
      "learning_rate": 0.00018841849148418493,
      "loss": 0.5523,
      "step": 124
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 0.08848906308412552,
      "learning_rate": 0.00018832116788321167,
      "loss": 0.5374,
      "step": 125
    },
    {
      "epoch": 0.3054545454545455,
      "grad_norm": 0.07101805508136749,
      "learning_rate": 0.00018822384428223844,
      "loss": 0.5503,
      "step": 126
    },
    {
      "epoch": 0.30787878787878786,
      "grad_norm": 0.06706050038337708,
      "learning_rate": 0.00018812652068126521,
      "loss": 0.5544,
      "step": 127
    },
    {
      "epoch": 0.3103030303030303,
      "grad_norm": 0.06253364682197571,
      "learning_rate": 0.00018802919708029198,
      "loss": 0.5825,
      "step": 128
    },
    {
      "epoch": 0.31272727272727274,
      "grad_norm": 0.0666712075471878,
      "learning_rate": 0.00018793187347931876,
      "loss": 0.5505,
      "step": 129
    },
    {
      "epoch": 0.3151515151515151,
      "grad_norm": 0.06335099041461945,
      "learning_rate": 0.0001878345498783455,
      "loss": 0.566,
      "step": 130
    },
    {
      "epoch": 0.31757575757575757,
      "grad_norm": 0.06576841324567795,
      "learning_rate": 0.00018773722627737227,
      "loss": 0.5576,
      "step": 131
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.06052207574248314,
      "learning_rate": 0.00018763990267639904,
      "loss": 0.5496,
      "step": 132
    },
    {
      "epoch": 0.32242424242424245,
      "grad_norm": 0.06990842521190643,
      "learning_rate": 0.0001875425790754258,
      "loss": 0.5787,
      "step": 133
    },
    {
      "epoch": 0.32484848484848483,
      "grad_norm": 0.06944089382886887,
      "learning_rate": 0.00018744525547445258,
      "loss": 0.5823,
      "step": 134
    },
    {
      "epoch": 0.32727272727272727,
      "grad_norm": 0.05838549882173538,
      "learning_rate": 0.00018734793187347932,
      "loss": 0.5645,
      "step": 135
    },
    {
      "epoch": 0.3296969696969697,
      "grad_norm": 0.06813778728246689,
      "learning_rate": 0.0001872506082725061,
      "loss": 0.5829,
      "step": 136
    },
    {
      "epoch": 0.3321212121212121,
      "grad_norm": 0.0651688352227211,
      "learning_rate": 0.00018715328467153286,
      "loss": 0.5696,
      "step": 137
    },
    {
      "epoch": 0.33454545454545453,
      "grad_norm": 0.058600135147571564,
      "learning_rate": 0.00018705596107055963,
      "loss": 0.5472,
      "step": 138
    },
    {
      "epoch": 0.336969696969697,
      "grad_norm": 0.09631790220737457,
      "learning_rate": 0.00018695863746958638,
      "loss": 0.5452,
      "step": 139
    },
    {
      "epoch": 0.3393939393939394,
      "grad_norm": 0.061679765582084656,
      "learning_rate": 0.00018686131386861315,
      "loss": 0.5637,
      "step": 140
    },
    {
      "epoch": 0.3418181818181818,
      "grad_norm": 0.05879385769367218,
      "learning_rate": 0.00018676399026763992,
      "loss": 0.5413,
      "step": 141
    },
    {
      "epoch": 0.34424242424242424,
      "grad_norm": 0.0700845718383789,
      "learning_rate": 0.0001866666666666667,
      "loss": 0.5391,
      "step": 142
    },
    {
      "epoch": 0.3466666666666667,
      "grad_norm": 0.0675090104341507,
      "learning_rate": 0.00018656934306569346,
      "loss": 0.5535,
      "step": 143
    },
    {
      "epoch": 0.3490909090909091,
      "grad_norm": 0.10042846202850342,
      "learning_rate": 0.0001864720194647202,
      "loss": 0.5643,
      "step": 144
    },
    {
      "epoch": 0.3515151515151515,
      "grad_norm": 0.06561391055583954,
      "learning_rate": 0.00018637469586374697,
      "loss": 0.5535,
      "step": 145
    },
    {
      "epoch": 0.35393939393939394,
      "grad_norm": 0.06090841069817543,
      "learning_rate": 0.00018627737226277374,
      "loss": 0.5658,
      "step": 146
    },
    {
      "epoch": 0.3563636363636364,
      "grad_norm": 0.06215941533446312,
      "learning_rate": 0.0001861800486618005,
      "loss": 0.5333,
      "step": 147
    },
    {
      "epoch": 0.35878787878787877,
      "grad_norm": 0.057674869894981384,
      "learning_rate": 0.00018608272506082728,
      "loss": 0.5822,
      "step": 148
    },
    {
      "epoch": 0.3612121212121212,
      "grad_norm": 0.05976865440607071,
      "learning_rate": 0.00018598540145985402,
      "loss": 0.562,
      "step": 149
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.06777815520763397,
      "learning_rate": 0.0001858880778588808,
      "loss": 0.553,
      "step": 150
    },
    {
      "epoch": 0.3660606060606061,
      "grad_norm": 0.0646166056394577,
      "learning_rate": 0.00018579075425790756,
      "loss": 0.5239,
      "step": 151
    },
    {
      "epoch": 0.36848484848484847,
      "grad_norm": 0.12189126014709473,
      "learning_rate": 0.0001856934306569343,
      "loss": 0.5609,
      "step": 152
    },
    {
      "epoch": 0.3709090909090909,
      "grad_norm": 0.06082267314195633,
      "learning_rate": 0.00018559610705596108,
      "loss": 0.5682,
      "step": 153
    },
    {
      "epoch": 0.37333333333333335,
      "grad_norm": 0.07489784806966782,
      "learning_rate": 0.00018549878345498785,
      "loss": 0.5575,
      "step": 154
    },
    {
      "epoch": 0.37575757575757573,
      "grad_norm": 0.06415938585996628,
      "learning_rate": 0.0001854014598540146,
      "loss": 0.5799,
      "step": 155
    },
    {
      "epoch": 0.3781818181818182,
      "grad_norm": 0.0640651062130928,
      "learning_rate": 0.00018530413625304136,
      "loss": 0.5654,
      "step": 156
    },
    {
      "epoch": 0.3806060606060606,
      "grad_norm": 0.06074777990579605,
      "learning_rate": 0.00018520681265206813,
      "loss": 0.5819,
      "step": 157
    },
    {
      "epoch": 0.38303030303030305,
      "grad_norm": 0.060014959424734116,
      "learning_rate": 0.0001851094890510949,
      "loss": 0.5461,
      "step": 158
    },
    {
      "epoch": 0.38545454545454544,
      "grad_norm": 0.06002107262611389,
      "learning_rate": 0.00018501216545012164,
      "loss": 0.5368,
      "step": 159
    },
    {
      "epoch": 0.3878787878787879,
      "grad_norm": 0.061761707067489624,
      "learning_rate": 0.00018491484184914841,
      "loss": 0.5678,
      "step": 160
    },
    {
      "epoch": 0.3903030303030303,
      "grad_norm": 0.06580917537212372,
      "learning_rate": 0.00018481751824817518,
      "loss": 0.5362,
      "step": 161
    },
    {
      "epoch": 0.3927272727272727,
      "grad_norm": 0.06305402517318726,
      "learning_rate": 0.00018472019464720195,
      "loss": 0.566,
      "step": 162
    },
    {
      "epoch": 0.39515151515151514,
      "grad_norm": 0.07035670429468155,
      "learning_rate": 0.00018462287104622873,
      "loss": 0.5765,
      "step": 163
    },
    {
      "epoch": 0.3975757575757576,
      "grad_norm": 0.06285785883665085,
      "learning_rate": 0.00018452554744525547,
      "loss": 0.5454,
      "step": 164
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.06579060107469559,
      "learning_rate": 0.00018442822384428224,
      "loss": 0.5696,
      "step": 165
    },
    {
      "epoch": 0.4024242424242424,
      "grad_norm": 0.06274209171533585,
      "learning_rate": 0.000184330900243309,
      "loss": 0.5406,
      "step": 166
    },
    {
      "epoch": 0.40484848484848485,
      "grad_norm": 0.05804755166172981,
      "learning_rate": 0.00018423357664233578,
      "loss": 0.5294,
      "step": 167
    },
    {
      "epoch": 0.4072727272727273,
      "grad_norm": 0.06430191546678543,
      "learning_rate": 0.00018413625304136255,
      "loss": 0.526,
      "step": 168
    },
    {
      "epoch": 0.40969696969696967,
      "grad_norm": 0.13350482285022736,
      "learning_rate": 0.0001840389294403893,
      "loss": 0.5682,
      "step": 169
    },
    {
      "epoch": 0.4121212121212121,
      "grad_norm": 0.07210890203714371,
      "learning_rate": 0.00018394160583941606,
      "loss": 0.5775,
      "step": 170
    },
    {
      "epoch": 0.41454545454545455,
      "grad_norm": 0.05939320847392082,
      "learning_rate": 0.00018384428223844283,
      "loss": 0.5245,
      "step": 171
    },
    {
      "epoch": 0.416969696969697,
      "grad_norm": 0.06696563214063644,
      "learning_rate": 0.0001837469586374696,
      "loss": 0.5961,
      "step": 172
    },
    {
      "epoch": 0.4193939393939394,
      "grad_norm": 0.05933167412877083,
      "learning_rate": 0.00018364963503649637,
      "loss": 0.5246,
      "step": 173
    },
    {
      "epoch": 0.4218181818181818,
      "grad_norm": 0.08005242049694061,
      "learning_rate": 0.00018355231143552312,
      "loss": 0.5503,
      "step": 174
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 0.06471698731184006,
      "learning_rate": 0.00018345498783454989,
      "loss": 0.5333,
      "step": 175
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 0.05958030745387077,
      "learning_rate": 0.00018335766423357666,
      "loss": 0.5393,
      "step": 176
    },
    {
      "epoch": 0.4290909090909091,
      "grad_norm": 0.05842345580458641,
      "learning_rate": 0.00018326034063260343,
      "loss": 0.5612,
      "step": 177
    },
    {
      "epoch": 0.4315151515151515,
      "grad_norm": 0.0645299032330513,
      "learning_rate": 0.00018316301703163017,
      "loss": 0.5457,
      "step": 178
    },
    {
      "epoch": 0.43393939393939396,
      "grad_norm": 0.06129203736782074,
      "learning_rate": 0.00018306569343065694,
      "loss": 0.5447,
      "step": 179
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 0.0591256208717823,
      "learning_rate": 0.0001829683698296837,
      "loss": 0.5796,
      "step": 180
    },
    {
      "epoch": 0.4387878787878788,
      "grad_norm": 0.06893151998519897,
      "learning_rate": 0.00018287104622871048,
      "loss": 0.5528,
      "step": 181
    },
    {
      "epoch": 0.4412121212121212,
      "grad_norm": 0.06359567493200302,
      "learning_rate": 0.00018277372262773725,
      "loss": 0.5677,
      "step": 182
    },
    {
      "epoch": 0.44363636363636366,
      "grad_norm": 0.059533968567848206,
      "learning_rate": 0.000182676399026764,
      "loss": 0.5554,
      "step": 183
    },
    {
      "epoch": 0.44606060606060605,
