{
  "best_metric": 0.8067082166671753,
  "best_model_checkpoint": "miner_id_24/checkpoint-400",
  "epoch": 0.15312260745925846,
  "eval_steps": 200,
  "global_step": 1400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010937329104232747,
      "grad_norm": 1.0359435081481934,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.7552,
      "step": 1
    },
    {
      "epoch": 0.00010937329104232747,
      "eval_loss": 0.7747385501861572,
      "eval_runtime": 40.8616,
      "eval_samples_per_second": 18.012,
      "eval_steps_per_second": 4.503,
      "step": 1
    },
    {
      "epoch": 0.00021874658208465494,
      "grad_norm": 0.957185685634613,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.4443,
      "step": 2
    },
    {
      "epoch": 0.00032811987312698237,
      "grad_norm": 1.1346784830093384,
      "learning_rate": 2e-05,
      "loss": 0.8643,
      "step": 3
    },
    {
      "epoch": 0.0004374931641693099,
      "grad_norm": 0.9469565749168396,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.7323,
      "step": 4
    },
    {
      "epoch": 0.0005468664552116373,
      "grad_norm": 0.7470714449882507,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.7802,
      "step": 5
    },
    {
      "epoch": 0.0006562397462539647,
      "grad_norm": 0.9336181282997131,
      "learning_rate": 4e-05,
      "loss": 0.7257,
      "step": 6
    },
    {
      "epoch": 0.0007656130372962922,
      "grad_norm": 1.0791195631027222,
      "learning_rate": 4.666666666666667e-05,
      "loss": 0.8429,
      "step": 7
    },
    {
      "epoch": 0.0008749863283386198,
      "grad_norm": 0.7835611701011658,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.6867,
      "step": 8
    },
    {
      "epoch": 0.0009843596193809471,
      "grad_norm": 0.97986900806427,
      "learning_rate": 6e-05,
      "loss": 1.344,
      "step": 9
    },
    {
      "epoch": 0.0010937329104232746,
      "grad_norm": 0.7541531920433044,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.0589,
      "step": 10
    },
    {
      "epoch": 0.001203106201465602,
      "grad_norm": 0.9011327624320984,
      "learning_rate": 7.333333333333333e-05,
      "loss": 0.9204,
      "step": 11
    },
    {
      "epoch": 0.0013124794925079295,
      "grad_norm": 0.73972088098526,
      "learning_rate": 8e-05,
      "loss": 0.5648,
      "step": 12
    },
    {
      "epoch": 0.001421852783550257,
      "grad_norm": 0.8409032225608826,
      "learning_rate": 8.666666666666667e-05,
      "loss": 0.7085,
      "step": 13
    },
    {
      "epoch": 0.0015312260745925844,
      "grad_norm": 0.7147814035415649,
      "learning_rate": 9.333333333333334e-05,
      "loss": 0.5697,
      "step": 14
    },
    {
      "epoch": 0.0016405993656349119,
      "grad_norm": 1.2943480014801025,
      "learning_rate": 0.0001,
      "loss": 0.5326,
      "step": 15
    },
    {
      "epoch": 0.0017499726566772395,
      "grad_norm": 1.0381604433059692,
      "learning_rate": 0.00010666666666666667,
      "loss": 0.6035,
      "step": 16
    },
    {
      "epoch": 0.001859345947719567,
      "grad_norm": 1.241224765777588,
      "learning_rate": 0.00011333333333333334,
      "loss": 0.8444,
      "step": 17
    },
    {
      "epoch": 0.0019687192387618942,
      "grad_norm": 1.2240588665008545,
      "learning_rate": 0.00012,
      "loss": 1.2189,
      "step": 18
    },
    {
      "epoch": 0.002078092529804222,
      "grad_norm": 0.6758236885070801,
      "learning_rate": 0.00012666666666666666,
      "loss": 0.8096,
      "step": 19
    },
    {
      "epoch": 0.002187465820846549,
      "grad_norm": 0.9755652546882629,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.7745,
      "step": 20
    },
    {
      "epoch": 0.002296839111888877,
      "grad_norm": 0.9789362549781799,
      "learning_rate": 0.00014,
      "loss": 0.8419,
      "step": 21
    },
    {
      "epoch": 0.002406212402931204,
      "grad_norm": 1.243459939956665,
      "learning_rate": 0.00014666666666666666,
      "loss": 0.6975,
      "step": 22
    },
    {
      "epoch": 0.0025155856939735317,
      "grad_norm": 1.1147222518920898,
      "learning_rate": 0.00015333333333333334,
      "loss": 1.0447,
      "step": 23
    },
    {
      "epoch": 0.002624958985015859,
      "grad_norm": 0.7549237012863159,
      "learning_rate": 0.00016,
      "loss": 0.8227,
      "step": 24
    },
    {
      "epoch": 0.0027343322760581866,
      "grad_norm": 0.9991783499717712,
      "learning_rate": 0.0001666666666666667,
      "loss": 0.7753,
      "step": 25
    },
    {
      "epoch": 0.002843705567100514,
      "grad_norm": 0.8530986309051514,
      "learning_rate": 0.00017333333333333334,
      "loss": 1.0104,
      "step": 26
    },
    {
      "epoch": 0.0029530788581428415,
      "grad_norm": 1.0823960304260254,
      "learning_rate": 0.00018,
      "loss": 0.6805,
      "step": 27
    },
    {
      "epoch": 0.003062452149185169,
      "grad_norm": 1.1649422645568848,
      "learning_rate": 0.0001866666666666667,
      "loss": 0.651,
      "step": 28
    },
    {
      "epoch": 0.0031718254402274965,
      "grad_norm": 1.153540849685669,
      "learning_rate": 0.00019333333333333333,
      "loss": 0.6845,
      "step": 29
    },
    {
      "epoch": 0.0032811987312698237,
      "grad_norm": 1.0849957466125488,
      "learning_rate": 0.0002,
      "loss": 0.843,
      "step": 30
    },
    {
      "epoch": 0.0033905720223121514,
      "grad_norm": 1.088346242904663,
      "learning_rate": 0.00019999999934264446,
      "loss": 0.7297,
      "step": 31
    },
    {
      "epoch": 0.003499945313354479,
      "grad_norm": 0.8655444979667664,
      "learning_rate": 0.00019999999737057786,
      "loss": 0.8366,
      "step": 32
    },
    {
      "epoch": 0.0036093186043968063,
      "grad_norm": 0.9512057900428772,
      "learning_rate": 0.00019999999408380027,
      "loss": 0.5827,
      "step": 33
    },
    {
      "epoch": 0.003718691895439134,
      "grad_norm": 0.9010905623435974,
      "learning_rate": 0.0001999999894823116,
      "loss": 0.9626,
      "step": 34
    },
    {
      "epoch": 0.003828065186481461,
      "grad_norm": 0.8122968077659607,
      "learning_rate": 0.00019999998356611204,
      "loss": 0.9244,
      "step": 35
    },
    {
      "epoch": 0.0039374384775237884,
      "grad_norm": 1.0451189279556274,
      "learning_rate": 0.00019999997633520162,
      "loss": 0.8667,
      "step": 36
    },
    {
      "epoch": 0.004046811768566116,
      "grad_norm": 0.9873628616333008,
      "learning_rate": 0.00019999996778958046,
      "loss": 0.6803,
      "step": 37
    },
    {
      "epoch": 0.004156185059608444,
      "grad_norm": 0.9295932650566101,
      "learning_rate": 0.00019999995792924864,
      "loss": 0.6587,
      "step": 38
    },
    {
      "epoch": 0.0042655583506507715,
      "grad_norm": 0.9532923102378845,
      "learning_rate": 0.00019999994675420628,
      "loss": 0.7123,
      "step": 39
    },
    {
      "epoch": 0.004374931641693098,
      "grad_norm": 0.8833261132240295,
      "learning_rate": 0.00019999993426445358,
      "loss": 0.6655,
      "step": 40
    },
    {
      "epoch": 0.004484304932735426,
      "grad_norm": 0.7765618562698364,
      "learning_rate": 0.00019999992045999067,
      "loss": 0.6227,
      "step": 41
    },
    {
      "epoch": 0.004593678223777754,
      "grad_norm": 1.0266915559768677,
      "learning_rate": 0.0001999999053408177,
      "loss": 0.9985,
      "step": 42
    },
    {
      "epoch": 0.004703051514820081,
      "grad_norm": 0.7699204683303833,
      "learning_rate": 0.00019999988890693492,
      "loss": 0.8645,
      "step": 43
    },
    {
      "epoch": 0.004812424805862408,
      "grad_norm": 1.003393292427063,
      "learning_rate": 0.00019999987115834253,
      "loss": 0.8971,
      "step": 44
    },
    {
      "epoch": 0.004921798096904736,
      "grad_norm": 0.8142101168632507,
      "learning_rate": 0.0001999998520950408,
      "loss": 0.7234,
      "step": 45
    },
    {
      "epoch": 0.0050311713879470634,
      "grad_norm": 1.3098042011260986,
      "learning_rate": 0.0001999998317170299,
      "loss": 0.8737,
      "step": 46
    },
    {
      "epoch": 0.005140544678989391,
      "grad_norm": 0.8643680214881897,
      "learning_rate": 0.00019999981002431015,
      "loss": 0.8877,
      "step": 47
    },
    {
      "epoch": 0.005249917970031718,
      "grad_norm": 0.873254120349884,
      "learning_rate": 0.00019999978701688183,
      "loss": 0.6834,
      "step": 48
    },
    {
      "epoch": 0.005359291261074046,
      "grad_norm": 0.8523358106613159,
      "learning_rate": 0.00019999976269474522,
      "loss": 0.887,
      "step": 49
    },
    {
      "epoch": 0.005468664552116373,
      "grad_norm": 1.0463756322860718,
      "learning_rate": 0.00019999973705790068,
      "loss": 0.6026,
      "step": 50
    },
    {
      "epoch": 0.005578037843158701,
      "grad_norm": 0.9958584308624268,
      "learning_rate": 0.00019999971010634853,
      "loss": 0.8893,
      "step": 51
    },
    {
      "epoch": 0.005687411134201028,
      "grad_norm": 1.0434130430221558,
      "learning_rate": 0.0001999996818400891,
      "loss": 0.8421,
      "step": 52
    },
    {
      "epoch": 0.005796784425243355,
      "grad_norm": 0.917728841304779,
      "learning_rate": 0.0001999996522591228,
      "loss": 0.6586,
      "step": 53
    },
    {
      "epoch": 0.005906157716285683,
      "grad_norm": 0.8328091502189636,
      "learning_rate": 0.00019999962136345,
      "loss": 0.8971,
      "step": 54
    },
    {
      "epoch": 0.006015531007328011,
      "grad_norm": 1.2430554628372192,
      "learning_rate": 0.0001999995891530711,
      "loss": 1.0108,
      "step": 55
    },
    {
      "epoch": 0.006124904298370338,
      "grad_norm": 0.9426673054695129,
      "learning_rate": 0.00019999955562798654,
      "loss": 0.9291,
      "step": 56
    },
    {
      "epoch": 0.006234277589412665,
      "grad_norm": 1.0275059938430786,
      "learning_rate": 0.00019999952078819674,
      "loss": 1.0881,
      "step": 57
    },
    {
      "epoch": 0.006343650880454993,
      "grad_norm": 1.0648664236068726,
      "learning_rate": 0.00019999948463370217,
      "loss": 0.7744,
      "step": 58
    },
    {
      "epoch": 0.006453024171497321,
      "grad_norm": 0.9224843382835388,
      "learning_rate": 0.00019999944716450328,
      "loss": 0.8151,
      "step": 59
    },
    {
      "epoch": 0.006562397462539647,
      "grad_norm": 0.9548549652099609,
      "learning_rate": 0.00019999940838060062,
      "loss": 0.8695,
      "step": 60
    },
    {
      "epoch": 0.006671770753581975,
      "grad_norm": 0.9503769874572754,
      "learning_rate": 0.00019999936828199468,
      "loss": 0.7061,
      "step": 61
    },
    {
      "epoch": 0.006781144044624303,
      "grad_norm": 1.0756902694702148,
      "learning_rate": 0.00019999932686868595,
      "loss": 0.5131,
      "step": 62
    },
    {