      "grad_norm": 0.06985704600811005,
      "learning_rate": 0.00018257907542579076,
      "loss": 0.541,
      "step": 184
    },
    {
      "epoch": 0.4484848484848485,
      "grad_norm": 0.0740571990609169,
      "learning_rate": 0.00018248175182481753,
      "loss": 0.5421,
      "step": 185
    },
    {
      "epoch": 0.4509090909090909,
      "grad_norm": 0.06296324729919434,
      "learning_rate": 0.0001823844282238443,
      "loss": 0.5511,
      "step": 186
    },
    {
      "epoch": 0.4533333333333333,
      "grad_norm": 0.0589432567358017,
      "learning_rate": 0.00018228710462287107,
      "loss": 0.5516,
      "step": 187
    },
    {
      "epoch": 0.45575757575757575,
      "grad_norm": 0.11923418194055557,
      "learning_rate": 0.00018218978102189782,
      "loss": 0.5655,
      "step": 188
    },
    {
      "epoch": 0.4581818181818182,
      "grad_norm": 0.06673496216535568,
      "learning_rate": 0.0001820924574209246,
      "loss": 0.5642,
      "step": 189
    },
    {
      "epoch": 0.46060606060606063,
      "grad_norm": 0.06538072228431702,
      "learning_rate": 0.00018199513381995136,
      "loss": 0.5686,
      "step": 190
    },
    {
      "epoch": 0.463030303030303,
      "grad_norm": 0.06611759960651398,
      "learning_rate": 0.00018189781021897813,
      "loss": 0.5649,
      "step": 191
    },
    {
      "epoch": 0.46545454545454545,
      "grad_norm": 0.06542181223630905,
      "learning_rate": 0.00018180048661800487,
      "loss": 0.5631,
      "step": 192
    },
    {
      "epoch": 0.4678787878787879,
      "grad_norm": 0.06455749273300171,
      "learning_rate": 0.00018170316301703164,
      "loss": 0.5361,
      "step": 193
    },
    {
      "epoch": 0.4703030303030303,
      "grad_norm": 0.0632220059633255,
      "learning_rate": 0.0001816058394160584,
      "loss": 0.5332,
      "step": 194
    },
    {
      "epoch": 0.4727272727272727,
      "grad_norm": 0.06765448302030563,
      "learning_rate": 0.00018150851581508515,
      "loss": 0.5538,
      "step": 195
    },
    {
      "epoch": 0.47515151515151516,
      "grad_norm": 0.0653989240527153,
      "learning_rate": 0.00018141119221411192,
      "loss": 0.5404,
      "step": 196
    },
    {
      "epoch": 0.4775757575757576,
      "grad_norm": 0.0783257856965065,
      "learning_rate": 0.0001813138686131387,
      "loss": 0.5567,
      "step": 197
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.056732699275016785,
      "learning_rate": 0.00018121654501216544,
      "loss": 0.5546,
      "step": 198
    },
    {
      "epoch": 0.4824242424242424,
      "grad_norm": 0.06991420686244965,
      "learning_rate": 0.0001811192214111922,
      "loss": 0.5645,
      "step": 199
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 0.07767068594694138,
      "learning_rate": 0.00018102189781021898,
      "loss": 0.5714,
      "step": 200
    },
    {
      "epoch": 0.48727272727272725,
      "grad_norm": 0.07061710208654404,
      "learning_rate": 0.00018092457420924575,
      "loss": 0.5477,
      "step": 201
    },
    {
      "epoch": 0.4896969696969697,
      "grad_norm": 0.06803636997938156,
      "learning_rate": 0.00018082725060827252,
      "loss": 0.5754,
      "step": 202
    },
    {
      "epoch": 0.4921212121212121,
      "grad_norm": 0.05597437545657158,
      "learning_rate": 0.00018072992700729926,
      "loss": 0.5327,
      "step": 203
    },
    {
      "epoch": 0.49454545454545457,
      "grad_norm": 0.05977711081504822,
      "learning_rate": 0.00018063260340632603,
      "loss": 0.5676,
      "step": 204
    },
    {
      "epoch": 0.49696969696969695,
      "grad_norm": 0.06017453595995903,
      "learning_rate": 0.0001805352798053528,
      "loss": 0.5603,
      "step": 205
    },
    {
      "epoch": 0.4993939393939394,
      "grad_norm": 0.07916443794965744,
      "learning_rate": 0.00018043795620437957,
      "loss": 0.5563,
      "step": 206
    },
    {
      "epoch": 0.5018181818181818,
      "grad_norm": 0.05583438277244568,
      "learning_rate": 0.00018034063260340634,
      "loss": 0.5204,
      "step": 207
    },
    {
      "epoch": 0.5042424242424243,
      "grad_norm": 0.07012349367141724,
      "learning_rate": 0.00018024330900243309,
      "loss": 0.5661,
      "step": 208
    },
    {
      "epoch": 0.5066666666666667,
      "grad_norm": 0.057964831590652466,
      "learning_rate": 0.00018014598540145986,
      "loss": 0.5456,
      "step": 209
    },
    {
      "epoch": 0.509090909090909,
      "grad_norm": 1.3452612161636353,
      "learning_rate": 0.00018004866180048663,
      "loss": 0.5323,
      "step": 210
    },
    {
      "epoch": 0.5115151515151515,
      "grad_norm": 0.06258725374937057,
      "learning_rate": 0.0001799513381995134,
      "loss": 0.5459,
      "step": 211
    },
    {
      "epoch": 0.5139393939393939,
      "grad_norm": 0.06114456430077553,
      "learning_rate": 0.00017985401459854014,
      "loss": 0.5225,
      "step": 212
    },
    {
      "epoch": 0.5163636363636364,
      "grad_norm": 0.06262862682342529,
      "learning_rate": 0.0001797566909975669,
      "loss": 0.5454,
      "step": 213
    },
    {
      "epoch": 0.5187878787878788,
      "grad_norm": 0.09649477154016495,
      "learning_rate": 0.00017965936739659368,
      "loss": 0.546,
      "step": 214
    },
    {
      "epoch": 0.5212121212121212,
      "grad_norm": 0.06361106783151627,
      "learning_rate": 0.00017956204379562045,
      "loss": 0.5355,
      "step": 215
    },
    {
      "epoch": 0.5236363636363637,
      "grad_norm": 0.061119530349969864,
      "learning_rate": 0.00017946472019464722,
      "loss": 0.5451,
      "step": 216
    },
    {
      "epoch": 0.526060606060606,
      "grad_norm": 0.07254000008106232,
      "learning_rate": 0.00017936739659367396,
      "loss": 0.5436,
      "step": 217
    },
    {
      "epoch": 0.5284848484848484,
      "grad_norm": 0.06356175988912582,
      "learning_rate": 0.00017927007299270073,
      "loss": 0.5376,
      "step": 218
    },
    {
      "epoch": 0.5309090909090909,
      "grad_norm": 0.0601746030151844,
      "learning_rate": 0.0001791727493917275,
      "loss": 0.5229,
      "step": 219
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.29285281896591187,
      "learning_rate": 0.00017907542579075427,
      "loss": 0.5543,
      "step": 220
    },
    {
      "epoch": 0.5357575757575758,
      "grad_norm": 0.06783048063516617,
      "learning_rate": 0.00017897810218978104,
      "loss": 0.5287,
      "step": 221
    },
    {
      "epoch": 0.5381818181818182,
      "grad_norm": 0.08351709693670273,
      "learning_rate": 0.0001788807785888078,
      "loss": 0.5862,
      "step": 222
    },
    {
      "epoch": 0.5406060606060606,
      "grad_norm": 0.06248465180397034,
      "learning_rate": 0.00017878345498783456,
      "loss": 0.5584,
      "step": 223
    },
    {
      "epoch": 0.5430303030303031,
      "grad_norm": 0.05912860482931137,
      "learning_rate": 0.00017868613138686133,
      "loss": 0.5431,
      "step": 224
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.05736866220831871,
      "learning_rate": 0.0001785888077858881,
      "loss": 0.5392,
      "step": 225
    },
    {
      "epoch": 0.5478787878787879,
      "grad_norm": 0.0718221366405487,
      "learning_rate": 0.00017849148418491487,
      "loss": 0.5389,
      "step": 226
    },
    {
      "epoch": 0.5503030303030303,
      "grad_norm": 0.07681471109390259,
      "learning_rate": 0.0001783941605839416,
      "loss": 0.5675,
      "step": 227
    },
    {
      "epoch": 0.5527272727272727,
      "grad_norm": 0.37830424308776855,
      "learning_rate": 0.00017829683698296838,
      "loss": 0.545,
      "step": 228
    },
    {
      "epoch": 0.5551515151515152,
      "grad_norm": 0.07504663616418839,
      "learning_rate": 0.00017819951338199515,
      "loss": 0.5473,
      "step": 229
    },
    {
      "epoch": 0.5575757575757576,
      "grad_norm": 2.0385234355926514,
      "learning_rate": 0.00017810218978102192,
      "loss": 0.5668,
      "step": 230
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.0730227455496788,
      "learning_rate": 0.0001780048661800487,
      "loss": 0.5149,
      "step": 231
    },
    {
      "epoch": 0.5624242424242424,
      "grad_norm": 0.07216502726078033,
      "learning_rate": 0.00017790754257907544,
      "loss": 0.5619,
      "step": 232
    },
    {
      "epoch": 0.5648484848484848,
      "grad_norm": 0.21188175678253174,
      "learning_rate": 0.0001778102189781022,
      "loss": 0.522,
      "step": 233
    },
    {
      "epoch": 0.5672727272727273,
      "grad_norm": 0.08797410875558853,
      "learning_rate": 0.00017771289537712898,
      "loss": 0.5552,
      "step": 234
    },
    {
      "epoch": 0.5696969696969697,
      "grad_norm": 0.105152927339077,
      "learning_rate": 0.00017761557177615572,
      "loss": 0.5466,
      "step": 235
    },
    {
      "epoch": 0.5721212121212121,
      "grad_norm": 0.06970223039388657,
      "learning_rate": 0.0001775182481751825,
      "loss": 0.5509,
      "step": 236
    },
    {
      "epoch": 0.5745454545454546,
      "grad_norm": 0.08145711570978165,
      "learning_rate": 0.00017742092457420926,
      "loss": 0.5635,
      "step": 237
    },
    {
      "epoch": 0.576969696969697,
      "grad_norm": 0.06969096511602402,
      "learning_rate": 0.000177323600973236,
      "loss": 0.5763,
      "step": 238
    },
    {
      "epoch": 0.5793939393939394,
      "grad_norm": 1.7367609739303589,
      "learning_rate": 0.00017722627737226277,
      "loss": 0.5406,
      "step": 239
    },
    {
      "epoch": 0.5818181818181818,
      "grad_norm": 0.07154524326324463,
      "learning_rate": 0.00017712895377128954,
      "loss": 0.5716,
      "step": 240
    },
    {
      "epoch": 0.5842424242424242,
      "grad_norm": 0.0744590312242508,
      "learning_rate": 0.0001770316301703163,
      "loss": 0.5313,
      "step": 241
    },
    {
      "epoch": 0.5866666666666667,
      "grad_norm": 0.07628407329320908,
      "learning_rate": 0.00017693430656934306,
      "loss": 0.541,
      "step": 242
    },
    {
      "epoch": 0.5890909090909091,
      "grad_norm": 0.06648588180541992,
      "learning_rate": 0.00017683698296836983,
      "loss": 0.5349,
      "step": 243
    },
    {
      "epoch": 0.5915151515151515,
      "grad_norm": 0.25192779302597046,
      "learning_rate": 0.0001767396593673966,
      "loss": 0.5606,
      "step": 244
    },
    {
      "epoch": 0.593939393939394,
      "grad_norm": 0.0673336535692215,
      "learning_rate": 0.00017664233576642337,
      "loss": 0.5719,
      "step": 245
    },
    {
      "epoch": 0.5963636363636363,
      "grad_norm": 0.06543178111314774,
      "learning_rate": 0.00017654501216545014,
      "loss": 0.5487,
      "step": 246
    },
    {
      "epoch": 0.5987878787878788,
      "grad_norm": 0.0843130424618721,
      "learning_rate": 0.00017644768856447688,
      "loss": 0.5391,
      "step": 247
    },
    {
      "epoch": 0.6012121212121212,
      "grad_norm": 0.06382573395967484,
      "learning_rate": 0.00017635036496350365,
      "loss": 0.5538,
      "step": 248
    },
    {
      "epoch": 0.6036363636363636,
      "grad_norm": 0.06857671588659286,
      "learning_rate": 0.00017625304136253042,
      "loss": 0.5707,
      "step": 249
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.0810059905052185,
      "learning_rate": 0.0001761557177615572,
      "loss": 0.5681,
      "step": 250
    },
    {
      "epoch": 0.6084848484848485,
      "grad_norm": 0.07038403302431107,
      "learning_rate": 0.00017605839416058393,
      "loss": 0.5754,
      "step": 251
    },
    {
      "epoch": 0.610909090909091,
      "grad_norm": 0.08081474900245667,
      "learning_rate": 0.0001759610705596107,
      "loss": 0.582,
      "step": 252
    },
    {
      "epoch": 0.6133333333333333,
      "grad_norm": 0.0683026984333992,
      "learning_rate": 0.00017586374695863747,
      "loss": 0.5282,
      "step": 253
    },
    {
      "epoch": 0.6157575757575757,
      "grad_norm": 0.07140510529279709,
      "learning_rate": 0.00017576642335766424,
      "loss": 0.546,
      "step": 254
    },
    {
      "epoch": 0.6181818181818182,
      "grad_norm": 0.12273766845464706,
      "learning_rate": 0.00017566909975669101,
      "loss": 0.5553,
      "step": 255
    },
    {
      "epoch": 0.6206060606060606,
      "grad_norm": 0.06285770982503891,
      "learning_rate": 0.00017557177615571776,
      "loss": 0.5526,
      "step": 256
    },
    {
      "epoch": 0.623030303030303,
      "grad_norm": 0.07583372294902802,
      "learning_rate": 0.00017547445255474453,
      "loss": 0.5283,
      "step": 257
    },
    {
      "epoch": 0.6254545454545455,
      "grad_norm": 0.06511462479829788,
      "learning_rate": 0.0001753771289537713,
      "loss": 0.5641,
      "step": 258
    },
    {
      "epoch": 0.6278787878787879,
      "grad_norm": 0.059908416122198105,
      "learning_rate": 0.00017527980535279807,
      "loss": 0.5198,
      "step": 259
    },
    {
      "epoch": 0.6303030303030303,
      "grad_norm": 0.10349190980195999,
      "learning_rate": 0.00017518248175182484,
      "loss": 0.5277,
      "step": 260
    },
    {
      "epoch": 0.6327272727272727,
      "grad_norm": 0.069496750831604,
      "learning_rate": 0.00017508515815085158,
      "loss": 0.5344,
      "step": 261
    },
    {
      "epoch": 0.6351515151515151,
      "grad_norm": 0.09573681652545929,
      "learning_rate": 0.00017498783454987835,
      "loss": 0.5292,
      "step": 262
    },
    {
      "epoch": 0.6375757575757576,
      "grad_norm": 0.06820680946111679,
      "learning_rate": 0.00017489051094890512,
      "loss": 0.5712,
      "step": 263
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.1631213277578354,
      "learning_rate": 0.0001747931873479319,
      "loss": 0.5718,
      "step": 264
    },
    {
      "epoch": 0.6424242424242425,
      "grad_norm": 0.19588926434516907,
      "learning_rate": 0.00017469586374695866,
      "loss": 0.5542,
      "step": 265
    },
    {
      "epoch": 0.6448484848484849,
      "grad_norm": 0.0614098384976387,
      "learning_rate": 0.0001745985401459854,
      "loss": 0.5586,
      "step": 266
    },
    {
      "epoch": 0.6472727272727272,
      "grad_norm": 0.05868373438715935,
      "learning_rate": 0.00017450121654501218,
      "loss": 0.5424,
      "step": 267
    },
    {
      "epoch": 0.6496969696969697,
      "grad_norm": 0.10498708486557007,
      "learning_rate": 0.00017440389294403895,
      "loss": 0.5423,
      "step": 268
    },
    {
      "epoch": 0.6521212121212121,
      "grad_norm": 0.06701310724020004,
      "learning_rate": 0.00017430656934306572,
      "loss": 0.5347,
      "step": 269
    },
    {
      "epoch": 0.6545454545454545,
      "grad_norm": 0.07281468063592911,
      "learning_rate": 0.00017420924574209249,
      "loss": 0.5674,
      "step": 270
    },
    {
      "epoch": 0.656969696969697,
      "grad_norm": 0.06737703084945679,
      "learning_rate": 0.00017411192214111923,
      "loss": 0.6011,
      "step": 271
    },
    {
      "epoch": 0.6593939393939394,
      "grad_norm": 0.0630665197968483,
      "learning_rate": 0.000174014598540146,
      "loss": 0.5546,
      "step": 272
    },
    {
      "epoch": 0.6618181818181819,
      "grad_norm": 0.0635378435254097,
      "learning_rate": 0.00017391727493917277,
      "loss": 0.5602,
      "step": 273
    },
    {
      "epoch": 0.6642424242424242,
      "grad_norm": 0.24494418501853943,
      "learning_rate": 0.00017381995133819954,
      "loss": 0.5037,
      "step": 274
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.0832589864730835,
      "learning_rate": 0.00017372262773722628,
      "loss": 0.5581,
      "step": 275
    },
    {
      "epoch": 0.6690909090909091,
      "grad_norm": 0.061255015432834625,
      "learning_rate": 0.00017362530413625305,
      "loss": 0.5289,
      "step": 276
    },
    {
      "epoch": 0.6715151515151515,
      "grad_norm": 0.062059953808784485,
      "learning_rate": 0.00017352798053527982,
      "loss": 0.5532,
      "step": 277
    },
    {
      "epoch": 0.673939393939394,
      "grad_norm": 0.08214735239744186,
      "learning_rate": 0.00017343065693430657,
      "loss": 0.5454,
      "step": 278
    },
    {
      "epoch": 0.6763636363636364,
      "grad_norm": 0.07996552437543869,
      "learning_rate": 0.00017333333333333334,
      "loss": 0.5572,
      "step": 279
    },
    {
      "epoch": 0.6787878787878788,
      "grad_norm": 0.06204145774245262,
      "learning_rate": 0.0001732360097323601,
      "loss": 0.558,
      "step": 280
    },
    {
      "epoch": 0.6812121212121212,
      "grad_norm": 0.05966441333293915,
      "learning_rate": 0.00017313868613138685,
      "loss": 0.5419,
      "step": 281
    },
    {
      "epoch": 0.6836363636363636,
      "grad_norm": 0.07609891891479492,
      "learning_rate": 0.00017304136253041362,
      "loss": 0.5771,
      "step": 282
    },
    {
      "epoch": 0.686060606060606,
      "grad_norm": 0.06977101415395737,
      "learning_rate": 0.0001729440389294404,
      "loss": 0.5614,
      "step": 283
    },
    {
      "epoch": 0.6884848484848485,
      "grad_norm": 0.08119616657495499,
      "learning_rate": 0.00017284671532846716,
      "loss": 0.5591,
      "step": 284
    },
    {
      "epoch": 0.6909090909090909,
      "grad_norm": 0.05884050577878952,
      "learning_rate": 0.00017274939172749393,
      "loss": 0.5469,
      "step": 285
    },
    {
      "epoch": 0.6933333333333334,
      "grad_norm": 0.07192666083574295,
      "learning_rate": 0.00017265206812652067,
      "loss": 0.5291,
      "step": 286
    },
    {
      "epoch": 0.6957575757575758,
      "grad_norm": 0.06349042057991028,
      "learning_rate": 0.00017255474452554744,
      "loss": 0.5622,
      "step": 287
    },
    {
      "epoch": 0.6981818181818182,
      "grad_norm": 0.06524200737476349,
      "learning_rate": 0.00017245742092457421,
      "loss": 0.5675,
      "step": 288
    },
    {
      "epoch": 0.7006060606060606,
      "grad_norm": 0.07002637535333633,
      "learning_rate": 0.00017236009732360098,
      "loss": 0.5836,
      "step": 289
    },
    {
      "epoch": 0.703030303030303,
      "grad_norm": 0.06424380838871002,
      "learning_rate": 0.00017226277372262773,
      "loss": 0.5567,
      "step": 290
    },
    {
      "epoch": 0.7054545454545454,
      "grad_norm": 0.06327451020479202,
      "learning_rate": 0.0001721654501216545,
      "loss": 0.5252,
      "step": 291
    },
    {
      "epoch": 0.7078787878787879,
      "grad_norm": 0.11821381747722626,
      "learning_rate": 0.00017206812652068127,
      "loss": 0.5473,
      "step": 292
    },
    {
      "epoch": 0.7103030303030303,
      "grad_norm": 0.05885179713368416,
      "learning_rate": 0.00017197080291970804,
      "loss": 0.5574,
      "step": 293
    },
    {
      "epoch": 0.7127272727272728,
      "grad_norm": 0.07020985335111618,
      "learning_rate": 0.0001718734793187348,
      "loss": 0.5574,
      "step": 294
    },
    {
      "epoch": 0.7151515151515152,
      "grad_norm": 0.06301289051771164,
      "learning_rate": 0.00017177615571776155,
      "loss": 0.5539,
      "step": 295
    },
    {
      "epoch": 0.7175757575757575,
      "grad_norm": 0.06687553972005844,
      "learning_rate": 0.00017167883211678832,
      "loss": 0.5413,
      "step": 296
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.0593469999730587,
      "learning_rate": 0.0001715815085158151,
      "loss": 0.5388,
      "step": 297
    },
    {
      "epoch": 0.7224242424242424,
      "grad_norm": 0.06330721080303192,
      "learning_rate": 0.00017148418491484186,
      "loss": 0.5322,
      "step": 298
    },
    {
      "epoch": 0.7248484848484849,
      "grad_norm": 0.06611055880784988,
      "learning_rate": 0.00017138686131386863,
      "loss": 0.5429,
      "step": 299
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.06124502792954445,
      "learning_rate": 0.00017128953771289537,
      "loss": 0.5481,
      "step": 300
    },
    {
      "epoch": 0.7296969696969697,
      "grad_norm": 0.060752421617507935,
      "learning_rate": 0.00017119221411192215,
      "loss": 0.5243,
      "step": 301
    },
    {
      "epoch": 0.7321212121212122,
      "grad_norm": 0.0700276643037796,
      "learning_rate": 0.00017109489051094892,
      "loss": 0.5406,
      "step": 302
    },
    {
      "epoch": 0.7345454545454545,
      "grad_norm": 0.0923948884010315,