      "epoch": 0.00689051733566663,
      "grad_norm": 0.9061060547828674,
      "learning_rate": 0.00019999928414067499,
      "loss": 1.0903,
      "step": 63
    },
    {
      "epoch": 0.006999890626708958,
      "grad_norm": 1.2045193910598755,
      "learning_rate": 0.0001999992400979624,
      "loss": 0.7959,
      "step": 64
    },
    {
      "epoch": 0.007109263917751285,
      "grad_norm": 0.785504162311554,
      "learning_rate": 0.0001999991947405487,
      "loss": 1.067,
      "step": 65
    },
    {
      "epoch": 0.007218637208793613,
      "grad_norm": 0.8506015539169312,
      "learning_rate": 0.00019999914806843454,
      "loss": 1.0416,
      "step": 66
    },
    {
      "epoch": 0.00732801049983594,
      "grad_norm": 1.103265404701233,
      "learning_rate": 0.00019999910008162048,
      "loss": 0.5667,
      "step": 67
    },
    {
      "epoch": 0.007437383790878268,
      "grad_norm": 0.9666427969932556,
      "learning_rate": 0.0001999990507801072,
      "loss": 0.7017,
      "step": 68
    },
    {
      "epoch": 0.007546757081920595,
      "grad_norm": 0.7427759170532227,
      "learning_rate": 0.0001999990001638953,
      "loss": 1.0521,
      "step": 69
    },
    {
      "epoch": 0.007656130372962922,
      "grad_norm": 1.2603650093078613,
      "learning_rate": 0.00019999894823298552,
      "loss": 0.7703,
      "step": 70
    },
    {
      "epoch": 0.00776550366400525,
      "grad_norm": 1.3171355724334717,
      "learning_rate": 0.00019999889498737848,
      "loss": 0.7608,
      "step": 71
    },
    {
      "epoch": 0.007874876955047577,
      "grad_norm": 0.9187859892845154,
      "learning_rate": 0.0001999988404270749,
      "loss": 0.9708,
      "step": 72
    },
    {
      "epoch": 0.007984250246089905,
      "grad_norm": 0.8871030807495117,
      "learning_rate": 0.0001999987845520755,
      "loss": 0.8331,
      "step": 73
    },
    {
      "epoch": 0.008093623537132232,
      "grad_norm": 0.8429688811302185,
      "learning_rate": 0.00019999872736238097,
      "loss": 1.0762,
      "step": 74
    },
    {
      "epoch": 0.008202996828174559,
      "grad_norm": 0.8408651351928711,
      "learning_rate": 0.0001999986688579921,
      "loss": 0.6704,
      "step": 75
    },
    {
      "epoch": 0.008312370119216888,
      "grad_norm": 0.7103726267814636,
      "learning_rate": 0.0001999986090389097,
      "loss": 0.8437,
      "step": 76
    },
    {
      "epoch": 0.008421743410259214,
      "grad_norm": 1.084578275680542,
      "learning_rate": 0.00019999854790513452,
      "loss": 0.7259,
      "step": 77
    },
    {
      "epoch": 0.008531116701301543,
      "grad_norm": 0.8537347316741943,
      "learning_rate": 0.0001999984854566673,
      "loss": 0.8551,
      "step": 78
    },
    {
      "epoch": 0.00864048999234387,
      "grad_norm": 1.005993366241455,
      "learning_rate": 0.00019999842169350897,
      "loss": 0.9122,
      "step": 79
    },
    {
      "epoch": 0.008749863283386197,
      "grad_norm": 1.0594606399536133,
      "learning_rate": 0.00019999835661566032,
      "loss": 0.7878,
      "step": 80
    },
    {
      "epoch": 0.008859236574428525,
      "grad_norm": 0.9891486763954163,
      "learning_rate": 0.00019999829022312218,
      "loss": 0.9339,
      "step": 81
    },
    {
      "epoch": 0.008968609865470852,
      "grad_norm": 1.752136468887329,
      "learning_rate": 0.00019999822251589547,
      "loss": 0.637,
      "step": 82
    },
    {
      "epoch": 0.009077983156513179,
      "grad_norm": 1.3982586860656738,
      "learning_rate": 0.00019999815349398104,
      "loss": 0.8485,
      "step": 83
    },
    {
      "epoch": 0.009187356447555507,
      "grad_norm": 1.1201657056808472,
      "learning_rate": 0.00019999808315737983,
      "loss": 0.8483,
      "step": 84
    },
    {
      "epoch": 0.009296729738597834,
      "grad_norm": 1.1798042058944702,
      "learning_rate": 0.00019999801150609271,
      "loss": 1.1654,
      "step": 85
    },
    {
      "epoch": 0.009406103029640163,
      "grad_norm": 1.119722843170166,
      "learning_rate": 0.00019999793854012072,
      "loss": 0.9427,
      "step": 86
    },
    {
      "epoch": 0.00951547632068249,
      "grad_norm": 1.9652173519134521,
      "learning_rate": 0.0001999978642594647,
      "loss": 1.0173,
      "step": 87
    },
    {
      "epoch": 0.009624849611724816,
      "grad_norm": 0.8673993349075317,
      "learning_rate": 0.00019999778866412572,
      "loss": 0.843,
      "step": 88
    },
    {
      "epoch": 0.009734222902767145,
      "grad_norm": 0.9615687727928162,
      "learning_rate": 0.00019999771175410475,
      "loss": 1.0409,
      "step": 89
    },
    {
      "epoch": 0.009843596193809472,
      "grad_norm": 0.9303264021873474,
      "learning_rate": 0.00019999763352940278,
      "loss": 1.0045,
      "step": 90
    },
    {
      "epoch": 0.009952969484851798,
      "grad_norm": 1.1048322916030884,
      "learning_rate": 0.00019999755399002087,
      "loss": 0.9833,
      "step": 91
    },
    {
      "epoch": 0.010062342775894127,
      "grad_norm": 0.7181215286254883,
      "learning_rate": 0.00019999747313596003,
      "loss": 0.8382,
      "step": 92
    },
    {
      "epoch": 0.010171716066936454,
      "grad_norm": 1.0009384155273438,
      "learning_rate": 0.00019999739096722134,
      "loss": 0.8917,
      "step": 93
    },
    {
      "epoch": 0.010281089357978782,
      "grad_norm": 0.7550287842750549,
      "learning_rate": 0.00019999730748380588,
      "loss": 0.9104,
      "step": 94
    },
    {
      "epoch": 0.010390462649021109,
      "grad_norm": 1.126756191253662,
      "learning_rate": 0.00019999722268571475,
      "loss": 0.8792,
      "step": 95
    },
    {
      "epoch": 0.010499835940063436,
      "grad_norm": 1.0714164972305298,
      "learning_rate": 0.00019999713657294907,
      "loss": 0.9516,
      "step": 96
    },
    {
      "epoch": 0.010609209231105764,
      "grad_norm": 1.324127197265625,
      "learning_rate": 0.00019999704914550997,
      "loss": 0.997,
      "step": 97
    },
    {
      "epoch": 0.010718582522148091,
      "grad_norm": 0.8866165280342102,
      "learning_rate": 0.00019999696040339857,
      "loss": 0.7956,
      "step": 98
    },
    {
      "epoch": 0.01082795581319042,
      "grad_norm": 0.9012518525123596,
      "learning_rate": 0.00019999687034661607,
      "loss": 0.9225,
      "step": 99
    },
    {
      "epoch": 0.010937329104232747,
      "grad_norm": 0.7945853471755981,
      "learning_rate": 0.00019999677897516364,
      "loss": 1.1462,
      "step": 100
    },
    {
      "epoch": 0.011046702395275073,
      "grad_norm": 1.0762516260147095,
      "learning_rate": 0.0001999966862890425,
      "loss": 0.8994,
      "step": 101
    },
    {
      "epoch": 0.011156075686317402,
      "grad_norm": 0.872011661529541,
      "learning_rate": 0.00019999659228825384,
      "loss": 1.169,
      "step": 102
    },
    {
      "epoch": 0.011265448977359729,
      "grad_norm": 1.1329362392425537,
      "learning_rate": 0.0001999964969727989,
      "loss": 0.6135,
      "step": 103
    },
    {
      "epoch": 0.011374822268402056,
      "grad_norm": 1.047389268875122,
      "learning_rate": 0.00019999640034267898,
      "loss": 1.0515,
      "step": 104
    },
    {
      "epoch": 0.011484195559444384,
      "grad_norm": 1.3864418268203735,
      "learning_rate": 0.00019999630239789527,
      "loss": 0.6238,
      "step": 105
    },
    {
      "epoch": 0.01159356885048671,
      "grad_norm": 0.9831883311271667,
      "learning_rate": 0.00019999620313844915,
      "loss": 1.1318,
      "step": 106
    },
    {
      "epoch": 0.01170294214152904,
      "grad_norm": 1.0314894914627075,
      "learning_rate": 0.00019999610256434184,
      "loss": 0.7566,
      "step": 107
    },
    {
      "epoch": 0.011812315432571366,
      "grad_norm": 1.4733610153198242,
      "learning_rate": 0.00019999600067557472,
      "loss": 0.7978,
      "step": 108
    },
    {
      "epoch": 0.011921688723613693,
      "grad_norm": 0.9159018993377686,
      "learning_rate": 0.0001999958974721491,
      "loss": 0.8544,
      "step": 109
    },
    {
      "epoch": 0.012031062014656022,
      "grad_norm": 0.8146981596946716,
      "learning_rate": 0.00019999579295406635,
      "loss": 0.5639,
      "step": 110
    },
    {
      "epoch": 0.012140435305698348,
      "grad_norm": 0.8243168592453003,
      "learning_rate": 0.0001999956871213278,
      "loss": 0.7903,
      "step": 111
    },
    {
      "epoch": 0.012249808596740675,
      "grad_norm": 0.980814516544342,
      "learning_rate": 0.00019999557997393494,
      "loss": 1.01,
      "step": 112
    },
    {
      "epoch": 0.012359181887783004,
      "grad_norm": 1.437961459159851,
      "learning_rate": 0.0001999954715118891,
      "loss": 0.8245,
      "step": 113
    },
    {
      "epoch": 0.01246855517882533,
      "grad_norm": 1.483574390411377,
      "learning_rate": 0.0001999953617351917,
      "loss": 0.9152,
      "step": 114
    },
    {
      "epoch": 0.012577928469867659,
      "grad_norm": 0.9745296835899353,
      "learning_rate": 0.00019999525064384423,
      "loss": 0.7377,
      "step": 115
    },
    {
      "epoch": 0.012687301760909986,
      "grad_norm": 1.2854357957839966,
      "learning_rate": 0.00019999513823784813,
      "loss": 1.0215,
      "step": 116
    },
    {
      "epoch": 0.012796675051952313,
      "grad_norm": 1.4880210161209106,
      "learning_rate": 0.00019999502451720487,
      "loss": 0.6604,
      "step": 117
    },
    {
      "epoch": 0.012906048342994641,
      "grad_norm": 1.0523297786712646,
      "learning_rate": 0.00019999490948191594,
      "loss": 0.8873,
      "step": 118
    },
    {
      "epoch": 0.013015421634036968,
      "grad_norm": 1.0283764600753784,
      "learning_rate": 0.0001999947931319829,
      "loss": 0.8407,
      "step": 119
    },
    {
      "epoch": 0.013124794925079295,
      "grad_norm": 1.0384728908538818,
      "learning_rate": 0.0001999946754674072,
      "loss": 0.9039,
      "step": 120
    },
    {
      "epoch": 0.013234168216121623,
      "grad_norm": 0.8750423789024353,
      "learning_rate": 0.00019999455648819049,
      "loss": 1.0058,
      "step": 121
    },
    {
      "epoch": 0.01334354150716395,
      "grad_norm": 0.8427900075912476,
      "learning_rate": 0.00019999443619433423,
      "loss": 1.0078,
      "step": 122
    },
    {
      "epoch": 0.013452914798206279,
      "grad_norm": 1.3203353881835938,
      "learning_rate": 0.00019999431458584004,
      "loss": 0.8924,
      "step": 123
    },
    {
      "epoch": 0.013562288089248606,
      "grad_norm": 0.7723014950752258,
      "learning_rate": 0.00019999419166270954,
      "loss": 0.8432,
      "step": 124
    },
    {
      "epoch": 0.013671661380290932,
      "grad_norm": 0.9909713864326477,
      "learning_rate": 0.00019999406742494434,
      "loss": 0.8528,
      "step": 125
    },
    {
      "epoch": 0.01378103467133326,
      "grad_norm": 1.0303891897201538,
      "learning_rate": 0.00019999394187254606,
      "loss": 0.6699,
      "step": 126
    },
    {
      "epoch": 0.013890407962375588,
      "grad_norm": 0.8098687529563904,
      "learning_rate": 0.00019999381500551632,
      "loss": 1.0615,
      "step": 127
    },
    {
      "epoch": 0.013999781253417916,
      "grad_norm": 0.8698800206184387,
      "learning_rate": 0.00019999368682385686,
      "loss": 0.7004,
      "step": 128
    },
    {
      "epoch": 0.014109154544460243,
      "grad_norm": 1.163340449333191,
      "learning_rate": 0.00019999355732756936,
      "loss": 0.7752,
      "step": 129
    },
    {
      "epoch": 0.01421852783550257,
      "grad_norm": 1.1491297483444214,
      "learning_rate": 0.00019999342651665542,
      "loss": 1.0112,
      "step": 130
    },
    {
      "epoch": 0.014327901126544898,
      "grad_norm": 0.7571056485176086,
      "learning_rate": 0.00019999329439111688,
      "loss": 1.0722,
      "step": 131
    },
    {
      "epoch": 0.014437274417587225,
      "grad_norm": 1.1919002532958984,
      "learning_rate": 0.00019999316095095542,
      "loss": 0.7939,
      "step": 132
    },
    {
      "epoch": 0.014546647708629552,
      "grad_norm": 1.0839415788650513,
      "learning_rate": 0.0001999930261961728,
      "loss": 0.7247,
      "step": 133
    },
    {
      "epoch": 0.01465602099967188,
      "grad_norm": 1.123969316482544,
      "learning_rate": 0.00019999289012677079,
      "loss": 0.7543,
      "step": 134
    },
    {
      "epoch": 0.014765394290714207,
      "grad_norm": 1.1143224239349365,
      "learning_rate": 0.0001999927527427512,
      "loss": 1.0124,
      "step": 135
    },
    {
      "epoch": 0.014874767581756536,
      "grad_norm": 1.0003845691680908,
      "learning_rate": 0.00019999261404411579,
      "loss": 0.7766,
      "step": 136
    },
    {
      "epoch": 0.014984140872798863,
      "grad_norm": 1.154555082321167,
      "learning_rate": 0.00019999247403086642,
      "loss": 0.8062,
      "step": 137
    },
    {
      "epoch": 0.01509351416384119,
      "grad_norm": 1.1724870204925537,
      "learning_rate": 0.00019999233270300492,
      "loss": 0.7935,
      "step": 138
    },
    {
      "epoch": 0.015202887454883518,
      "grad_norm": 0.812342643737793,
      "learning_rate": 0.00019999219006053317,
      "loss": 0.7218,
      "step": 139
    },
    {
      "epoch": 0.015312260745925845,
      "grad_norm": 1.1357048749923706,
      "learning_rate": 0.00019999204610345302,
      "loss": 0.7117,
      "step": 140
    },
    {
      "epoch": 0.015421634036968172,
      "grad_norm": 0.9869748950004578,
      "learning_rate": 0.0001999919008317664,
      "loss": 0.9765,
      "step": 141
    },
    {
      "epoch": 0.0155310073280105,
      "grad_norm": 0.977894127368927,
      "learning_rate": 0.00019999175424547513,
      "loss": 0.7474,
      "step": 142
    },
    {
      "epoch": 0.01564038061905283,
      "grad_norm": 0.9802875518798828,
      "learning_rate": 0.00019999160634458124,
      "loss": 0.7464,
      "step": 143
    },
    {
      "epoch": 0.015749753910095154,
      "grad_norm": 0.8524045348167419,
      "learning_rate": 0.0001999914571290866,
      "loss": 0.7183,
      "step": 144
    },
    {
      "epoch": 0.015859127201137482,
      "grad_norm": 1.2041178941726685,
      "learning_rate": 0.0001999913065989932,
      "loss": 0.8245,
      "step": 145
    },
    {
      "epoch": 0.01596850049217981,
      "grad_norm": 1.451375126838684,
      "learning_rate": 0.00019999115475430304,
      "loss": 0.8932,
      "step": 146
    },
    {
      "epoch": 0.016077873783222136,
      "grad_norm": 0.8621544241905212,
      "learning_rate": 0.00019999100159501812,
      "loss": 1.1615,
      "step": 147
    },
    {
      "epoch": 0.016187247074264464,
      "grad_norm": 1.1287329196929932,
      "learning_rate": 0.00019999084712114042,
      "loss": 1.1429,
      "step": 148
    },
    {
      "epoch": 0.016296620365306793,
      "grad_norm": 1.1720576286315918,
      "learning_rate": 0.00019999069133267195,
      "loss": 0.5356,
      "step": 149
    },
    {
      "epoch": 0.016405993656349118,
      "grad_norm": 0.7974927425384521,
      "learning_rate": 0.00019999053422961482,
      "loss": 1.082,
      "step": 150
    },
    {
      "epoch": 0.016515366947391447,
      "grad_norm": 0.86858731508255,
      "learning_rate": 0.00019999037581197108,
      "loss": 0.7021,
      "step": 151
    },
    {
      "epoch": 0.016624740238433775,
      "grad_norm": 0.8884678483009338,
      "learning_rate": 0.00019999021607974276,
      "loss": 0.8077,
      "step": 152
    },
    {
      "epoch": 0.0167341135294761,
      "grad_norm": 1.3161729574203491,
      "learning_rate": 0.00019999005503293203,
      "loss": 0.6789,
      "step": 153
    },
    {
      "epoch": 0.01684348682051843,
      "grad_norm": 1.1194474697113037,
      "learning_rate": 0.00019998989267154093,
      "loss": 0.8708,
      "step": 154
    },
    {
      "epoch": 0.016952860111560757,
      "grad_norm": 1.1400177478790283,
      "learning_rate": 0.0001999897289955717,
      "loss": 0.8416,
      "step": 155
    },
    {
      "epoch": 0.017062233402603086,
      "grad_norm": 1.155961513519287,
      "learning_rate": 0.0001999895640050264,
      "loss": 0.9628,
      "step": 156
    },
    {
      "epoch": 0.01717160669364541,
      "grad_norm": 1.5118356943130493,
      "learning_rate": 0.00019998939769990727,
      "loss": 0.9591,
      "step": 157
    },
    {
      "epoch": 0.01728097998468774,
      "grad_norm": 1.029440999031067,
      "learning_rate": 0.0001999892300802164,
      "loss": 0.5659,
      "step": 158
    },
    {
      "epoch": 0.017390353275730068,
      "grad_norm": 1.3784666061401367,
      "learning_rate": 0.00019998906114595608,
      "loss": 1.018,
      "step": 159
    },
    {
      "epoch": 0.017499726566772393,
      "grad_norm": 0.9848626852035522,
      "learning_rate": 0.00019998889089712849,
      "loss": 0.8016,
      "step": 160
    },
    {
      "epoch": 0.01760909985781472,
      "grad_norm": 1.188879132270813,
      "learning_rate": 0.0001999887193337359,
      "loss": 1.2011,
      "step": 161
    },
    {
      "epoch": 0.01771847314885705,
      "grad_norm": 0.9314888119697571,
      "learning_rate": 0.00019998854645578057,
      "loss": 0.7455,
      "step": 162
    },
    {
      "epoch": 0.017827846439899375,
      "grad_norm": 1.001659870147705,
      "learning_rate": 0.00019998837226326469,
      "loss": 1.033,
      "step": 163
    },
    {
      "epoch": 0.017937219730941704,
      "grad_norm": 1.4195637702941895,
      "learning_rate": 0.00019998819675619064,
      "loss": 0.8527,
      "step": 164
    },
    {
      "epoch": 0.018046593021984032,
      "grad_norm": 0.8885000944137573,
      "learning_rate": 0.00019998801993456069,
      "loss": 0.6358,
      "step": 165
    },
    {
      "epoch": 0.018155966313026357,
      "grad_norm": 1.070360779762268,
      "learning_rate": 0.0001999878417983772,
      "loss": 0.7843,
      "step": 166
    },
    {
      "epoch": 0.018265339604068686,
      "grad_norm": 1.1388875246047974,
      "learning_rate": 0.00019998766234764247,
      "loss": 0.9364,
      "step": 167
    },
    {
      "epoch": 0.018374712895111014,
      "grad_norm": 2.4844179153442383,
      "learning_rate": 0.00019998748158235884,
      "loss": 0.6608,
      "step": 168
    },
    {
      "epoch": 0.018484086186153343,
      "grad_norm": 1.0103005170822144,
      "learning_rate": 0.00019998729950252876,
      "loss": 0.7691,
      "step": 169
    },
    {
      "epoch": 0.018593459477195668,
      "grad_norm": 0.9184209704399109,
      "learning_rate": 0.00019998711610815458,
      "loss": 0.914,
      "step": 170
    },
    {
      "epoch": 0.018702832768237997,
      "grad_norm": 1.0094612836837769,
      "learning_rate": 0.00019998693139923867,
      "loss": 0.9174,
      "step": 171
    },
    {
      "epoch": 0.018812206059280325,
      "grad_norm": 0.7898897528648376,
      "learning_rate": 0.00019998674537578353,
      "loss": 0.9579,
      "step": 172
    },
    {
      "epoch": 0.01892157935032265,
      "grad_norm": 1.0184580087661743,
      "learning_rate": 0.00019998655803779163,
      "loss": 0.8242,
      "step": 173
    },
    {
      "epoch": 0.01903095264136498,
      "grad_norm": 1.002568244934082,
      "learning_rate": 0.00019998636938526533,
      "loss": 0.9002,
      "step": 174
    },
    {
      "epoch": 0.019140325932407307,
      "grad_norm": 0.7966347932815552,
      "learning_rate": 0.00019998617941820716,
      "loss": 1.0177,
      "step": 175
    },
    {
      "epoch": 0.019249699223449632,
      "grad_norm": 1.333112359046936,
      "learning_rate": 0.00019998598813661964,
      "loss": 0.6221,
      "step": 176
    },
    {
      "epoch": 0.01935907251449196,
      "grad_norm": 1.2348626852035522,
      "learning_rate": 0.00019998579554050526,
      "loss": 0.6833,
      "step": 177
    },
    {
      "epoch": 0.01946844580553429,
      "grad_norm": 1.1256965398788452,
      "learning_rate": 0.00019998560162986655,
      "loss": 0.9427,
      "step": 178
    },
    {
      "epoch": 0.019577819096576615,
      "grad_norm": 1.006744146347046,
      "learning_rate": 0.00019998540640470608,
      "loss": 0.8733,
      "step": 179
    },
    {
      "epoch": 0.019687192387618943,
      "grad_norm": 0.9952765107154846,
      "learning_rate": 0.00019998520986502636,
      "loss": 0.8656,
      "step": 180
    },
    {
      "epoch": 0.01979656567866127,
      "grad_norm": 0.9037217497825623,
      "learning_rate": 0.00019998501201083004,
      "loss": 0.9612,
      "step": 181
    },
    {
      "epoch": 0.019905938969703597,
      "grad_norm": 1.0065454244613647,
      "learning_rate": 0.0001999848128421197,
      "loss": 0.7898,
      "step": 182
    },
    {
      "epoch": 0.020015312260745925,
      "grad_norm": 1.0890108346939087,
      "learning_rate": 0.00019998461235889797,
      "loss": 0.7269,
      "step": 183
    },
    {
      "epoch": 0.020124685551788254,
      "grad_norm": 1.2539864778518677,
      "learning_rate": 0.00019998441056116745,
      "loss": 0.7934,
      "step": 184
    },
    {
      "epoch": 0.020234058842830582,
      "grad_norm": 0.9602129459381104,
      "learning_rate": 0.00019998420744893084,
      "loss": 0.549,
      "step": 185
    },
    {
      "epoch": 0.020343432133872907,
      "grad_norm": 1.4105061292648315,
      "learning_rate": 0.00019998400302219076,
      "loss": 1.005,
      "step": 186
    },
    {
      "epoch": 0.020452805424915236,
      "grad_norm": 1.430650234222412,
      "learning_rate": 0.0001999837972809499,
      "loss": 0.7051,
      "step": 187
    },
    {
      "epoch": 0.020562178715957564,
      "grad_norm": 1.191211223602295,
      "learning_rate": 0.00019998359022521106,
      "loss": 0.7129,
      "step": 188
    },
    {
      "epoch": 0.02067155200699989,