      "learning_rate": 0.00017099756690997569,
      "loss": 0.552,
      "step": 303
    },
    {
      "epoch": 0.7369696969696969,
      "grad_norm": 0.059077825397253036,
      "learning_rate": 0.00017090024330900246,
      "loss": 0.5465,
      "step": 304
    },
    {
      "epoch": 0.7393939393939394,
      "grad_norm": 16.5856990814209,
      "learning_rate": 0.0001708029197080292,
      "loss": 0.5525,
      "step": 305
    },
    {
      "epoch": 0.7418181818181818,
      "grad_norm": 0.9094518423080444,
      "learning_rate": 0.00017070559610705597,
      "loss": 0.5344,
      "step": 306
    },
    {
      "epoch": 0.7442424242424243,
      "grad_norm": 0.09564822167158127,
      "learning_rate": 0.00017060827250608274,
      "loss": 0.5459,
      "step": 307
    },
    {
      "epoch": 0.7466666666666667,
      "grad_norm": 0.06621440500020981,
      "learning_rate": 0.0001705109489051095,
      "loss": 0.5614,
      "step": 308
    },
    {
      "epoch": 0.7490909090909091,
      "grad_norm": 0.11044643819332123,
      "learning_rate": 0.00017041362530413628,
      "loss": 0.5778,
      "step": 309
    },
    {
      "epoch": 0.7515151515151515,
      "grad_norm": 0.39716076850891113,
      "learning_rate": 0.00017031630170316302,
      "loss": 0.5552,
      "step": 310
    },
    {
      "epoch": 0.7539393939393939,
      "grad_norm": 0.9215524792671204,
      "learning_rate": 0.0001702189781021898,
      "loss": 0.5514,
      "step": 311
    },
    {
      "epoch": 0.7563636363636363,
      "grad_norm": 0.07326694577932358,
      "learning_rate": 0.00017012165450121656,
      "loss": 0.5381,
      "step": 312
    },
    {
      "epoch": 0.7587878787878788,
      "grad_norm": 0.08419661968946457,
      "learning_rate": 0.00017002433090024333,
      "loss": 0.5415,
      "step": 313
    },
    {
      "epoch": 0.7612121212121212,
      "grad_norm": 0.22310017049312592,
      "learning_rate": 0.0001699270072992701,
      "loss": 0.528,
      "step": 314
    },
    {
      "epoch": 0.7636363636363637,
      "grad_norm": 0.09572742879390717,
      "learning_rate": 0.00016982968369829685,
      "loss": 0.5342,
      "step": 315
    },
    {
      "epoch": 0.7660606060606061,
      "grad_norm": 0.19657564163208008,
      "learning_rate": 0.00016973236009732362,
      "loss": 0.5407,
      "step": 316
    },
    {
      "epoch": 0.7684848484848484,
      "grad_norm": 0.09534162282943726,
      "learning_rate": 0.0001696350364963504,
      "loss": 0.5701,
      "step": 317
    },
    {
      "epoch": 0.7709090909090909,
      "grad_norm": 0.0713532343506813,
      "learning_rate": 0.00016953771289537713,
      "loss": 0.5313,
      "step": 318
    },
    {
      "epoch": 0.7733333333333333,
      "grad_norm": 0.07661478221416473,
      "learning_rate": 0.0001694403892944039,
      "loss": 0.5667,
      "step": 319
    },
    {
      "epoch": 0.7757575757575758,
      "grad_norm": 0.08309673517942429,
      "learning_rate": 0.00016934306569343067,
      "loss": 0.5574,
      "step": 320
    },
    {
      "epoch": 0.7781818181818182,
      "grad_norm": 0.06612791121006012,
      "learning_rate": 0.0001692457420924574,
      "loss": 0.577,
      "step": 321
    },
    {
      "epoch": 0.7806060606060606,
      "grad_norm": 0.08840884268283844,
      "learning_rate": 0.00016914841849148418,
      "loss": 0.5453,
      "step": 322
    },
    {
      "epoch": 0.7830303030303031,
      "grad_norm": 0.08443542569875717,
      "learning_rate": 0.00016905109489051095,
      "loss": 0.5847,
      "step": 323
    },
    {
      "epoch": 0.7854545454545454,
      "grad_norm": 0.14692683517932892,
      "learning_rate": 0.0001689537712895377,
      "loss": 0.5495,
      "step": 324
    },
    {
      "epoch": 0.7878787878787878,
      "grad_norm": 0.1230396255850792,
      "learning_rate": 0.00016885644768856447,
      "loss": 0.5131,
      "step": 325
    },
    {
      "epoch": 0.7903030303030303,
      "grad_norm": 0.060949210077524185,
      "learning_rate": 0.00016875912408759124,
      "loss": 0.5389,
      "step": 326
    },
    {
      "epoch": 0.7927272727272727,
      "grad_norm": 0.06270138919353485,
      "learning_rate": 0.000168661800486618,
      "loss": 0.5574,
      "step": 327
    },
    {
      "epoch": 0.7951515151515152,
      "grad_norm": 0.08615492284297943,
      "learning_rate": 0.00016856447688564478,
      "loss": 0.5307,
      "step": 328
    },
    {
      "epoch": 0.7975757575757576,
      "grad_norm": 0.09964334964752197,
      "learning_rate": 0.00016846715328467152,
      "loss": 0.5778,
      "step": 329
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.06368327140808105,
      "learning_rate": 0.0001683698296836983,
      "loss": 0.5605,
      "step": 330
    },
    {
      "epoch": 0.8024242424242424,
      "grad_norm": 0.21477310359477997,
      "learning_rate": 0.00016827250608272506,
      "loss": 0.5156,
      "step": 331
    },
    {
      "epoch": 0.8048484848484848,
      "grad_norm": 0.06147007271647453,
      "learning_rate": 0.00016817518248175183,
      "loss": 0.5547,
      "step": 332
    },
    {
      "epoch": 0.8072727272727273,
      "grad_norm": 0.06428639590740204,
      "learning_rate": 0.0001680778588807786,
      "loss": 0.5672,
      "step": 333
    },
    {
      "epoch": 0.8096969696969697,
      "grad_norm": 0.08526673913002014,
      "learning_rate": 0.00016798053527980534,
      "loss": 0.5543,
      "step": 334
    },
    {
      "epoch": 0.8121212121212121,
      "grad_norm": 0.06326498091220856,
      "learning_rate": 0.00016788321167883211,
      "loss": 0.5277,
      "step": 335
    },
    {
      "epoch": 0.8145454545454546,
      "grad_norm": 0.07078804820775986,
      "learning_rate": 0.00016778588807785889,
      "loss": 0.5533,
      "step": 336
    },
    {
      "epoch": 0.816969696969697,
      "grad_norm": 0.06639284640550613,
      "learning_rate": 0.00016768856447688566,
      "loss": 0.5511,
      "step": 337
    },
    {
      "epoch": 0.8193939393939393,
      "grad_norm": 0.06346958875656128,
      "learning_rate": 0.00016759124087591243,
      "loss": 0.5338,
      "step": 338
    },
    {
      "epoch": 0.8218181818181818,
      "grad_norm": 0.12766961753368378,
      "learning_rate": 0.00016749391727493917,
      "loss": 0.5598,
      "step": 339
    },
    {
      "epoch": 0.8242424242424242,
      "grad_norm": 0.06857267767190933,
      "learning_rate": 0.00016739659367396594,
      "loss": 0.5511,
      "step": 340
    },
    {
      "epoch": 0.8266666666666667,
      "grad_norm": 0.06484483182430267,
      "learning_rate": 0.0001672992700729927,
      "loss": 0.5483,
      "step": 341
    },
    {
      "epoch": 0.8290909090909091,
      "grad_norm": 0.277243047952652,
      "learning_rate": 0.00016720194647201948,
      "loss": 0.5331,
      "step": 342
    },
    {
      "epoch": 0.8315151515151515,
      "grad_norm": 0.07482493668794632,
      "learning_rate": 0.00016710462287104625,
      "loss": 0.5218,
      "step": 343
    },
    {
      "epoch": 0.833939393939394,
      "grad_norm": 0.1206628829240799,
      "learning_rate": 0.000167007299270073,
      "loss": 0.5884,
      "step": 344
    },
    {
      "epoch": 0.8363636363636363,
      "grad_norm": 0.06652140617370605,
      "learning_rate": 0.00016690997566909976,
      "loss": 0.5488,
      "step": 345
    },
    {
      "epoch": 0.8387878787878787,
      "grad_norm": 0.06260206550359726,
      "learning_rate": 0.00016681265206812653,
      "loss": 0.5402,
      "step": 346
    },
    {
      "epoch": 0.8412121212121212,
      "grad_norm": 0.07941880822181702,
      "learning_rate": 0.0001667153284671533,
      "loss": 0.5291,
      "step": 347
    },
    {
      "epoch": 0.8436363636363636,
      "grad_norm": 0.07369414716959,
      "learning_rate": 0.00016661800486618007,
      "loss": 0.5515,
      "step": 348
    },
    {
      "epoch": 0.8460606060606061,
      "grad_norm": 0.10566204786300659,
      "learning_rate": 0.00016652068126520682,
      "loss": 0.5576,
      "step": 349
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 0.07749351859092712,
      "learning_rate": 0.0001664233576642336,
      "loss": 0.5616,
      "step": 350
    },
    {
      "epoch": 0.850909090909091,
      "grad_norm": 0.06561629474163055,
      "learning_rate": 0.00016632603406326036,
      "loss": 0.5736,
      "step": 351
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 0.06700663268566132,
      "learning_rate": 0.00016622871046228713,
      "loss": 0.5177,
      "step": 352
    },
    {
      "epoch": 0.8557575757575757,
      "grad_norm": 0.06279561668634415,
      "learning_rate": 0.0001661313868613139,
      "loss": 0.5511,
      "step": 353
    },
    {
      "epoch": 0.8581818181818182,
      "grad_norm": 0.06577979773283005,
      "learning_rate": 0.00016603406326034064,
      "loss": 0.5752,
      "step": 354
    },
    {
      "epoch": 0.8606060606060606,
      "grad_norm": 0.09091326594352722,
      "learning_rate": 0.0001659367396593674,
      "loss": 0.5409,
      "step": 355
    },
    {
      "epoch": 0.863030303030303,
      "grad_norm": 0.06229273974895477,
      "learning_rate": 0.00016583941605839418,
      "loss": 0.5574,
      "step": 356
    },
    {
      "epoch": 0.8654545454545455,
      "grad_norm": 0.06422200798988342,
      "learning_rate": 0.00016574209245742095,
      "loss": 0.5225,
      "step": 357
    },
    {
      "epoch": 0.8678787878787879,
      "grad_norm": 0.07569282501935959,
      "learning_rate": 0.0001656447688564477,
      "loss": 0.5601,
      "step": 358
    },
    {
      "epoch": 0.8703030303030304,
      "grad_norm": 0.06488022953271866,
      "learning_rate": 0.00016554744525547446,
      "loss": 0.5663,
      "step": 359
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": 0.061794087290763855,
      "learning_rate": 0.00016545012165450123,
      "loss": 0.5597,
      "step": 360
    },
    {
      "epoch": 0.8751515151515151,
      "grad_norm": 0.06778302788734436,
      "learning_rate": 0.00016535279805352798,
      "loss": 0.5606,
      "step": 361
    },
    {
      "epoch": 0.8775757575757576,
      "grad_norm": 0.07145091891288757,
      "learning_rate": 0.00016525547445255475,
      "loss": 0.5825,
      "step": 362
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.06406552344560623,
      "learning_rate": 0.00016515815085158152,
      "loss": 0.5285,
      "step": 363
    },
    {
      "epoch": 0.8824242424242424,
      "grad_norm": 0.062254372984170914,
      "learning_rate": 0.00016506082725060826,
      "loss": 0.5267,
      "step": 364
    },
    {
      "epoch": 0.8848484848484849,
      "grad_norm": 0.0661516785621643,
      "learning_rate": 0.00016496350364963503,
      "loss": 0.5378,
      "step": 365
    },
    {
      "epoch": 0.8872727272727273,
      "grad_norm": 0.18471062183380127,
      "learning_rate": 0.0001648661800486618,
      "loss": 0.5307,
      "step": 366
    },
    {
      "epoch": 0.8896969696969697,
      "grad_norm": 0.07140319049358368,
      "learning_rate": 0.00016476885644768857,
      "loss": 0.5384,
      "step": 367
    },
    {
      "epoch": 0.8921212121212121,
      "grad_norm": 0.06179990619421005,
      "learning_rate": 0.00016467153284671531,
      "loss": 0.5546,
      "step": 368
    },
    {
      "epoch": 0.8945454545454545,
      "grad_norm": 0.08868462592363358,
      "learning_rate": 0.00016457420924574208,
      "loss": 0.5574,
      "step": 369
    },
    {
      "epoch": 0.896969696969697,
      "grad_norm": 0.0605100579559803,
      "learning_rate": 0.00016447688564476886,
      "loss": 0.5378,
      "step": 370
    },
    {
      "epoch": 0.8993939393939394,
      "grad_norm": 0.07448717206716537,
      "learning_rate": 0.00016437956204379563,
      "loss": 0.5226,
      "step": 371
    },
    {
      "epoch": 0.9018181818181819,
      "grad_norm": 0.058721281588077545,
      "learning_rate": 0.0001642822384428224,
      "loss": 0.5227,
      "step": 372
    },
    {
      "epoch": 0.9042424242424243,
      "grad_norm": 0.10651890933513641,
      "learning_rate": 0.00016418491484184914,
      "loss": 0.5495,
      "step": 373
    },
    {
      "epoch": 0.9066666666666666,
      "grad_norm": 0.06286682188510895,
      "learning_rate": 0.0001640875912408759,
      "loss": 0.5556,
      "step": 374
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.061558134853839874,
      "learning_rate": 0.00016399026763990268,
      "loss": 0.5599,
      "step": 375
    },
    {
      "epoch": 0.9115151515151515,
      "grad_norm": 0.0807129442691803,
      "learning_rate": 0.00016389294403892945,
      "loss": 0.5607,
      "step": 376
    },
    {
      "epoch": 0.9139393939393939,
      "grad_norm": 0.1463339477777481,
      "learning_rate": 0.00016379562043795622,
      "loss": 0.5379,
      "step": 377
    },
    {
      "epoch": 0.9163636363636364,
      "grad_norm": 0.06681551784276962,
      "learning_rate": 0.00016369829683698296,
      "loss": 0.5821,
      "step": 378
    },
    {
      "epoch": 0.9187878787878788,
      "grad_norm": 0.0629209652543068,
      "learning_rate": 0.00016360097323600973,
      "loss": 0.5408,
      "step": 379
    },
    {
      "epoch": 0.9212121212121213,
      "grad_norm": 0.08325511962175369,
      "learning_rate": 0.0001635036496350365,
      "loss": 0.5447,
      "step": 380
    },
    {
      "epoch": 0.9236363636363636,
      "grad_norm": 0.059034720063209534,
      "learning_rate": 0.00016340632603406327,
      "loss": 0.5323,
      "step": 381
    },
    {
      "epoch": 0.926060606060606,
      "grad_norm": 0.38955235481262207,
      "learning_rate": 0.00016330900243309004,
      "loss": 0.521,
      "step": 382
    },
    {
      "epoch": 0.9284848484848485,
      "grad_norm": 0.13808448612689972,
      "learning_rate": 0.00016321167883211679,
      "loss": 0.5534,
      "step": 383
    },
    {
      "epoch": 0.9309090909090909,
      "grad_norm": 0.05884072557091713,
      "learning_rate": 0.00016311435523114356,
      "loss": 0.5402,
      "step": 384
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 0.13356482982635498,
      "learning_rate": 0.00016301703163017033,
      "loss": 0.5691,
      "step": 385
    },
    {
      "epoch": 0.9357575757575758,
      "grad_norm": 0.09560886770486832,
      "learning_rate": 0.0001629197080291971,
      "loss": 0.5465,
      "step": 386
    },
    {
      "epoch": 0.9381818181818182,
      "grad_norm": 0.15289190411567688,
      "learning_rate": 0.00016282238442822387,
      "loss": 0.5107,
      "step": 387
    },
    {
      "epoch": 0.9406060606060606,
      "grad_norm": 0.07369023561477661,
      "learning_rate": 0.0001627250608272506,
      "loss": 0.5357,
      "step": 388
    },
    {
      "epoch": 0.943030303030303,
      "grad_norm": 0.06464044004678726,
      "learning_rate": 0.00016262773722627738,
      "loss": 0.5615,
      "step": 389
    },
    {
      "epoch": 0.9454545454545454,
      "grad_norm": 0.07892990112304688,
      "learning_rate": 0.00016253041362530415,
      "loss": 0.5118,
      "step": 390
    },
    {
      "epoch": 0.9478787878787879,
      "grad_norm": 1.0883806943893433,
      "learning_rate": 0.00016243309002433092,
      "loss": 0.5373,
      "step": 391
    },
    {
      "epoch": 0.9503030303030303,
      "grad_norm": 0.2524948716163635,
      "learning_rate": 0.0001623357664233577,
      "loss": 0.5254,
      "step": 392
    },
    {
      "epoch": 0.9527272727272728,
      "grad_norm": 0.0685998871922493,
      "learning_rate": 0.00016223844282238443,
      "loss": 0.5754,
      "step": 393
    },
    {
      "epoch": 0.9551515151515152,
      "grad_norm": 0.1674545258283615,
      "learning_rate": 0.0001621411192214112,
      "loss": 0.5356,
      "step": 394
    },
    {
      "epoch": 0.9575757575757575,
      "grad_norm": 0.06556844711303711,
      "learning_rate": 0.00016204379562043797,
      "loss": 0.5238,
      "step": 395
    },
    {
      "epoch": 0.96,
      "grad_norm": 2.013521909713745,
      "learning_rate": 0.00016194647201946474,
      "loss": 0.558,
      "step": 396
    },
    {
      "epoch": 0.9624242424242424,
      "grad_norm": 0.060163550078868866,
      "learning_rate": 0.00016184914841849151,
      "loss": 0.5225,
      "step": 397
    },
    {
      "epoch": 0.9648484848484848,
      "grad_norm": 0.08271557092666626,
      "learning_rate": 0.00016175182481751826,
      "loss": 0.5526,
      "step": 398
    },
    {
      "epoch": 0.9672727272727273,
      "grad_norm": 0.07372593134641647,
      "learning_rate": 0.00016165450121654503,
      "loss": 0.5869,
      "step": 399
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 0.06488582491874695,
      "learning_rate": 0.0001615571776155718,
      "loss": 0.5643,
      "step": 400
    },
    {
      "epoch": 0.9721212121212122,
      "grad_norm": 0.06240461394190788,
      "learning_rate": 0.00016145985401459854,
      "loss": 0.5608,
      "step": 401
    },
    {
      "epoch": 0.9745454545454545,
      "grad_norm": 0.10943777114152908,
      "learning_rate": 0.0001613625304136253,
      "loss": 0.5465,
      "step": 402
    },
    {
      "epoch": 0.9769696969696969,
      "grad_norm": 0.0842636451125145,
      "learning_rate": 0.00016126520681265208,
      "loss": 0.5564,
      "step": 403
    },
    {
      "epoch": 0.9793939393939394,
      "grad_norm": 0.0634654089808464,
      "learning_rate": 0.00016116788321167882,
      "loss": 0.5632,
      "step": 404
    },
    {
      "epoch": 0.9818181818181818,
      "grad_norm": 0.07495876401662827,
      "learning_rate": 0.0001610705596107056,
      "loss": 0.5606,
      "step": 405
    },
    {
      "epoch": 0.9842424242424243,
      "grad_norm": 0.07579754292964935,
      "learning_rate": 0.00016097323600973237,
      "loss": 0.5116,
      "step": 406
    },
    {
      "epoch": 0.9866666666666667,
      "grad_norm": 0.07818548381328583,
      "learning_rate": 0.0001608759124087591,
      "loss": 0.5678,
      "step": 407
    },
    {
      "epoch": 0.9890909090909091,
      "grad_norm": 0.07886462658643723,
      "learning_rate": 0.00016077858880778588,
      "loss": 0.5591,
      "step": 408
    },
    {
      "epoch": 0.9915151515151515,
      "grad_norm": 0.06973772495985031,
      "learning_rate": 0.00016068126520681265,
      "loss": 0.567,
      "step": 409
    },
    {
      "epoch": 0.9939393939393939,
      "grad_norm": 0.06554748117923737,
      "learning_rate": 0.00016058394160583942,
      "loss": 0.5487,
      "step": 410
    },
    {
      "epoch": 0.9963636363636363,
      "grad_norm": 0.08189699798822403,
      "learning_rate": 0.0001604866180048662,
      "loss": 0.5647,
      "step": 411
    },
    {
      "epoch": 0.9987878787878788,
      "grad_norm": 0.08697541058063507,
      "learning_rate": 0.00016038929440389293,
      "loss": 0.539,
      "step": 412
    },
    {
      "epoch": 1.0012121212121212,
      "grad_norm": 0.11948265880346298,
      "learning_rate": 0.0001602919708029197,
      "loss": 0.5451,
      "step": 413
    },
    {
      "epoch": 1.0036363636363637,
      "grad_norm": 0.07803041487932205,
      "learning_rate": 0.00016019464720194647,
      "loss": 0.51,
      "step": 414
    },
    {
      "epoch": 1.006060606060606,
      "grad_norm": 0.07906968146562576,
      "learning_rate": 0.00016009732360097324,
      "loss": 0.5448,
      "step": 415
    },
    {
      "epoch": 1.0084848484848485,
      "grad_norm": 0.23532415926456451,
      "learning_rate": 0.00016,
      "loss": 0.5389,
      "step": 416
    },
    {
      "epoch": 1.010909090909091,
      "grad_norm": 0.0702560618519783,
      "learning_rate": 0.00015990267639902676,
      "loss": 0.5137,
      "step": 417
    },
    {
      "epoch": 1.0133333333333334,
      "grad_norm": 0.09237232804298401,
      "learning_rate": 0.00015980535279805353,
      "loss": 0.4929,
      "step": 418
    },
    {
      "epoch": 1.0157575757575759,
      "grad_norm": 0.22942174971103668,
      "learning_rate": 0.0001597080291970803,
      "loss": 0.5067,
      "step": 419
    },
    {
      "epoch": 1.018181818181818,
      "grad_norm": 0.07129258662462234,
      "learning_rate": 0.00015961070559610707,
      "loss": 0.5337,
      "step": 420
    },
    {
      "epoch": 1.0206060606060605,
      "grad_norm": 0.09399973601102829,
      "learning_rate": 0.00015951338199513384,
      "loss": 0.545,
      "step": 421
    },
    {
      "epoch": 1.023030303030303,
      "grad_norm": 0.11831745505332947,
      "learning_rate": 0.00015941605839416058,
      "loss": 0.5214,
      "step": 422
    },
    {