      "grad_norm": 0.9433074593544006,
      "learning_rate": 0.00019998338185497682,
      "loss": 0.7383,
      "step": 189
    },
    {
      "epoch": 0.020780925298042218,
      "grad_norm": 1.2458714246749878,
      "learning_rate": 0.00019998317217025005,
      "loss": 0.7533,
      "step": 190
    },
    {
      "epoch": 0.020890298589084547,
      "grad_norm": 1.443598747253418,
      "learning_rate": 0.00019998296117103341,
      "loss": 0.7505,
      "step": 191
    },
    {
      "epoch": 0.02099967188012687,
      "grad_norm": 0.9617491364479065,
      "learning_rate": 0.00019998274885732971,
      "loss": 0.8154,
      "step": 192
    },
    {
      "epoch": 0.0211090451711692,
      "grad_norm": 1.0256359577178955,
      "learning_rate": 0.00019998253522914174,
      "loss": 0.8709,
      "step": 193
    },
    {
      "epoch": 0.02121841846221153,
      "grad_norm": 1.1407520771026611,
      "learning_rate": 0.0001999823202864723,
      "loss": 1.0066,
      "step": 194
    },
    {
      "epoch": 0.021327791753253854,
      "grad_norm": 0.9075395464897156,
      "learning_rate": 0.00019998210402932424,
      "loss": 0.7433,
      "step": 195
    },
    {
      "epoch": 0.021437165044296182,
      "grad_norm": 1.1892637014389038,
      "learning_rate": 0.0001999818864577004,
      "loss": 0.6049,
      "step": 196
    },
    {
      "epoch": 0.02154653833533851,
      "grad_norm": 1.0141085386276245,
      "learning_rate": 0.0001999816675716036,
      "loss": 1.0684,
      "step": 197
    },
    {
      "epoch": 0.02165591162638084,
      "grad_norm": 1.0636556148529053,
      "learning_rate": 0.00019998144737103682,
      "loss": 1.0034,
      "step": 198
    },
    {
      "epoch": 0.021765284917423165,
      "grad_norm": 0.9643628597259521,
      "learning_rate": 0.0001999812258560028,
      "loss": 0.9938,
      "step": 199
    },
    {
      "epoch": 0.021874658208465493,
      "grad_norm": 0.9733682870864868,
      "learning_rate": 0.00019998100302650457,
      "loss": 1.0145,
      "step": 200
    },
    {
      "epoch": 0.021874658208465493,
      "eval_loss": 0.8068432807922363,
      "eval_runtime": 40.9547,
      "eval_samples_per_second": 17.971,
      "eval_steps_per_second": 4.493,
      "step": 200
    },
    {
      "epoch": 0.02198403149950782,
      "grad_norm": 0.89620041847229,
      "learning_rate": 0.00019998077888254501,
      "loss": 0.8309,
      "step": 201
    },
    {
      "epoch": 0.022093404790550147,
      "grad_norm": 1.041070580482483,
      "learning_rate": 0.0001999805534241271,
      "loss": 0.8251,
      "step": 202
    },
    {
      "epoch": 0.022202778081592475,
      "grad_norm": 0.8770344853401184,
      "learning_rate": 0.00019998032665125378,
      "loss": 0.9149,
      "step": 203
    },
    {
      "epoch": 0.022312151372634804,
      "grad_norm": 0.9978107810020447,
      "learning_rate": 0.000199980098563928,
      "loss": 0.8845,
      "step": 204
    },
    {
      "epoch": 0.02242152466367713,
      "grad_norm": 1.1167197227478027,
      "learning_rate": 0.00019997986916215284,
      "loss": 0.9254,
      "step": 205
    },
    {
      "epoch": 0.022530897954719457,
      "grad_norm": 1.0514531135559082,
      "learning_rate": 0.00019997963844593127,
      "loss": 0.8273,
      "step": 206
    },
    {
      "epoch": 0.022640271245761786,
      "grad_norm": 1.027596116065979,
      "learning_rate": 0.0001999794064152663,
      "loss": 0.867,
      "step": 207
    },
    {
      "epoch": 0.02274964453680411,
      "grad_norm": 1.3077362775802612,
      "learning_rate": 0.00019997917307016102,
      "loss": 0.9528,
      "step": 208
    },
    {
      "epoch": 0.02285901782784644,
      "grad_norm": 1.2617202997207642,
      "learning_rate": 0.0001999789384106185,
      "loss": 0.4163,
      "step": 209
    },
    {
      "epoch": 0.022968391118888768,
      "grad_norm": 1.9169830083847046,
      "learning_rate": 0.00019997870243664177,
      "loss": 0.8746,
      "step": 210
    },
    {
      "epoch": 0.023077764409931093,
      "grad_norm": 0.9455872774124146,
      "learning_rate": 0.00019997846514823396,
      "loss": 0.9282,
      "step": 211
    },
    {
      "epoch": 0.02318713770097342,
      "grad_norm": 1.0044574737548828,
      "learning_rate": 0.00019997822654539826,
      "loss": 0.8485,
      "step": 212
    },
    {
      "epoch": 0.02329651099201575,
      "grad_norm": 0.9601938128471375,
      "learning_rate": 0.00019997798662813772,
      "loss": 0.6501,
      "step": 213
    },
    {
      "epoch": 0.02340588428305808,
      "grad_norm": 0.7503620982170105,
      "learning_rate": 0.0001999777453964555,
      "loss": 0.9953,
      "step": 214
    },
    {
      "epoch": 0.023515257574100404,
      "grad_norm": 0.8733282685279846,
      "learning_rate": 0.0001999775028503548,
      "loss": 0.7488,
      "step": 215
    },
    {
      "epoch": 0.023624630865142732,
      "grad_norm": 1.1373885869979858,
      "learning_rate": 0.00019997725898983883,
      "loss": 0.8603,
      "step": 216
    },
    {
      "epoch": 0.02373400415618506,
      "grad_norm": 1.1404668092727661,
      "learning_rate": 0.00019997701381491072,
      "loss": 0.8454,
      "step": 217
    },
    {
      "epoch": 0.023843377447227386,
      "grad_norm": 0.7852329015731812,
      "learning_rate": 0.00019997676732557378,
      "loss": 0.5155,
      "step": 218
    },
    {
      "epoch": 0.023952750738269715,
      "grad_norm": 0.6994953751564026,
      "learning_rate": 0.0001999765195218312,
      "loss": 0.8015,
      "step": 219
    },
    {
      "epoch": 0.024062124029312043,
      "grad_norm": 1.1219515800476074,
      "learning_rate": 0.00019997627040368622,
      "loss": 0.94,
      "step": 220
    },
    {
      "epoch": 0.024171497320354368,
      "grad_norm": 1.3120551109313965,
      "learning_rate": 0.00019997601997114218,
      "loss": 0.9221,
      "step": 221
    },
    {
      "epoch": 0.024280870611396697,
      "grad_norm": 1.1464701890945435,
      "learning_rate": 0.00019997576822420232,
      "loss": 0.6533,
      "step": 222
    },
    {
      "epoch": 0.024390243902439025,
      "grad_norm": 0.9645900726318359,
      "learning_rate": 0.00019997551516286999,
      "loss": 1.0048,
      "step": 223
    },
    {
      "epoch": 0.02449961719348135,
      "grad_norm": 0.811614990234375,
      "learning_rate": 0.0001999752607871485,
      "loss": 1.1218,
      "step": 224
    },
    {
      "epoch": 0.02460899048452368,
      "grad_norm": 1.0914621353149414,
      "learning_rate": 0.0001999750050970411,
      "loss": 0.765,
      "step": 225
    },
    {
      "epoch": 0.024718363775566007,
      "grad_norm": 1.0596243143081665,
      "learning_rate": 0.00019997474809255135,
      "loss": 1.0341,
      "step": 226
    },
    {
      "epoch": 0.024827737066608336,
      "grad_norm": 1.055033564567566,
      "learning_rate": 0.00019997448977368247,
      "loss": 0.6386,
      "step": 227
    },
    {
      "epoch": 0.02493711035765066,
      "grad_norm": 0.9922929406166077,
      "learning_rate": 0.0001999742301404379,
      "loss": 0.7942,
      "step": 228
    },
    {
      "epoch": 0.02504648364869299,
      "grad_norm": 1.2093638181686401,
      "learning_rate": 0.00019997396919282107,
      "loss": 0.8164,
      "step": 229
    },
    {
      "epoch": 0.025155856939735318,
      "grad_norm": 1.3952484130859375,
      "learning_rate": 0.0001999737069308354,
      "loss": 0.8928,
      "step": 230
    },
    {
      "epoch": 0.025265230230777643,
      "grad_norm": 0.9438846707344055,
      "learning_rate": 0.00019997344335448433,
      "loss": 0.6457,
      "step": 231
    },
    {
      "epoch": 0.02537460352181997,
      "grad_norm": 0.7343907952308655,
      "learning_rate": 0.00019997317846377134,
      "loss": 0.8762,
      "step": 232
    },
    {
      "epoch": 0.0254839768128623,
      "grad_norm": 1.0288769006729126,
      "learning_rate": 0.00019997291225869987,
      "loss": 0.7636,
      "step": 233
    },
    {
      "epoch": 0.025593350103904625,
      "grad_norm": 1.232852578163147,
      "learning_rate": 0.00019997264473927347,
      "loss": 0.6876,
      "step": 234
    },
    {
      "epoch": 0.025702723394946954,
      "grad_norm": 1.0084220170974731,
      "learning_rate": 0.00019997237590549567,
      "loss": 0.8275,
      "step": 235
    },
    {
      "epoch": 0.025812096685989282,
      "grad_norm": 1.7499910593032837,
      "learning_rate": 0.00019997210575736999,
      "loss": 1.1544,
      "step": 236
    },
    {
      "epoch": 0.025921469977031607,
      "grad_norm": 0.9005192518234253,
      "learning_rate": 0.00019997183429489992,
      "loss": 0.9512,
      "step": 237
    },
    {
      "epoch": 0.026030843268073936,
      "grad_norm": 1.054895281791687,
      "learning_rate": 0.0001999715615180891,
      "loss": 0.7701,
      "step": 238
    },
    {
      "epoch": 0.026140216559116265,
      "grad_norm": 0.9881554245948792,
      "learning_rate": 0.00019997128742694107,
      "loss": 0.9372,
      "step": 239
    },
    {
      "epoch": 0.02624958985015859,
      "grad_norm": 0.9707517027854919,
      "learning_rate": 0.00019997101202145947,
      "loss": 0.978,
      "step": 240
    },
    {
      "epoch": 0.026358963141200918,
      "grad_norm": 1.2869802713394165,
      "learning_rate": 0.0001999707353016479,
      "loss": 1.1234,
      "step": 241
    },
    {
      "epoch": 0.026468336432243247,
      "grad_norm": 1.2063279151916504,
      "learning_rate": 0.00019997045726751001,
      "loss": 0.7118,
      "step": 242
    },
    {
      "epoch": 0.026577709723285575,
      "grad_norm": 0.9686263799667358,
      "learning_rate": 0.00019997017791904947,
      "loss": 0.8869,
      "step": 243
    },
    {
      "epoch": 0.0266870830143279,
      "grad_norm": 0.963753342628479,
      "learning_rate": 0.00019996989725626992,
      "loss": 0.8479,
      "step": 244
    },
    {
      "epoch": 0.02679645630537023,
      "grad_norm": 0.8817402720451355,
      "learning_rate": 0.00019996961527917506,
      "loss": 0.5295,
      "step": 245
    },
    {
      "epoch": 0.026905829596412557,
      "grad_norm": 1.706606149673462,
      "learning_rate": 0.00019996933198776858,
      "loss": 0.7777,
      "step": 246
    },
    {
      "epoch": 0.027015202887454882,
      "grad_norm": 0.8349090814590454,
      "learning_rate": 0.00019996904738205426,
      "loss": 0.836,
      "step": 247
    },
    {
      "epoch": 0.02712457617849721,
      "grad_norm": 0.9602643251419067,
      "learning_rate": 0.00019996876146203578,
      "loss": 1.0578,
      "step": 248
    },
    {
      "epoch": 0.02723394946953954,
      "grad_norm": 0.8937216401100159,
      "learning_rate": 0.00019996847422771693,
      "loss": 0.8529,
      "step": 249
    },
    {
      "epoch": 0.027343322760581865,
      "grad_norm": 0.9380630254745483,
      "learning_rate": 0.00019996818567910148,
      "loss": 0.8573,
      "step": 250
    },
    {