      "epoch": 1.0254545454545454,
      "grad_norm": 0.2561107277870178,
      "learning_rate": 0.00015931873479318735,
      "loss": 0.5242,
      "step": 423
    },
    {
      "epoch": 1.0278787878787878,
      "grad_norm": 0.16861043870449066,
      "learning_rate": 0.00015922141119221412,
      "loss": 0.5299,
      "step": 424
    },
    {
      "epoch": 1.0303030303030303,
      "grad_norm": 0.07801260054111481,
      "learning_rate": 0.0001591240875912409,
      "loss": 0.498,
      "step": 425
    },
    {
      "epoch": 1.0327272727272727,
      "grad_norm": 0.10205968469381332,
      "learning_rate": 0.00015902676399026766,
      "loss": 0.5217,
      "step": 426
    },
    {
      "epoch": 1.0351515151515152,
      "grad_norm": 0.07868583500385284,
      "learning_rate": 0.0001589294403892944,
      "loss": 0.511,
      "step": 427
    },
    {
      "epoch": 1.0375757575757576,
      "grad_norm": 0.08247793465852737,
      "learning_rate": 0.00015883211678832117,
      "loss": 0.5201,
      "step": 428
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.08052457123994827,
      "learning_rate": 0.00015873479318734794,
      "loss": 0.5321,
      "step": 429
    },
    {
      "epoch": 1.0424242424242425,
      "grad_norm": 0.08852489292621613,
      "learning_rate": 0.00015863746958637471,
      "loss": 0.5117,
      "step": 430
    },
    {
      "epoch": 1.044848484848485,
      "grad_norm": 0.07379024475812912,
      "learning_rate": 0.00015854014598540148,
      "loss": 0.4899,
      "step": 431
    },
    {
      "epoch": 1.0472727272727274,
      "grad_norm": 0.09352800995111465,
      "learning_rate": 0.00015844282238442823,
      "loss": 0.5208,
      "step": 432
    },
    {
      "epoch": 1.0496969696969698,
      "grad_norm": 0.09359347820281982,
      "learning_rate": 0.000158345498783455,
      "loss": 0.4816,
      "step": 433
    },
    {
      "epoch": 1.0521212121212122,
      "grad_norm": 0.11520864814519882,
      "learning_rate": 0.00015824817518248177,
      "loss": 0.5564,
      "step": 434
    },
    {
      "epoch": 1.0545454545454545,
      "grad_norm": 0.0901479572057724,
      "learning_rate": 0.00015815085158150854,
      "loss": 0.5113,
      "step": 435
    },
    {
      "epoch": 1.056969696969697,
      "grad_norm": 0.09867888689041138,
      "learning_rate": 0.00015805352798053528,
      "loss": 0.5325,
      "step": 436
    },
    {
      "epoch": 1.0593939393939393,
      "grad_norm": 0.08376406133174896,
      "learning_rate": 0.00015795620437956205,
      "loss": 0.5106,
      "step": 437
    },
    {
      "epoch": 1.0618181818181818,
      "grad_norm": 0.28106987476348877,
      "learning_rate": 0.00015785888077858882,
      "loss": 0.5013,
      "step": 438
    },
    {
      "epoch": 1.0642424242424242,
      "grad_norm": 0.07944633066654205,
      "learning_rate": 0.0001577615571776156,
      "loss": 0.5337,
      "step": 439
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.8428522348403931,
      "learning_rate": 0.00015766423357664236,
      "loss": 0.4969,
      "step": 440
    },
    {
      "epoch": 1.069090909090909,
      "grad_norm": 0.09679432958364487,
      "learning_rate": 0.0001575669099756691,
      "loss": 0.5111,
      "step": 441
    },
    {
      "epoch": 1.0715151515151515,
      "grad_norm": 0.0897364467382431,
      "learning_rate": 0.00015746958637469588,
      "loss": 0.5178,
      "step": 442
    },
    {
      "epoch": 1.073939393939394,
      "grad_norm": 0.10259881615638733,
      "learning_rate": 0.00015737226277372265,
      "loss": 0.5387,
      "step": 443
    },
    {
      "epoch": 1.0763636363636364,
      "grad_norm": 0.10026432573795319,
      "learning_rate": 0.00015727493917274942,
      "loss": 0.502,
      "step": 444
    },
    {
      "epoch": 1.0787878787878789,
      "grad_norm": 0.09740475565195084,
      "learning_rate": 0.00015717761557177616,
      "loss": 0.5164,
      "step": 445
    },
    {
      "epoch": 1.0812121212121213,
      "grad_norm": 1.0940067768096924,
      "learning_rate": 0.00015708029197080293,
      "loss": 0.5119,
      "step": 446
    },
    {
      "epoch": 1.0836363636363637,
      "grad_norm": 0.10390187054872513,
      "learning_rate": 0.0001569829683698297,
      "loss": 0.4889,
      "step": 447
    },
    {
      "epoch": 1.086060606060606,
      "grad_norm": 0.11603379249572754,
      "learning_rate": 0.00015688564476885644,
      "loss": 0.4958,
      "step": 448
    },
    {
      "epoch": 1.0884848484848484,
      "grad_norm": 0.13268797099590302,
      "learning_rate": 0.0001567883211678832,
      "loss": 0.5119,
      "step": 449
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.08276034891605377,
      "learning_rate": 0.00015669099756690998,
      "loss": 0.5211,
      "step": 450
    },
    {
      "epoch": 1.0933333333333333,
      "grad_norm": 0.19291619956493378,
      "learning_rate": 0.00015659367396593673,
      "loss": 0.5359,
      "step": 451
    },
    {
      "epoch": 1.0957575757575757,
      "grad_norm": 0.0860522985458374,
      "learning_rate": 0.0001564963503649635,
      "loss": 0.5072,
      "step": 452
    },
    {
      "epoch": 1.0981818181818181,
      "grad_norm": 0.08189697563648224,
      "learning_rate": 0.00015639902676399027,
      "loss": 0.5251,
      "step": 453
    },
    {
      "epoch": 1.1006060606060606,
      "grad_norm": 0.10226292163133621,
      "learning_rate": 0.00015630170316301704,
      "loss": 0.4952,
      "step": 454
    },
    {
      "epoch": 1.103030303030303,
      "grad_norm": 0.08467255532741547,
      "learning_rate": 0.0001562043795620438,
      "loss": 0.5269,
      "step": 455
    },
    {
      "epoch": 1.1054545454545455,
      "grad_norm": 0.16166187822818756,
      "learning_rate": 0.00015610705596107055,
      "loss": 0.5067,
      "step": 456
    },
    {
      "epoch": 1.107878787878788,
      "grad_norm": 0.13106173276901245,
      "learning_rate": 0.00015600973236009732,
      "loss": 0.5124,
      "step": 457
    },
    {
      "epoch": 1.1103030303030303,
      "grad_norm": 0.07907097786664963,
      "learning_rate": 0.0001559124087591241,
      "loss": 0.5238,
      "step": 458
    },
    {
      "epoch": 1.1127272727272728,
      "grad_norm": 0.0969403013586998,
      "learning_rate": 0.00015581508515815086,
      "loss": 0.5118,
      "step": 459
    },
    {
      "epoch": 1.1151515151515152,
      "grad_norm": 0.08411287516355515,
      "learning_rate": 0.00015571776155717763,
      "loss": 0.525,
      "step": 460
    },
    {
      "epoch": 1.1175757575757577,
      "grad_norm": 0.2570047676563263,
      "learning_rate": 0.00015562043795620437,
      "loss": 0.4981,
      "step": 461
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.09194251149892807,
      "learning_rate": 0.00015552311435523114,
      "loss": 0.4952,
      "step": 462
    },
    {
      "epoch": 1.1224242424242423,
      "grad_norm": 0.09415578842163086,
      "learning_rate": 0.00015542579075425791,
      "loss": 0.5053,
      "step": 463
    },
    {
      "epoch": 1.1248484848484848,
      "grad_norm": 0.08985944092273712,
      "learning_rate": 0.00015532846715328468,
      "loss": 0.5035,
      "step": 464
    },
    {
      "epoch": 1.1272727272727272,
      "grad_norm": 0.10237359255552292,
      "learning_rate": 0.00015523114355231145,
      "loss": 0.5061,
      "step": 465
    },
    {
      "epoch": 1.1296969696969696,
      "grad_norm": 0.08705998957157135,
      "learning_rate": 0.0001551338199513382,
      "loss": 0.4956,
      "step": 466
    },
    {
      "epoch": 1.132121212121212,
      "grad_norm": 0.0913153737783432,
      "learning_rate": 0.00015503649635036497,
      "loss": 0.5451,
      "step": 467
    },
    {
      "epoch": 1.1345454545454545,
      "grad_norm": 0.09190309047698975,
      "learning_rate": 0.00015493917274939174,
      "loss": 0.5148,
      "step": 468
    },
    {
      "epoch": 1.136969696969697,
      "grad_norm": 0.08330673724412918,
      "learning_rate": 0.0001548418491484185,
      "loss": 0.522,
      "step": 469
    },
    {
      "epoch": 1.1393939393939394,
      "grad_norm": 0.09082568436861038,
      "learning_rate": 0.00015474452554744528,
      "loss": 0.5396,
      "step": 470
    },
    {
      "epoch": 1.1418181818181818,
      "grad_norm": 0.0848437175154686,
      "learning_rate": 0.00015464720194647202,
      "loss": 0.4883,
      "step": 471
    },
    {
      "epoch": 1.1442424242424243,
      "grad_norm": 0.10349821299314499,
      "learning_rate": 0.0001545498783454988,
      "loss": 0.5163,
      "step": 472
    },
    {
      "epoch": 1.1466666666666667,
      "grad_norm": 0.10405348241329193,
      "learning_rate": 0.00015445255474452556,
      "loss": 0.4941,
      "step": 473
    },
    {
      "epoch": 1.1490909090909092,
      "grad_norm": 0.08469447493553162,
      "learning_rate": 0.00015435523114355233,
      "loss": 0.5098,
      "step": 474
    },
    {
      "epoch": 1.1515151515151516,
      "grad_norm": 0.08546050637960434,
      "learning_rate": 0.00015425790754257908,
      "loss": 0.5197,
      "step": 475
    },
    {
      "epoch": 1.1539393939393938,
      "grad_norm": 0.08997242152690887,
      "learning_rate": 0.00015416058394160585,
      "loss": 0.499,
      "step": 476
    },
    {
      "epoch": 1.1563636363636363,
      "grad_norm": 0.08245165646076202,
      "learning_rate": 0.00015406326034063262,
      "loss": 0.5129,
      "step": 477
    },
    {
      "epoch": 1.1587878787878787,
      "grad_norm": 0.08958356082439423,
      "learning_rate": 0.00015396593673965939,
      "loss": 0.5175,
      "step": 478
    },
    {
      "epoch": 1.1612121212121211,
      "grad_norm": 0.08009914308786392,
      "learning_rate": 0.00015386861313868616,
      "loss": 0.534,
      "step": 479
    },
    {
      "epoch": 1.1636363636363636,
      "grad_norm": 0.089272640645504,
      "learning_rate": 0.0001537712895377129,
      "loss": 0.5156,
      "step": 480
    },
    {
      "epoch": 1.166060606060606,
      "grad_norm": 0.08497253060340881,
      "learning_rate": 0.00015367396593673967,
      "loss": 0.5169,
      "step": 481
    },
    {
      "epoch": 1.1684848484848485,
      "grad_norm": 0.08458175510168076,
      "learning_rate": 0.00015357664233576644,
      "loss": 0.5134,
      "step": 482
    },
    {
      "epoch": 1.170909090909091,
      "grad_norm": 0.08339492976665497,
      "learning_rate": 0.0001534793187347932,
      "loss": 0.5013,
      "step": 483
    },
    {
      "epoch": 1.1733333333333333,
      "grad_norm": 0.10656485706567764,
      "learning_rate": 0.00015338199513381998,
      "loss": 0.5187,
      "step": 484
    },
    {
      "epoch": 1.1757575757575758,
      "grad_norm": 0.0818299651145935,
      "learning_rate": 0.00015328467153284672,
      "loss": 0.5056,
      "step": 485
    },
    {
      "epoch": 1.1781818181818182,
      "grad_norm": 0.1118079349398613,
      "learning_rate": 0.0001531873479318735,
      "loss": 0.5227,
      "step": 486
    },
    {
      "epoch": 1.1806060606060607,
      "grad_norm": 0.0880877748131752,
      "learning_rate": 0.00015309002433090026,
      "loss": 0.5076,
      "step": 487
    },
    {
      "epoch": 1.183030303030303,
      "grad_norm": 0.08330365270376205,
      "learning_rate": 0.000152992700729927,
      "loss": 0.5078,
      "step": 488
    },
    {
      "epoch": 1.1854545454545455,
      "grad_norm": 0.08401932567358017,
      "learning_rate": 0.00015289537712895378,
      "loss": 0.5022,
      "step": 489
    },
    {
      "epoch": 1.187878787878788,
      "grad_norm": 0.09882496297359467,
      "learning_rate": 0.00015279805352798055,
      "loss": 0.516,
      "step": 490
    },
    {
      "epoch": 1.1903030303030304,
      "grad_norm": 0.08196999877691269,
      "learning_rate": 0.0001527007299270073,
      "loss": 0.4995,
      "step": 491
    },
    {
      "epoch": 1.1927272727272726,
      "grad_norm": 0.1815212368965149,
      "learning_rate": 0.00015260340632603406,
      "loss": 0.5208,
      "step": 492
    },
    {
      "epoch": 1.195151515151515,
      "grad_norm": 0.10694020986557007,
      "learning_rate": 0.00015250608272506083,
      "loss": 0.5298,
      "step": 493
    },
    {
      "epoch": 1.1975757575757575,
      "grad_norm": 0.08709581196308136,
      "learning_rate": 0.0001524087591240876,
      "loss": 0.5185,
      "step": 494
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.0916096493601799,
      "learning_rate": 0.00015231143552311434,
      "loss": 0.5158,
      "step": 495
    },
    {
      "epoch": 1.2024242424242424,
      "grad_norm": 0.08709704130887985,
      "learning_rate": 0.00015221411192214111,
      "loss": 0.5075,
      "step": 496
    },
    {
      "epoch": 1.2048484848484848,
      "grad_norm": 0.08242951333522797,
      "learning_rate": 0.00015211678832116788,
      "loss": 0.5183,
      "step": 497
    },
    {
      "epoch": 1.2072727272727273,
      "grad_norm": 0.09210577607154846,
      "learning_rate": 0.00015201946472019465,
      "loss": 0.5563,
      "step": 498
    },
    {
      "epoch": 1.2096969696969697,
      "grad_norm": 0.08756948262453079,
      "learning_rate": 0.00015192214111922142,
      "loss": 0.5096,
      "step": 499
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 0.08763476461172104,
      "learning_rate": 0.00015182481751824817,
      "loss": 0.5366,
      "step": 500
    },
    {
      "epoch": 1.2157575757575758,
      "grad_norm": 0.09851865470409393,
      "learning_rate": 0.00015172749391727494,
      "loss": 0.513,
      "step": 501
    },
    {
      "epoch": 1.2181818181818183,
      "grad_norm": 0.08382665365934372,
      "learning_rate": 0.0001516301703163017,
      "loss": 0.5228,
      "step": 502
    },
    {
      "epoch": 1.2206060606060607,
      "grad_norm": 0.08667465299367905,
      "learning_rate": 0.00015153284671532848,
      "loss": 0.5605,
      "step": 503
    },
    {
      "epoch": 1.2230303030303031,
      "grad_norm": 0.08665841072797775,
      "learning_rate": 0.00015143552311435525,
      "loss": 0.4944,
      "step": 504
    },
    {
      "epoch": 1.2254545454545456,
      "grad_norm": 0.09344764053821564,
      "learning_rate": 0.000151338199513382,
      "loss": 0.5148,
      "step": 505
    },
    {
      "epoch": 1.2278787878787878,
      "grad_norm": 0.11476101726293564,
      "learning_rate": 0.00015124087591240876,
      "loss": 0.4943,
      "step": 506
    },
    {
      "epoch": 1.2303030303030302,
      "grad_norm": 0.08675657957792282,
      "learning_rate": 0.00015114355231143553,
      "loss": 0.5026,
      "step": 507
    },
    {
      "epoch": 1.2327272727272727,
      "grad_norm": 0.0824153870344162,
      "learning_rate": 0.0001510462287104623,
      "loss": 0.498,
      "step": 508
    },
    {
      "epoch": 1.2351515151515151,
      "grad_norm": 0.08708232641220093,
      "learning_rate": 0.00015094890510948907,
      "loss": 0.5157,
      "step": 509
    },
    {
      "epoch": 1.2375757575757576,
      "grad_norm": 0.11077408492565155,
      "learning_rate": 0.00015085158150851582,
      "loss": 0.484,
      "step": 510
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.13466417789459229,
      "learning_rate": 0.00015075425790754259,
      "loss": 0.5141,
      "step": 511
    },
    {
      "epoch": 1.2424242424242424,
      "grad_norm": 0.08861487358808517,
      "learning_rate": 0.00015065693430656936,
      "loss": 0.5377,
      "step": 512
    },
    {
      "epoch": 1.2448484848484849,
      "grad_norm": 0.08291108161211014,
      "learning_rate": 0.00015055961070559613,
      "loss": 0.4983,
      "step": 513
    },
    {
      "epoch": 1.2472727272727273,
      "grad_norm": 0.08234492689371109,
      "learning_rate": 0.00015046228710462287,
      "loss": 0.5004,
      "step": 514
    },
    {
      "epoch": 1.2496969696969698,
      "grad_norm": 0.08518437296152115,
      "learning_rate": 0.00015036496350364964,
      "loss": 0.4999,
      "step": 515
    },
    {
      "epoch": 1.2521212121212122,
      "grad_norm": 0.09255598485469818,
      "learning_rate": 0.0001502676399026764,
      "loss": 0.4991,
      "step": 516
    },
    {
      "epoch": 1.2545454545454544,
      "grad_norm": 0.10292229801416397,
      "learning_rate": 0.00015017031630170318,
      "loss": 0.5311,
      "step": 517
    },
    {
      "epoch": 1.2569696969696968,
      "grad_norm": 0.08543982356786728,
      "learning_rate": 0.00015007299270072995,
      "loss": 0.4944,
      "step": 518
    },
    {
      "epoch": 1.2593939393939393,
      "grad_norm": 0.09525194764137268,
      "learning_rate": 0.0001499756690997567,
      "loss": 0.5092,
      "step": 519
    },
    {
      "epoch": 1.2618181818181817,
      "grad_norm": 0.1020321249961853,
      "learning_rate": 0.00014987834549878346,
      "loss": 0.5262,
      "step": 520
    },
    {
      "epoch": 1.2642424242424242,
      "grad_norm": 0.09426764398813248,
      "learning_rate": 0.00014978102189781023,
      "loss": 0.5013,
      "step": 521
    },
    {
      "epoch": 1.2666666666666666,
      "grad_norm": 0.13493221998214722,
      "learning_rate": 0.000149683698296837,
      "loss": 0.4999,
      "step": 522
    },
    {
      "epoch": 1.269090909090909,
      "grad_norm": 0.08331029117107391,
      "learning_rate": 0.00014958637469586377,
      "loss": 0.5145,
      "step": 523
    },
    {
      "epoch": 1.2715151515151515,
      "grad_norm": 0.09309305250644684,
      "learning_rate": 0.00014948905109489052,
      "loss": 0.5147,
      "step": 524
    },
    {
      "epoch": 1.273939393939394,
      "grad_norm": 0.08079483360052109,
      "learning_rate": 0.0001493917274939173,
      "loss": 0.5081,
      "step": 525
    },
    {
      "epoch": 1.2763636363636364,
      "grad_norm": 0.09371911734342575,
      "learning_rate": 0.00014929440389294406,
      "loss": 0.5227,
      "step": 526
    },
    {
      "epoch": 1.2787878787878788,
      "grad_norm": 0.08061868697404861,
      "learning_rate": 0.00014919708029197083,
      "loss": 0.5065,
      "step": 527
    },
    {
      "epoch": 1.2812121212121212,
      "grad_norm": 0.09465505182743073,
      "learning_rate": 0.00014909975669099757,
      "loss": 0.5242,
      "step": 528
    },
    {
      "epoch": 1.2836363636363637,
      "grad_norm": 0.08646652847528458,
      "learning_rate": 0.00014900243309002434,
      "loss": 0.5198,
      "step": 529
    },
    {
      "epoch": 1.2860606060606061,
      "grad_norm": 0.09964391589164734,
      "learning_rate": 0.0001489051094890511,
      "loss": 0.5187,
      "step": 530
    },
    {
      "epoch": 1.2884848484848486,
      "grad_norm": 0.2668514549732208,
      "learning_rate": 0.00014880778588807785,
      "loss": 0.5063,
      "step": 531
    },
    {
      "epoch": 1.290909090909091,
      "grad_norm": 0.8861544728279114,
      "learning_rate": 0.00014871046228710462,
      "loss": 0.5352,
      "step": 532
    },
    {
      "epoch": 1.2933333333333334,
      "grad_norm": 0.09407690167427063,
      "learning_rate": 0.0001486131386861314,
      "loss": 0.504,
      "step": 533
    },
    {
      "epoch": 1.2957575757575759,
      "grad_norm": 0.0829433873295784,
      "learning_rate": 0.00014851581508515814,
      "loss": 0.5226,
      "step": 534
    },
    {
      "epoch": 1.298181818181818,
      "grad_norm": 0.09572310000658035,
      "learning_rate": 0.0001484184914841849,
      "loss": 0.5181,
      "step": 535
    },
    {
      "epoch": 1.3006060606060605,
      "grad_norm": 0.1050073653459549,
      "learning_rate": 0.00014832116788321168,
      "loss": 0.495,
      "step": 536
    },
    {
      "epoch": 1.303030303030303,
      "grad_norm": 0.09953190386295319,
      "learning_rate": 0.00014822384428223845,
      "loss": 0.5148,
      "step": 537
    },
    {
      "epoch": 1.3054545454545454,
      "grad_norm": 0.09054164588451385,
      "learning_rate": 0.00014812652068126522,
      "loss": 0.5316,
      "step": 538
    },
    {
      "epoch": 1.3078787878787879,
      "grad_norm": 0.09377751499414444,
      "learning_rate": 0.00014802919708029196,
      "loss": 0.5237,
      "step": 539
    },
    {
      "epoch": 1.3103030303030303,
      "grad_norm": 0.09183742105960846,
      "learning_rate": 0.00014793187347931873,
      "loss": 0.5081,
      "step": 540
    },
    {
      "epoch": 1.3127272727272727,
      "grad_norm": 0.0925275981426239,
      "learning_rate": 0.0001478345498783455,
      "loss": 0.5081,
      "step": 541
    },
    {
      "epoch": 1.3151515151515152,
      "grad_norm": 0.10807181149721146,