      "epoch": 0.027452696051624193,
      "grad_norm": 1.332655668258667,
      "learning_rate": 0.00019996789581619323,
      "loss": 0.629,
      "step": 251
    },
    {
      "epoch": 0.02756206934266652,
      "grad_norm": 1.4816393852233887,
      "learning_rate": 0.000199967604638996,
      "loss": 0.7475,
      "step": 252
    },
    {
      "epoch": 0.027671442633708847,
      "grad_norm": 1.049055814743042,
      "learning_rate": 0.0001999673121475136,
      "loss": 0.7129,
      "step": 253
    },
    {
      "epoch": 0.027780815924751175,
      "grad_norm": 1.3890293836593628,
      "learning_rate": 0.00019996701834174986,
      "loss": 1.0256,
      "step": 254
    },
    {
      "epoch": 0.027890189215793504,
      "grad_norm": 1.0529813766479492,
      "learning_rate": 0.00019996672322170867,
      "loss": 1.0666,
      "step": 255
    },
    {
      "epoch": 0.027999562506835832,
      "grad_norm": 0.8624351024627686,
      "learning_rate": 0.0001999664267873939,
      "loss": 0.6948,
      "step": 256
    },
    {
      "epoch": 0.028108935797878157,
      "grad_norm": 0.8577688336372375,
      "learning_rate": 0.00019996612903880947,
      "loss": 0.82,
      "step": 257
    },
    {
      "epoch": 0.028218309088920486,
      "grad_norm": 0.8573757410049438,
      "learning_rate": 0.00019996582997595924,
      "loss": 0.8273,
      "step": 258
    },
    {
      "epoch": 0.028327682379962815,
      "grad_norm": 1.2395519018173218,
      "learning_rate": 0.0001999655295988472,
      "loss": 0.8064,
      "step": 259
    },
    {
      "epoch": 0.02843705567100514,
      "grad_norm": 0.8964936137199402,
      "learning_rate": 0.00019996522790747726,
      "loss": 0.7224,
      "step": 260
    },
    {
      "epoch": 0.028546428962047468,
      "grad_norm": 0.9282931685447693,
      "learning_rate": 0.00019996492490185341,
      "loss": 0.9585,
      "step": 261
    },
    {
      "epoch": 0.028655802253089797,
      "grad_norm": 1.1618013381958008,
      "learning_rate": 0.00019996462058197962,
      "loss": 0.7717,
      "step": 262
    },
    {
      "epoch": 0.028765175544132122,
      "grad_norm": 0.9413585662841797,
      "learning_rate": 0.00019996431494785993,
      "loss": 0.7748,
      "step": 263
    },
    {
      "epoch": 0.02887454883517445,
      "grad_norm": 1.3444674015045166,
      "learning_rate": 0.0001999640079994983,
      "loss": 1.0287,
      "step": 264
    },
    {
      "epoch": 0.02898392212621678,
      "grad_norm": 1.3082046508789062,
      "learning_rate": 0.00019996369973689876,
      "loss": 0.7817,
      "step": 265
    },
    {
      "epoch": 0.029093295417259104,
      "grad_norm": 1.4798815250396729,
      "learning_rate": 0.0001999633901600654,
      "loss": 0.791,
      "step": 266
    },
    {
      "epoch": 0.029202668708301432,
      "grad_norm": 1.3128074407577515,
      "learning_rate": 0.00019996307926900233,
      "loss": 0.9972,
      "step": 267
    },
    {
      "epoch": 0.02931204199934376,
      "grad_norm": 1.3363100290298462,
      "learning_rate": 0.00019996276706371355,
      "loss": 0.7227,
      "step": 268
    },
    {
      "epoch": 0.029421415290386086,
      "grad_norm": 1.2146847248077393,
      "learning_rate": 0.00019996245354420323,
      "loss": 0.7839,
      "step": 269
    },
    {
      "epoch": 0.029530788581428415,
      "grad_norm": 1.0506778955459595,
      "learning_rate": 0.00019996213871047543,
      "loss": 0.8816,
      "step": 270
    },
    {
      "epoch": 0.029640161872470743,
      "grad_norm": 1.0352805852890015,
      "learning_rate": 0.00019996182256253435,
      "loss": 0.9029,
      "step": 271
    },
    {
      "epoch": 0.02974953516351307,
      "grad_norm": 1.319678544998169,
      "learning_rate": 0.00019996150510038412,
      "loss": 1.0377,
      "step": 272
    },
    {
      "epoch": 0.029858908454555397,
      "grad_norm": 1.0857889652252197,
      "learning_rate": 0.00019996118632402892,
      "loss": 0.8303,
      "step": 273
    },
    {
      "epoch": 0.029968281745597725,
      "grad_norm": 1.0412633419036865,
      "learning_rate": 0.00019996086623347292,
      "loss": 0.7897,
      "step": 274
    },
    {
      "epoch": 0.030077655036640054,
      "grad_norm": 0.9532299637794495,
      "learning_rate": 0.00019996054482872036,
      "loss": 0.834,
      "step": 275
    },
    {
      "epoch": 0.03018702832768238,
      "grad_norm": 1.0339388847351074,
      "learning_rate": 0.00019996022210977543,
      "loss": 0.8657,
      "step": 276
    },
    {
      "epoch": 0.030296401618724707,
      "grad_norm": 0.7535502910614014,
      "learning_rate": 0.00019995989807664242,
      "loss": 0.8136,
      "step": 277
    },
    {
      "epoch": 0.030405774909767036,
      "grad_norm": 1.1453170776367188,
      "learning_rate": 0.00019995957272932554,
      "loss": 0.6857,
      "step": 278
    },
    {
      "epoch": 0.03051514820080936,
      "grad_norm": 1.1806614398956299,
      "learning_rate": 0.0001999592460678291,
      "loss": 0.9984,
      "step": 279
    },
    {
      "epoch": 0.03062452149185169,
      "grad_norm": 1.112640142440796,
      "learning_rate": 0.0001999589180921574,
      "loss": 0.761,
      "step": 280
    },
    {
      "epoch": 0.030733894782894018,
      "grad_norm": 1.4966400861740112,
      "learning_rate": 0.0001999585888023147,
      "loss": 0.8953,
      "step": 281
    },
    {
      "epoch": 0.030843268073936343,
      "grad_norm": 1.293006420135498,
      "learning_rate": 0.0001999582581983054,
      "loss": 1.0241,
      "step": 282
    },
    {
      "epoch": 0.030952641364978672,
      "grad_norm": 1.177804946899414,
      "learning_rate": 0.0001999579262801338,
      "loss": 0.5965,
      "step": 283
    },
    {
      "epoch": 0.031062014656021,
      "grad_norm": 0.9398424029350281,
      "learning_rate": 0.0001999575930478043,
      "loss": 1.0178,
      "step": 284
    },
    {
      "epoch": 0.03117138794706333,
      "grad_norm": 1.0919867753982544,
      "learning_rate": 0.00019995725850132122,
      "loss": 0.9371,
      "step": 285
    },
    {
      "epoch": 0.03128076123810566,
      "grad_norm": 1.0972379446029663,
      "learning_rate": 0.000199956922640689,
      "loss": 0.962,
      "step": 286
    },
    {
      "epoch": 0.03139013452914798,
      "grad_norm": 1.2337533235549927,
      "learning_rate": 0.00019995658546591205,
      "loss": 1.1587,
      "step": 287
    },
    {
      "epoch": 0.03149950782019031,
      "grad_norm": 0.93784499168396,
      "learning_rate": 0.00019995624697699484,
      "loss": 0.7551,
      "step": 288
    },
    {
      "epoch": 0.03160888111123264,
      "grad_norm": 0.9531101584434509,
      "learning_rate": 0.00019995590717394177,
      "loss": 0.8181,
      "step": 289
    },
    {
      "epoch": 0.031718254402274965,
      "grad_norm": 1.0460001230239868,
      "learning_rate": 0.00019995556605675733,
      "loss": 1.0045,
      "step": 290
    },
    {
      "epoch": 0.03182762769331729,
      "grad_norm": 1.0514802932739258,
      "learning_rate": 0.00019995522362544597,
      "loss": 0.6646,
      "step": 291
    },
    {
      "epoch": 0.03193700098435962,
      "grad_norm": 1.0225249528884888,
      "learning_rate": 0.0001999548798800122,
      "loss": 0.8103,
      "step": 292
    },
    {
      "epoch": 0.03204637427540195,
      "grad_norm": 0.8883015513420105,
      "learning_rate": 0.0001999545348204606,
      "loss": 1.0488,
      "step": 293
    },
    {
      "epoch": 0.03215574756644427,
      "grad_norm": 0.8221065998077393,
      "learning_rate": 0.00019995418844679565,
      "loss": 0.7915,
      "step": 294
    },
    {
      "epoch": 0.032265120857486604,
      "grad_norm": 0.8032001852989197,
      "learning_rate": 0.00019995384075902192,
      "loss": 0.7785,
      "step": 295
    },
    {
      "epoch": 0.03237449414852893,
      "grad_norm": 1.0787360668182373,
      "learning_rate": 0.00019995349175714399,
      "loss": 0.6105,
      "step": 296
    },
    {
      "epoch": 0.032483867439571254,
      "grad_norm": 1.3346359729766846,
      "learning_rate": 0.00019995314144116642,
      "loss": 0.8981,
      "step": 297
    },
    {
      "epoch": 0.032593240730613586,
      "grad_norm": 1.1637407541275024,
      "learning_rate": 0.00019995278981109382,
      "loss": 0.6765,
      "step": 298
    },
    {
      "epoch": 0.03270261402165591,
      "grad_norm": 1.3199541568756104,
      "learning_rate": 0.00019995243686693085,
      "loss": 0.896,
      "step": 299
    },
    {
      "epoch": 0.032811987312698236,
      "grad_norm": 1.139554738998413,
      "learning_rate": 0.00019995208260868211,
      "loss": 0.865,
      "step": 300
    },
    {
      "epoch": 0.03292136060374057,
      "grad_norm": 1.1647419929504395,
      "learning_rate": 0.00019995172703635232,
      "loss": 0.7797,
      "step": 301
    },
    {
      "epoch": 0.03303073389478289,
      "grad_norm": 0.7142788767814636,
      "learning_rate": 0.00019995137014994606,
      "loss": 0.8755,
      "step": 302
    },
    {
      "epoch": 0.03314010718582522,
      "grad_norm": 0.908873438835144,
      "learning_rate": 0.00019995101194946808,
      "loss": 0.9655,
      "step": 303
    },
    {
      "epoch": 0.03324948047686755,
      "grad_norm": 1.0069727897644043,
      "learning_rate": 0.0001999506524349231,
      "loss": 0.9139,
      "step": 304
    },
    {
      "epoch": 0.033358853767909875,
      "grad_norm": 0.8300521373748779,
      "learning_rate": 0.0001999502916063158,
      "loss": 0.9362,
      "step": 305
    },
    {
      "epoch": 0.0334682270589522,
      "grad_norm": 1.2162195444107056,
      "learning_rate": 0.00019994992946365098,
      "loss": 0.7641,
      "step": 306
    },
    {
      "epoch": 0.03357760034999453,
      "grad_norm": 0.970177173614502,
      "learning_rate": 0.00019994956600693335,
      "loss": 0.9676,
      "step": 307
    },
    {
      "epoch": 0.03368697364103686,
      "grad_norm": 0.9938404560089111,
      "learning_rate": 0.00019994920123616772,
      "loss": 0.8936,
      "step": 308
    },
    {
      "epoch": 0.03379634693207919,
      "grad_norm": 1.2428972721099854,
      "learning_rate": 0.00019994883515135888,
      "loss": 0.885,
      "step": 309
    },
    {
      "epoch": 0.033905720223121515,
      "grad_norm": 0.8554952144622803,
      "learning_rate": 0.00019994846775251161,
      "loss": 1.0265,
      "step": 310
    },
    {
      "epoch": 0.03401509351416384,
      "grad_norm": 0.9248100519180298,
      "learning_rate": 0.00019994809903963078,
      "loss": 0.9309,
      "step": 311
    },
    {
      "epoch": 0.03412446680520617,
      "grad_norm": 1.1711786985397339,
      "learning_rate": 0.00019994772901272124,
      "loss": 0.867,
      "step": 312
    },
    {
      "epoch": 0.0342338400962485,
      "grad_norm": 1.6409622430801392,
      "learning_rate": 0.00019994735767178785,
      "loss": 1.0833,
      "step": 313
    },
    {
      "epoch": 0.03434321338729082,
      "grad_norm": 1.0994210243225098,
      "learning_rate": 0.00019994698501683546,
      "loss": 0.9876,
      "step": 314
    },
    {
      "epoch": 0.034452586678333154,
      "grad_norm": 1.307111144065857,
      "learning_rate": 0.00019994661104786901,
      "loss": 1.1115,
      "step": 315
    },
    {
      "epoch": 0.03456195996937548,
      "grad_norm": 1.2924015522003174,
      "learning_rate": 0.0001999462357648934,
      "loss": 0.7232,
      "step": 316
    },
    {
      "epoch": 0.034671333260417804,
      "grad_norm": 0.8390319347381592,
      "learning_rate": 0.00019994585916791353,
      "loss": 0.8054,
      "step": 317
    },
    {
      "epoch": 0.034780706551460136,
      "grad_norm": 1.4466496706008911,
      "learning_rate": 0.0001999454812569344,
      "loss": 0.8531,
      "step": 318
    },
    {
      "epoch": 0.03489007984250246,
      "grad_norm": 0.805334746837616,
      "learning_rate": 0.000199945102031961,
      "loss": 0.7877,
      "step": 319
    },
    {
      "epoch": 0.034999453133544786,
      "grad_norm": 0.8856577277183533,
      "learning_rate": 0.00019994472149299823,
      "loss": 1.0711,
      "step": 320
    },
    {
      "epoch": 0.03510882642458712,
      "grad_norm": 1.0543880462646484,
      "learning_rate": 0.00019994433964005116,
      "loss": 0.6526,
      "step": 321
    },
    {
      "epoch": 0.03521819971562944,
      "grad_norm": 0.9808034896850586,
      "learning_rate": 0.0001999439564731248,
      "loss": 0.6553,
      "step": 322
    },
    {
      "epoch": 0.03532757300667177,
      "grad_norm": 1.1530299186706543,
      "learning_rate": 0.00019994357199222418,
      "loss": 0.8814,
      "step": 323
    },
    {
      "epoch": 0.0354369462977141,
      "grad_norm": 1.1313234567642212,
      "learning_rate": 0.00019994318619735434,
      "loss": 0.73,
      "step": 324
    },
    {
      "epoch": 0.035546319588756425,
      "grad_norm": 1.1225991249084473,
      "learning_rate": 0.00019994279908852036,
      "loss": 0.8988,
      "step": 325
    },
    {
      "epoch": 0.03565569287979875,
      "grad_norm": 1.2102971076965332,
      "learning_rate": 0.00019994241066572735,
      "loss": 0.6714,
      "step": 326
    },
    {
      "epoch": 0.03576506617084108,
      "grad_norm": 1.3862812519073486,
      "learning_rate": 0.0001999420209289804,
      "loss": 0.6208,
      "step": 327
    },
    {
      "epoch": 0.03587443946188341,
      "grad_norm": 1.3298919200897217,
      "learning_rate": 0.00019994162987828465,
      "loss": 0.9615,
      "step": 328
    },
    {
      "epoch": 0.03598381275292573,
      "grad_norm": 1.1198225021362305,
      "learning_rate": 0.00019994123751364523,
      "loss": 0.8243,
      "step": 329
    },
    {
      "epoch": 0.036093186043968065,
      "grad_norm": 1.2356019020080566,
      "learning_rate": 0.00019994084383506726,
      "loss": 0.9731,
      "step": 330
    },
    {
      "epoch": 0.03620255933501039,
      "grad_norm": 1.9511923789978027,
      "learning_rate": 0.00019994044884255596,
      "loss": 0.8388,
      "step": 331
    },
    {
      "epoch": 0.036311932626052715,
      "grad_norm": 0.8875001072883606,
      "learning_rate": 0.00019994005253611653,
      "loss": 1.0167,
      "step": 332
    },
    {
      "epoch": 0.03642130591709505,
      "grad_norm": 1.0356827974319458,
      "learning_rate": 0.00019993965491575414,
      "loss": 0.7601,
      "step": 333
    },
    {
      "epoch": 0.03653067920813737,
      "grad_norm": 1.9006911516189575,
      "learning_rate": 0.00019993925598147408,
      "loss": 0.8644,
      "step": 334
    },
    {
      "epoch": 0.0366400524991797,
      "grad_norm": 1.149804711341858,
      "learning_rate": 0.00019993885573328153,
      "loss": 0.7937,
      "step": 335
    },
    {
      "epoch": 0.03674942579022203,
      "grad_norm": 1.0978573560714722,
      "learning_rate": 0.00019993845417118176,
      "loss": 0.9806,
      "step": 336
    },
    {
      "epoch": 0.036858799081264354,
      "grad_norm": 1.353148341178894,
      "learning_rate": 0.0001999380512951801,
      "loss": 0.6028,
      "step": 337
    },
    {
      "epoch": 0.036968172372306686,
      "grad_norm": 1.0444083213806152,
      "learning_rate": 0.00019993764710528184,
      "loss": 0.674,
      "step": 338
    },
    {
      "epoch": 0.03707754566334901,
      "grad_norm": 0.7757420539855957,
      "learning_rate": 0.00019993724160149222,
      "loss": 0.937,
      "step": 339
    },
    {
      "epoch": 0.037186918954391336,
      "grad_norm": 0.8659959435462952,
      "learning_rate": 0.00019993683478381665,
      "loss": 1.0106,
      "step": 340
    },
    {
      "epoch": 0.03729629224543367,
      "grad_norm": 0.8398618698120117,
      "learning_rate": 0.00019993642665226046,
      "loss": 0.7869,
      "step": 341
    },
    {
      "epoch": 0.03740566553647599,
      "grad_norm": 0.8791778087615967,
      "learning_rate": 0.00019993601720682898,
      "loss": 0.903,
      "step": 342
    },
    {
      "epoch": 0.03751503882751832,
      "grad_norm": 1.330810785293579,
      "learning_rate": 0.0001999356064475276,
      "loss": 0.6288,
      "step": 343
    },
    {
      "epoch": 0.03762441211856065,
      "grad_norm": 1.0563044548034668,
      "learning_rate": 0.00019993519437436176,
      "loss": 0.5645,
      "step": 344
    },
    {
      "epoch": 0.037733785409602975,
      "grad_norm": 1.2644983530044556,
      "learning_rate": 0.00019993478098733687,
      "loss": 0.8415,
      "step": 345
    },
    {
      "epoch": 0.0378431587006453,
      "grad_norm": 0.8137854337692261,
      "learning_rate": 0.00019993436628645833,
      "loss": 1.0094,
      "step": 346
    },
    {
      "epoch": 0.03795253199168763,
      "grad_norm": 1.2424585819244385,
      "learning_rate": 0.0001999339502717316,
      "loss": 0.7191,
      "step": 347
    },
    {
      "epoch": 0.03806190528272996,
      "grad_norm": 1.3705171346664429,
      "learning_rate": 0.0001999335329431622,
      "loss": 0.5286,
      "step": 348
    },
    {
      "epoch": 0.03817127857377228,
      "grad_norm": 1.1841068267822266,
      "learning_rate": 0.00019993311430075553,
      "loss": 0.5205,
      "step": 349
    },
    {
      "epoch": 0.038280651864814615,
      "grad_norm": 1.2048940658569336,
      "learning_rate": 0.00019993269434451718,
      "loss": 0.9276,
      "step": 350
    },
    {
      "epoch": 0.03839002515585694,
      "grad_norm": 1.2034653425216675,
      "learning_rate": 0.0001999322730744526,
      "loss": 0.7758,
      "step": 351
    },
    {
      "epoch": 0.038499398446899265,
      "grad_norm": 1.435682773590088,
      "learning_rate": 0.00019993185049056738,
      "loss": 0.8242,
      "step": 352
    },
    {
      "epoch": 0.0386087717379416,
      "grad_norm": 1.1770561933517456,
      "learning_rate": 0.0001999314265928671,
      "loss": 0.9822,
      "step": 353
    },
    {
      "epoch": 0.03871814502898392,
      "grad_norm": 0.7326700687408447,
      "learning_rate": 0.00019993100138135725,
      "loss": 0.8557,
      "step": 354
    },
    {
      "epoch": 0.03882751832002625,
      "grad_norm": 1.003616213798523,
      "learning_rate": 0.00019993057485604348,
      "loss": 0.6837,
      "step": 355
    },
    {
      "epoch": 0.03893689161106858,
      "grad_norm": 1.0169602632522583,
      "learning_rate": 0.00019993014701693134,
      "loss": 0.9012,
      "step": 356
    },
    {
      "epoch": 0.039046264902110904,
      "grad_norm": 1.0350092649459839,
      "learning_rate": 0.00019992971786402653,
      "loss": 0.867,
      "step": 357
    },
    {
      "epoch": 0.03915563819315323,
      "grad_norm": 1.0841048955917358,
      "learning_rate": 0.00019992928739733464,
      "loss": 0.4754,
      "step": 358
    },
    {
      "epoch": 0.03926501148419556,
      "grad_norm": 1.2736769914627075,
      "learning_rate": 0.00019992885561686134,
      "loss": 0.9531,
      "step": 359
    },
    {
      "epoch": 0.039374384775237886,
      "grad_norm": 0.9346782565116882,
      "learning_rate": 0.00019992842252261232,
      "loss": 0.6625,
      "step": 360
    },
    {
      "epoch": 0.03948375806628021,
      "grad_norm": 0.9822466373443604,
      "learning_rate": 0.00019992798811459327,
      "loss": 0.9554,
      "step": 361
    },
    {
      "epoch": 0.03959313135732254,
      "grad_norm": 1.0642709732055664,
      "learning_rate": 0.0001999275523928099,
      "loss": 0.8168,
      "step": 362
    },
    {
      "epoch": 0.03970250464836487,
      "grad_norm": 1.0021849870681763,
      "learning_rate": 0.00019992711535726793,
      "loss": 0.7259,
      "step": 363
    },
    {
      "epoch": 0.03981187793940719,
      "grad_norm": 1.1150245666503906,
      "learning_rate": 0.00019992667700797313,
      "loss": 1.01,
      "step": 364
    },
    {
      "epoch": 0.039921251230449525,
      "grad_norm": 1.0754119157791138,
      "learning_rate": 0.00019992623734493118,
      "loss": 1.0127,
      "step": 365
    },
    {
      "epoch": 0.04003062452149185,
      "grad_norm": 0.9095409512519836,
      "learning_rate": 0.000199925796368148,
      "loss": 0.818,
      "step": 366
    },
    {
      "epoch": 0.04013999781253418,
      "grad_norm": 1.5074443817138672,
      "learning_rate": 0.00019992535407762927,
      "loss": 0.7231,
      "step": 367
    },
    {
      "epoch": 0.04024937110357651,
      "grad_norm": 1.306563377380371,
      "learning_rate": 0.00019992491047338086,
      "loss": 0.8003,
      "step": 368
    },
    {
      "epoch": 0.04035874439461883,
      "grad_norm": 1.491228699684143,
      "learning_rate": 0.00019992446555540857,
      "loss": 0.9417,
      "step": 369
    },
    {
      "epoch": 0.040468117685661165,
      "grad_norm": 1.25246262550354,
      "learning_rate": 0.0001999240193237183,
      "loss": 0.6386,
      "step": 370
    },
    {
      "epoch": 0.04057749097670349,
      "grad_norm": 0.9611380100250244,
      "learning_rate": 0.00019992357177831587,
      "loss": 1.0323,
      "step": 371
    },
    {
      "epoch": 0.040686864267745815,
      "grad_norm": 0.857864260673523,
      "learning_rate": 0.00019992312291920716,
      "loss": 1.1258,
      "step": 372
    },
    {
      "epoch": 0.04079623755878815,
      "grad_norm": 0.9377604722976685,
      "learning_rate": 0.00019992267274639814,
      "loss": 0.9012,
      "step": 373
    },
    {
      "epoch": 0.04090561084983047,
      "grad_norm": 1.0209131240844727,
      "learning_rate": 0.0001999222212598946,
      "loss": 0.8956,
      "step": 374
    },
    {
      "epoch": 0.0410149841408728,
      "grad_norm": 0.9510963559150696,
      "learning_rate": 0.00019992176845970262,
      "loss": 0.7232,
      "step": 375
    },
    {
      "epoch": 0.04112435743191513,
      "grad_norm": 1.049834132194519,
      "learning_rate": 0.00019992131434582808,
      "loss": 0.9097,
      "step": 376
    },
    {
      "epoch": 0.041233730722957454,
      "grad_norm": 1.051466464996338,