      "learning_rate": 0.00014773722627737227,
      "loss": 0.5204,
      "step": 542
    },
    {
      "epoch": 1.3175757575757576,
      "grad_norm": 0.10067620128393173,
      "learning_rate": 0.00014763990267639904,
      "loss": 0.5078,
      "step": 543
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.09460193663835526,
      "learning_rate": 0.00014754257907542579,
      "loss": 0.4712,
      "step": 544
    },
    {
      "epoch": 1.3224242424242425,
      "grad_norm": 0.1714082807302475,
      "learning_rate": 0.00014744525547445256,
      "loss": 0.5307,
      "step": 545
    },
    {
      "epoch": 1.3248484848484847,
      "grad_norm": 0.10749589651823044,
      "learning_rate": 0.00014734793187347933,
      "loss": 0.5141,
      "step": 546
    },
    {
      "epoch": 1.3272727272727272,
      "grad_norm": 0.10069436579942703,
      "learning_rate": 0.0001472506082725061,
      "loss": 0.5343,
      "step": 547
    },
    {
      "epoch": 1.3296969696969696,
      "grad_norm": 0.14761832356452942,
      "learning_rate": 0.00014715328467153284,
      "loss": 0.5028,
      "step": 548
    },
    {
      "epoch": 1.332121212121212,
      "grad_norm": 1.3738667964935303,
      "learning_rate": 0.0001470559610705596,
      "loss": 0.4939,
      "step": 549
    },
    {
      "epoch": 1.3345454545454545,
      "grad_norm": 0.3520508408546448,
      "learning_rate": 0.00014695863746958638,
      "loss": 0.5027,
      "step": 550
    },
    {
      "epoch": 1.336969696969697,
      "grad_norm": 0.10602544248104095,
      "learning_rate": 0.00014686131386861315,
      "loss": 0.5536,
      "step": 551
    },
    {
      "epoch": 1.3393939393939394,
      "grad_norm": 0.09854532778263092,
      "learning_rate": 0.00014676399026763992,
      "loss": 0.5253,
      "step": 552
    },
    {
      "epoch": 1.3418181818181818,
      "grad_norm": 0.08934779465198517,
      "learning_rate": 0.00014666666666666666,
      "loss": 0.5004,
      "step": 553
    },
    {
      "epoch": 1.3442424242424242,
      "grad_norm": 0.08334718644618988,
      "learning_rate": 0.00014656934306569343,
      "loss": 0.4879,
      "step": 554
    },
    {
      "epoch": 1.3466666666666667,
      "grad_norm": 0.08755338191986084,
      "learning_rate": 0.0001464720194647202,
      "loss": 0.5041,
      "step": 555
    },
    {
      "epoch": 1.3490909090909091,
      "grad_norm": 0.10793605446815491,
      "learning_rate": 0.00014637469586374697,
      "loss": 0.5145,
      "step": 556
    },
    {
      "epoch": 1.3515151515151516,
      "grad_norm": 0.1267707496881485,
      "learning_rate": 0.00014627737226277374,
      "loss": 0.5543,
      "step": 557
    },
    {
      "epoch": 1.353939393939394,
      "grad_norm": 0.09821425378322601,
      "learning_rate": 0.0001461800486618005,
      "loss": 0.4993,
      "step": 558
    },
    {
      "epoch": 1.3563636363636364,
      "grad_norm": 0.09854073822498322,
      "learning_rate": 0.00014608272506082726,
      "loss": 0.5296,
      "step": 559
    },
    {
      "epoch": 1.3587878787878789,
      "grad_norm": 0.08731967210769653,
      "learning_rate": 0.00014598540145985403,
      "loss": 0.4931,
      "step": 560
    },
    {
      "epoch": 1.3612121212121213,
      "grad_norm": 0.12153112888336182,
      "learning_rate": 0.0001458880778588808,
      "loss": 0.5063,
      "step": 561
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.09742265194654465,
      "learning_rate": 0.00014579075425790757,
      "loss": 0.5067,
      "step": 562
    },
    {
      "epoch": 1.3660606060606062,
      "grad_norm": 0.09881233423948288,
      "learning_rate": 0.0001456934306569343,
      "loss": 0.5556,
      "step": 563
    },
    {
      "epoch": 1.3684848484848484,
      "grad_norm": 0.08841077983379364,
      "learning_rate": 0.00014559610705596108,
      "loss": 0.537,
      "step": 564
    },
    {
      "epoch": 1.3709090909090909,
      "grad_norm": 0.08286780118942261,
      "learning_rate": 0.00014549878345498785,
      "loss": 0.4852,
      "step": 565
    },
    {
      "epoch": 1.3733333333333333,
      "grad_norm": 0.10221046954393387,
      "learning_rate": 0.00014540145985401462,
      "loss": 0.5136,
      "step": 566
    },
    {
      "epoch": 1.3757575757575757,
      "grad_norm": 0.11805588752031326,
      "learning_rate": 0.0001453041362530414,
      "loss": 0.5167,
      "step": 567
    },
    {
      "epoch": 1.3781818181818182,
      "grad_norm": 0.10228164494037628,
      "learning_rate": 0.00014520681265206813,
      "loss": 0.5193,
      "step": 568
    },
    {
      "epoch": 1.3806060606060606,
      "grad_norm": 0.09577467292547226,
      "learning_rate": 0.0001451094890510949,
      "loss": 0.5484,
      "step": 569
    },
    {
      "epoch": 1.383030303030303,
      "grad_norm": 0.10035896301269531,
      "learning_rate": 0.00014501216545012167,
      "loss": 0.5295,
      "step": 570
    },
    {
      "epoch": 1.3854545454545455,
      "grad_norm": 0.09537103027105331,
      "learning_rate": 0.00014491484184914842,
      "loss": 0.4905,
      "step": 571
    },
    {
      "epoch": 1.387878787878788,
      "grad_norm": 0.12688210606575012,
      "learning_rate": 0.0001448175182481752,
      "loss": 0.5122,
      "step": 572
    },
    {
      "epoch": 1.3903030303030304,
      "grad_norm": 0.11108087748289108,
      "learning_rate": 0.00014472019464720196,
      "loss": 0.5167,
      "step": 573
    },
    {
      "epoch": 1.3927272727272726,
      "grad_norm": 0.08123259991407394,
      "learning_rate": 0.0001446228710462287,
      "loss": 0.4984,
      "step": 574
    },
    {
      "epoch": 1.395151515151515,
      "grad_norm": 0.09493537247180939,
      "learning_rate": 0.00014452554744525547,
      "loss": 0.5122,
      "step": 575
    },
    {
      "epoch": 1.3975757575757575,
      "grad_norm": 0.10610169917345047,
      "learning_rate": 0.00014442822384428224,
      "loss": 0.5077,
      "step": 576
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.12278426438570023,
      "learning_rate": 0.000144330900243309,
      "loss": 0.5822,
      "step": 577
    },
    {
      "epoch": 1.4024242424242424,
      "grad_norm": 0.08439641445875168,
      "learning_rate": 0.00014423357664233576,
      "loss": 0.4969,
      "step": 578
    },
    {
      "epoch": 1.4048484848484848,
      "grad_norm": 0.1579558104276657,
      "learning_rate": 0.00014413625304136253,
      "loss": 0.508,
      "step": 579
    },
    {
      "epoch": 1.4072727272727272,
      "grad_norm": 0.10641365498304367,
      "learning_rate": 0.0001440389294403893,
      "loss": 0.5318,
      "step": 580
    },
    {
      "epoch": 1.4096969696969697,
      "grad_norm": 0.4571323096752167,
      "learning_rate": 0.00014394160583941607,
      "loss": 0.5568,
      "step": 581
    },
    {
      "epoch": 1.412121212121212,
      "grad_norm": 0.09110407531261444,
      "learning_rate": 0.00014384428223844284,
      "loss": 0.5055,
      "step": 582
    },
    {
      "epoch": 1.4145454545454546,
      "grad_norm": 0.10636278986930847,
      "learning_rate": 0.00014374695863746958,
      "loss": 0.5248,
      "step": 583
    },
    {
      "epoch": 1.416969696969697,
      "grad_norm": 0.09190414845943451,
      "learning_rate": 0.00014364963503649635,
      "loss": 0.5061,
      "step": 584
    },
    {
      "epoch": 1.4193939393939394,
      "grad_norm": 0.08538050204515457,
      "learning_rate": 0.00014355231143552312,
      "loss": 0.4963,
      "step": 585
    },
    {
      "epoch": 1.4218181818181819,
      "grad_norm": 0.08791066706180573,
      "learning_rate": 0.0001434549878345499,
      "loss": 0.4981,
      "step": 586
    },
    {
      "epoch": 1.4242424242424243,
      "grad_norm": 0.16966612637043,
      "learning_rate": 0.00014335766423357663,
      "loss": 0.4886,
      "step": 587
    },
    {
      "epoch": 1.4266666666666667,
      "grad_norm": 0.11110067367553711,
      "learning_rate": 0.0001432603406326034,
      "loss": 0.5101,
      "step": 588
    },
    {
      "epoch": 1.4290909090909092,
      "grad_norm": 0.12022274732589722,
      "learning_rate": 0.00014316301703163017,
      "loss": 0.5187,
      "step": 589
    },
    {
      "epoch": 1.4315151515151516,
      "grad_norm": 0.09382260590791702,
      "learning_rate": 0.00014306569343065694,
      "loss": 0.5234,
      "step": 590
    },
    {
      "epoch": 1.433939393939394,
      "grad_norm": 0.08684837073087692,
      "learning_rate": 0.0001429683698296837,
      "loss": 0.4994,
      "step": 591
    },
    {
      "epoch": 1.4363636363636363,
      "grad_norm": 0.3479120135307312,
      "learning_rate": 0.00014287104622871046,
      "loss": 0.4933,
      "step": 592
    },
    {
      "epoch": 1.4387878787878787,
      "grad_norm": 0.29582905769348145,
      "learning_rate": 0.00014277372262773723,
      "loss": 0.4984,
      "step": 593
    },
    {
      "epoch": 1.4412121212121212,
      "grad_norm": 0.22288404405117035,
      "learning_rate": 0.000142676399026764,
      "loss": 0.5313,
      "step": 594
    },
    {
      "epoch": 1.4436363636363636,
      "grad_norm": 0.39515429735183716,
      "learning_rate": 0.00014257907542579077,
      "loss": 0.5122,
      "step": 595
    },
    {
      "epoch": 1.446060606060606,
      "grad_norm": 0.11622841656208038,
      "learning_rate": 0.00014248175182481754,
      "loss": 0.5141,
      "step": 596
    },
    {
      "epoch": 1.4484848484848485,
      "grad_norm": 0.11276782304048538,
      "learning_rate": 0.00014238442822384428,
      "loss": 0.5231,
      "step": 597
    },
    {
      "epoch": 1.450909090909091,
      "grad_norm": 0.24036924540996552,
      "learning_rate": 0.00014228710462287105,
      "loss": 0.5443,
      "step": 598
    },
    {
      "epoch": 1.4533333333333334,
      "grad_norm": 0.10040941834449768,
      "learning_rate": 0.00014218978102189782,
      "loss": 0.5093,
      "step": 599
    },
    {
      "epoch": 1.4557575757575758,
      "grad_norm": 0.1752922534942627,
      "learning_rate": 0.0001420924574209246,
      "loss": 0.5303,
      "step": 600
    }
  ],
  "logging_steps": 1,
  "max_steps": 2060,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.1116706008989696e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}