      "learning_rate": 0.00019992085891827694,
      "loss": 0.8074,
      "step": 377
    },
    {
      "epoch": 0.04134310401399978,
      "grad_norm": 1.0262120962142944,
      "learning_rate": 0.00019992040217705525,
      "loss": 0.8217,
      "step": 378
    },
    {
      "epoch": 0.04145247730504211,
      "grad_norm": 0.8663240075111389,
      "learning_rate": 0.0001999199441221689,
      "loss": 0.8464,
      "step": 379
    },
    {
      "epoch": 0.041561850596084436,
      "grad_norm": 0.9827305674552917,
      "learning_rate": 0.000199919484753624,
      "loss": 0.6206,
      "step": 380
    },
    {
      "epoch": 0.04167122388712676,
      "grad_norm": 1.5495073795318604,
      "learning_rate": 0.0001999190240714266,
      "loss": 1.0151,
      "step": 381
    },
    {
      "epoch": 0.04178059717816909,
      "grad_norm": 1.396231770515442,
      "learning_rate": 0.0001999185620755827,
      "loss": 0.8768,
      "step": 382
    },
    {
      "epoch": 0.04188997046921142,
      "grad_norm": 1.0921934843063354,
      "learning_rate": 0.00019991809876609843,
      "loss": 0.8875,
      "step": 383
    },
    {
      "epoch": 0.04199934376025374,
      "grad_norm": 1.064682126045227,
      "learning_rate": 0.00019991763414297983,
      "loss": 0.6536,
      "step": 384
    },
    {
      "epoch": 0.042108717051296075,
      "grad_norm": 1.0808131694793701,
      "learning_rate": 0.00019991716820623304,
      "loss": 0.785,
      "step": 385
    },
    {
      "epoch": 0.0422180903423384,
      "grad_norm": 1.0913347005844116,
      "learning_rate": 0.0001999167009558642,
      "loss": 0.6544,
      "step": 386
    },
    {
      "epoch": 0.042327463633380726,
      "grad_norm": 1.3865599632263184,
      "learning_rate": 0.0001999162323918794,
      "loss": 0.8173,
      "step": 387
    },
    {
      "epoch": 0.04243683692442306,
      "grad_norm": 1.3333287239074707,
      "learning_rate": 0.00019991576251428487,
      "loss": 0.9835,
      "step": 388
    },
    {
      "epoch": 0.04254621021546538,
      "grad_norm": 0.8037435412406921,
      "learning_rate": 0.0001999152913230867,
      "loss": 0.931,
      "step": 389
    },
    {
      "epoch": 0.04265558350650771,
      "grad_norm": 0.8408225774765015,
      "learning_rate": 0.00019991481881829115,
      "loss": 0.88,
      "step": 390
    },
    {
      "epoch": 0.04276495679755004,
      "grad_norm": 1.035088062286377,
      "learning_rate": 0.00019991434499990442,
      "loss": 0.9706,
      "step": 391
    },
    {
      "epoch": 0.042874330088592365,
      "grad_norm": 1.2629435062408447,
      "learning_rate": 0.00019991386986793273,
      "loss": 0.7752,
      "step": 392
    },
    {
      "epoch": 0.04298370337963469,
      "grad_norm": 1.078934669494629,
      "learning_rate": 0.00019991339342238234,
      "loss": 0.4815,
      "step": 393
    },
    {
      "epoch": 0.04309307667067702,
      "grad_norm": 0.8836020231246948,
      "learning_rate": 0.0001999129156632595,
      "loss": 0.9411,
      "step": 394
    },
    {
      "epoch": 0.04320244996171935,
      "grad_norm": 1.166883945465088,
      "learning_rate": 0.00019991243659057045,
      "loss": 0.6927,
      "step": 395
    },
    {
      "epoch": 0.04331182325276168,
      "grad_norm": 1.344340443611145,
      "learning_rate": 0.0001999119562043216,
      "loss": 0.9603,
      "step": 396
    },
    {
      "epoch": 0.043421196543804004,
      "grad_norm": 0.9963370561599731,
      "learning_rate": 0.0001999114745045192,
      "loss": 1.0529,
      "step": 397
    },
    {
      "epoch": 0.04353056983484633,
      "grad_norm": 1.1938830614089966,
      "learning_rate": 0.00019991099149116955,
      "loss": 0.9239,
      "step": 398
    },
    {
      "epoch": 0.04363994312588866,
      "grad_norm": 1.109154462814331,
      "learning_rate": 0.00019991050716427903,
      "loss": 1.0685,
      "step": 399
    },
    {
      "epoch": 0.043749316416930986,
      "grad_norm": 0.9188171625137329,
      "learning_rate": 0.00019991002152385402,
      "loss": 1.0147,
      "step": 400
    },
    {
      "epoch": 0.043749316416930986,
      "eval_loss": 0.8067082166671753,
      "eval_runtime": 40.9342,
      "eval_samples_per_second": 17.98,
      "eval_steps_per_second": 4.495,
      "step": 400
    },
    {
      "epoch": 0.04385868970797331,
      "grad_norm": 0.9638638496398926,
      "learning_rate": 0.00019990953456990092,
      "loss": 0.9062,
      "step": 401
    },
    {
      "epoch": 0.04396806299901564,
      "grad_norm": 1.0281591415405273,
      "learning_rate": 0.00019990904630242607,
      "loss": 0.9666,
      "step": 402
    },
    {
      "epoch": 0.04407743629005797,
      "grad_norm": 1.0092509984970093,
      "learning_rate": 0.00019990855672143596,
      "loss": 0.6308,
      "step": 403
    },
    {
      "epoch": 0.04418680958110029,
      "grad_norm": 0.9775615334510803,
      "learning_rate": 0.00019990806582693697,
      "loss": 0.7727,
      "step": 404
    },
    {
      "epoch": 0.044296182872142625,
      "grad_norm": 1.1057891845703125,
      "learning_rate": 0.0001999075736189356,
      "loss": 1.2195,
      "step": 405
    },
    {
      "epoch": 0.04440555616318495,
      "grad_norm": 1.8804906606674194,
      "learning_rate": 0.0001999070800974383,
      "loss": 0.9471,
      "step": 406
    },
    {
      "epoch": 0.044514929454227276,
      "grad_norm": 0.916015088558197,
      "learning_rate": 0.00019990658526245153,
      "loss": 0.7251,
      "step": 407
    },
    {
      "epoch": 0.04462430274526961,
      "grad_norm": 1.1240051984786987,
      "learning_rate": 0.00019990608911398184,
      "loss": 1.0191,
      "step": 408
    },
    {
      "epoch": 0.04473367603631193,
      "grad_norm": 0.9934580326080322,
      "learning_rate": 0.00019990559165203572,
      "loss": 1.0016,
      "step": 409
    },
    {
      "epoch": 0.04484304932735426,
      "grad_norm": 0.9659127593040466,
      "learning_rate": 0.00019990509287661973,
      "loss": 1.0285,
      "step": 410
    },
    {
      "epoch": 0.04495242261839659,
      "grad_norm": 0.8822170495986938,
      "learning_rate": 0.00019990459278774046,
      "loss": 1.0685,
      "step": 411
    },
    {
      "epoch": 0.045061795909438915,
      "grad_norm": 1.0471923351287842,
      "learning_rate": 0.00019990409138540441,
      "loss": 0.8328,
      "step": 412
    },
    {
      "epoch": 0.04517116920048124,
      "grad_norm": 1.1356496810913086,
      "learning_rate": 0.0001999035886696182,
      "loss": 0.9262,
      "step": 413
    },
    {
      "epoch": 0.04528054249152357,
      "grad_norm": 0.9098622798919678,
      "learning_rate": 0.00019990308464038848,
      "loss": 0.6382,
      "step": 414
    },
    {
      "epoch": 0.0453899157825659,
      "grad_norm": 1.1171592473983765,
      "learning_rate": 0.00019990257929772184,
      "loss": 0.746,
      "step": 415
    },
    {
      "epoch": 0.04549928907360822,
      "grad_norm": 0.9921464920043945,
      "learning_rate": 0.0001999020726416249,
      "loss": 0.7603,
      "step": 416
    },
    {
      "epoch": 0.045608662364650554,
      "grad_norm": 1.0106383562088013,
      "learning_rate": 0.0001999015646721044,
      "loss": 0.7964,
      "step": 417
    },
    {
      "epoch": 0.04571803565569288,
      "grad_norm": 1.3405063152313232,
      "learning_rate": 0.00019990105538916694,
      "loss": 0.807,
      "step": 418
    },
    {
      "epoch": 0.045827408946735204,
      "grad_norm": 1.180208683013916,
      "learning_rate": 0.00019990054479281924,
      "loss": 0.9172,
      "step": 419
    },
    {
      "epoch": 0.045936782237777536,
      "grad_norm": 1.1107349395751953,
      "learning_rate": 0.00019990003288306802,
      "loss": 0.9676,
      "step": 420
    },
    {
      "epoch": 0.04604615552881986,
      "grad_norm": 0.8224467635154724,
      "learning_rate": 0.00019989951965991999,
      "loss": 0.811,
      "step": 421
    },
    {
      "epoch": 0.046155528819862186,
      "grad_norm": 1.0547099113464355,
      "learning_rate": 0.00019989900512338196,
      "loss": 0.9228,
      "step": 422
    },
    {
      "epoch": 0.04626490211090452,
      "grad_norm": 1.2838783264160156,
      "learning_rate": 0.0001998984892734606,
      "loss": 0.6898,
      "step": 423
    },
    {
      "epoch": 0.04637427540194684,
      "grad_norm": 1.7018957138061523,
      "learning_rate": 0.00019989797211016278,
      "loss": 0.8091,
      "step": 424
    },
    {
      "epoch": 0.046483648692989175,
      "grad_norm": 1.207707405090332,
      "learning_rate": 0.00019989745363349526,
      "loss": 0.6146,
      "step": 425
    },
    {
      "epoch": 0.0465930219840315,
      "grad_norm": 1.4657715559005737,
      "learning_rate": 0.00019989693384346482,
      "loss": 0.9031,
      "step": 426
    },
    {
      "epoch": 0.046702395275073826,
      "grad_norm": 1.3541256189346313,
      "learning_rate": 0.0001998964127400784,
      "loss": 0.6766,
      "step": 427
    },
    {
      "epoch": 0.04681176856611616,
      "grad_norm": 0.9115450382232666,
      "learning_rate": 0.00019989589032334268,
      "loss": 0.9605,
      "step": 428
    },
    {
      "epoch": 0.04692114185715848,
      "grad_norm": 0.9539338946342468,
      "learning_rate": 0.0001998953665932647,
      "loss": 1.0472,
      "step": 429
    },
    {
      "epoch": 0.04703051514820081,
      "grad_norm": 0.9659996628761292,
      "learning_rate": 0.00019989484154985126,
      "loss": 0.7071,
      "step": 430
    },
    {
      "epoch": 0.04713988843924314,
      "grad_norm": 1.097551703453064,
      "learning_rate": 0.0001998943151931093,
      "loss": 0.4573,
      "step": 431
    },
    {
      "epoch": 0.047249261730285465,
      "grad_norm": 1.287800908088684,
      "learning_rate": 0.0001998937875230457,
      "loss": 0.7062,
      "step": 432
    },
    {
      "epoch": 0.04735863502132779,
      "grad_norm": 0.9104124307632446,
      "learning_rate": 0.0001998932585396674,
      "loss": 0.5085,
      "step": 433
    },
    {
      "epoch": 0.04746800831237012,
      "grad_norm": 0.8423514366149902,
      "learning_rate": 0.0001998927282429814,
      "loss": 0.7665,
      "step": 434
    },
    {
      "epoch": 0.04757738160341245,
      "grad_norm": 1.021085500717163,
      "learning_rate": 0.0001998921966329946,
      "loss": 0.6975,
      "step": 435
    },
    {
      "epoch": 0.04768675489445477,
      "grad_norm": 1.40684175491333,
      "learning_rate": 0.0001998916637097141,
      "loss": 0.7913,
      "step": 436
    },
    {
      "epoch": 0.047796128185497104,
      "grad_norm": 1.0347301959991455,
      "learning_rate": 0.00019989112947314678,
      "loss": 0.7172,
      "step": 437
    },
    {
      "epoch": 0.04790550147653943,
      "grad_norm": 1.0268831253051758,
      "learning_rate": 0.00019989059392329974,
      "loss": 0.7212,
      "step": 438
    },
    {
      "epoch": 0.048014874767581754,
      "grad_norm": 1.0991255044937134,
      "learning_rate": 0.00019989005706018,
      "loss": 0.7781,
      "step": 439
    },
    {
      "epoch": 0.048124248058624086,
      "grad_norm": 1.0303900241851807,
      "learning_rate": 0.00019988951888379462,
      "loss": 0.8743,
      "step": 440
    },
    {
      "epoch": 0.04823362134966641,
      "grad_norm": 1.1497889757156372,
      "learning_rate": 0.0001998889793941507,
      "loss": 0.8768,
      "step": 441
    },
    {
      "epoch": 0.048342994640708736,
      "grad_norm": 1.1906489133834839,
      "learning_rate": 0.00019988843859125528,
      "loss": 0.7988,
      "step": 442
    },
    {
      "epoch": 0.04845236793175107,
      "grad_norm": 0.9526726603507996,
      "learning_rate": 0.0001998878964751155,
      "loss": 0.9272,
      "step": 443
    },
    {
      "epoch": 0.04856174122279339,
      "grad_norm": 1.0579299926757812,
      "learning_rate": 0.0001998873530457385,
      "loss": 0.7917,
      "step": 444
    },
    {
      "epoch": 0.04867111451383572,
      "grad_norm": 1.2798495292663574,
      "learning_rate": 0.0001998868083031314,
      "loss": 0.8362,
      "step": 445
    },
    {
      "epoch": 0.04878048780487805,
      "grad_norm": 1.187063217163086,
      "learning_rate": 0.00019988626224730135,
      "loss": 0.6954,
      "step": 446
    },
    {
      "epoch": 0.048889861095920376,
      "grad_norm": 0.8720710873603821,
      "learning_rate": 0.0001998857148782556,
      "loss": 0.6788,
      "step": 447
    },
    {
      "epoch": 0.0489992343869627,
      "grad_norm": 1.2096325159072876,
      "learning_rate": 0.00019988516619600128,
      "loss": 0.7242,
      "step": 448
    },
    {
      "epoch": 0.04910860767800503,
      "grad_norm": 0.9759934544563293,
      "learning_rate": 0.0001998846162005456,
      "loss": 0.82,
      "step": 449
    },
    {
      "epoch": 0.04921798096904736,
      "grad_norm": 0.9307674169540405,
      "learning_rate": 0.00019988406489189584,
      "loss": 1.0253,
      "step": 450
    },
    {
      "epoch": 0.04932735426008968,
      "grad_norm": 1.079480767250061,
      "learning_rate": 0.00019988351227005923,
      "loss": 0.7901,
      "step": 451
    },
    {
      "epoch": 0.049436727551132015,
      "grad_norm": 0.9951292276382446,
      "learning_rate": 0.000199882958335043,
      "loss": 0.8101,
      "step": 452
    },
    {
      "epoch": 0.04954610084217434,
      "grad_norm": 1.5982356071472168,
      "learning_rate": 0.00019988240308685447,
      "loss": 0.7624,
      "step": 453
    },
    {
      "epoch": 0.04965547413321667,
      "grad_norm": 1.5702210664749146,
      "learning_rate": 0.0001998818465255009,
      "loss": 1.0113,
      "step": 454
    },
    {
      "epoch": 0.049764847424259,
      "grad_norm": 0.8995147347450256,
      "learning_rate": 0.00019988128865098967,
      "loss": 0.8003,
      "step": 455
    },
    {
      "epoch": 0.04987422071530132,
      "grad_norm": 1.0795233249664307,
      "learning_rate": 0.00019988072946332808,
      "loss": 0.7688,
      "step": 456
    },
    {
      "epoch": 0.049983594006343654,
      "grad_norm": 1.1191943883895874,
      "learning_rate": 0.00019988016896252346,
      "loss": 0.8913,
      "step": 457
    },
    {
      "epoch": 0.05009296729738598,
      "grad_norm": 1.089416265487671,
      "learning_rate": 0.0001998796071485832,
      "loss": 0.6705,
      "step": 458
    },
    {
      "epoch": 0.050202340588428304,
      "grad_norm": 0.9763931632041931,
      "learning_rate": 0.0001998790440215147,
      "loss": 0.6319,
      "step": 459
    },
    {
      "epoch": 0.050311713879470636,
      "grad_norm": 1.4132522344589233,
      "learning_rate": 0.00019987847958132535,
      "loss": 0.7966,
      "step": 460
    },
    {
      "epoch": 0.05042108717051296,
      "grad_norm": 1.5261541604995728,
      "learning_rate": 0.00019987791382802255,
      "loss": 0.6739,
      "step": 461
    },
    {
      "epoch": 0.050530460461555286,
      "grad_norm": 1.1543093919754028,
      "learning_rate": 0.00019987734676161378,
      "loss": 1.3043,
      "step": 462
    },
    {
      "epoch": 0.05063983375259762,
      "grad_norm": 1.311062216758728,
      "learning_rate": 0.0001998767783821065,
      "loss": 0.8772,
      "step": 463
    },
    {
      "epoch": 0.05074920704363994,
      "grad_norm": 1.5114765167236328,
      "learning_rate": 0.00019987620868950812,
      "loss": 0.8614,
      "step": 464
    },
    {
      "epoch": 0.05085858033468227,
      "grad_norm": 1.1269599199295044,
      "learning_rate": 0.00019987563768382617,
      "loss": 0.9356,
      "step": 465
    },
    {
      "epoch": 0.0509679536257246,
      "grad_norm": 1.285370945930481,
      "learning_rate": 0.00019987506536506814,
      "loss": 0.6714,
      "step": 466
    },
    {
      "epoch": 0.051077326916766926,
      "grad_norm": 1.137934923171997,
      "learning_rate": 0.0001998744917332416,
      "loss": 0.5941,
      "step": 467
    },
    {
      "epoch": 0.05118670020780925,
      "grad_norm": 1.1598773002624512,
      "learning_rate": 0.00019987391678835404,
      "loss": 0.9834,
      "step": 468
    },
    {
      "epoch": 0.05129607349885158,
      "grad_norm": 1.5532463788986206,
      "learning_rate": 0.00019987334053041307,
      "loss": 0.8427,
      "step": 469
    },
    {
      "epoch": 0.05140544678989391,
      "grad_norm": 1.0216114521026611,
      "learning_rate": 0.00019987276295942621,
      "loss": 0.8592,
      "step": 470
    },
    {
      "epoch": 0.05151482008093623,
      "grad_norm": 1.5978375673294067,
      "learning_rate": 0.00019987218407540108,
      "loss": 0.6453,
      "step": 471
    },
    {
      "epoch": 0.051624193371978565,
      "grad_norm": 1.022755742073059,
      "learning_rate": 0.0001998716038783453,
      "loss": 0.9352,
      "step": 472
    },
    {
      "epoch": 0.05173356666302089,
      "grad_norm": 1.1233989000320435,
      "learning_rate": 0.00019987102236826646,
      "loss": 0.7528,
      "step": 473
    },
    {
      "epoch": 0.051842939954063215,
      "grad_norm": 1.0236766338348389,
      "learning_rate": 0.00019987043954517223,
      "loss": 0.7504,
      "step": 474
    },
    {
      "epoch": 0.05195231324510555,
      "grad_norm": 0.9642089009284973,
      "learning_rate": 0.0001998698554090703,
      "loss": 0.7342,
      "step": 475
    },
    {
      "epoch": 0.05206168653614787,
      "grad_norm": 1.0298606157302856,
      "learning_rate": 0.00019986926995996834,
      "loss": 0.9943,
      "step": 476
    },
    {
      "epoch": 0.0521710598271902,
      "grad_norm": 0.9320874214172363,
      "learning_rate": 0.000199868683197874,
      "loss": 1.1226,
      "step": 477
    },
    {
      "epoch": 0.05228043311823253,
      "grad_norm": 0.8626863956451416,
      "learning_rate": 0.000199868095122795,
      "loss": 1.0293,
      "step": 478
    },
    {
      "epoch": 0.052389806409274854,
      "grad_norm": 1.0206810235977173,
      "learning_rate": 0.00019986750573473914,
      "loss": 1.0032,
      "step": 479
    },
    {
      "epoch": 0.05249917970031718,
      "grad_norm": 1.1447771787643433,
      "learning_rate": 0.0001998669150337141,
      "loss": 0.8816,
      "step": 480
    },
    {
      "epoch": 0.05260855299135951,
      "grad_norm": 1.1172994375228882,
      "learning_rate": 0.0001998663230197277,
      "loss": 0.8034,
      "step": 481
    },
    {
      "epoch": 0.052717926282401836,
      "grad_norm": 1.1175955533981323,
      "learning_rate": 0.00019986572969278766,
      "loss": 0.9391,
      "step": 482
    },
    {
      "epoch": 0.05282729957344417,
      "grad_norm": 1.279219388961792,
      "learning_rate": 0.00019986513505290186,
      "loss": 0.7481,
      "step": 483
    },
    {
      "epoch": 0.05293667286448649,
      "grad_norm": 0.9596846103668213,
      "learning_rate": 0.00019986453910007806,
      "loss": 0.7093,
      "step": 484
    },
    {
      "epoch": 0.05304604615552882,
      "grad_norm": 1.5974267721176147,
      "learning_rate": 0.0001998639418343241,
      "loss": 0.9337,
      "step": 485
    },
    {
      "epoch": 0.05315541944657115,
      "grad_norm": 0.9189580678939819,
      "learning_rate": 0.0001998633432556478,
      "loss": 1.042,
      "step": 486
    },
    {
      "epoch": 0.053264792737613476,
      "grad_norm": 1.3200494050979614,
      "learning_rate": 0.00019986274336405714,
      "loss": 0.8717,
      "step": 487
    },
    {
      "epoch": 0.0533741660286558,
      "grad_norm": 1.514082431793213,
      "learning_rate": 0.0001998621421595599,
      "loss": 0.9438,
      "step": 488
    },
    {
      "epoch": 0.05348353931969813,
      "grad_norm": 1.1798110008239746,
      "learning_rate": 0.000199861539642164,
      "loss": 0.8857,
      "step": 489
    },
    {
      "epoch": 0.05359291261074046,
      "grad_norm": 1.3705772161483765,
      "learning_rate": 0.00019986093581187743,
      "loss": 0.7876,
      "step": 490
    },
    {
      "epoch": 0.05370228590178278,
      "grad_norm": 1.0883309841156006,
      "learning_rate": 0.00019986033066870805,
      "loss": 0.7006,
      "step": 491
    },
    {
      "epoch": 0.053811659192825115,
      "grad_norm": 1.2093448638916016,
      "learning_rate": 0.00019985972421266386,
      "loss": 0.8158,
      "step": 492
    },
    {
      "epoch": 0.05392103248386744,
      "grad_norm": 1.2223838567733765,
      "learning_rate": 0.00019985911644375282,
      "loss": 0.9867,
      "step": 493
    },
    {
      "epoch": 0.054030405774909765,
      "grad_norm": 1.2985742092132568,
      "learning_rate": 0.00019985850736198294,
      "loss": 0.7929,
      "step": 494
    },
    {
      "epoch": 0.0541397790659521,
      "grad_norm": 1.0266704559326172,
      "learning_rate": 0.00019985789696736215,
      "loss": 0.7462,
      "step": 495
    },
    {
      "epoch": 0.05424915235699442,
      "grad_norm": 1.272060513496399,
      "learning_rate": 0.00019985728525989858,
      "loss": 0.78,
      "step": 496
    },
    {
      "epoch": 0.05435852564803675,
      "grad_norm": 0.8229413032531738,
      "learning_rate": 0.00019985667223960021,
      "loss": 1.0024,
      "step": 497
    },
    {
      "epoch": 0.05446789893907908,
      "grad_norm": 1.0643401145935059,
      "learning_rate": 0.00019985605790647513,
      "loss": 0.8547,
      "step": 498
    },
    {
      "epoch": 0.054577272230121404,
      "grad_norm": 0.9842153787612915,
      "learning_rate": 0.00019985544226053137,
      "loss": 1.0151,
      "step": 499
    },
    {
      "epoch": 0.05468664552116373,
      "grad_norm": 1.050392508506775,
      "learning_rate": 0.00019985482530177707,
      "loss": 0.7329,
      "step": 500
    },
    {
      "epoch": 0.05479601881220606,
      "grad_norm": 1.1385303735733032,
      "learning_rate": 0.00019985420703022032,
      "loss": 0.8524,
      "step": 501
    },
    {
      "epoch": 0.054905392103248386,
      "grad_norm": 1.0153578519821167,
      "learning_rate": 0.0001998535874458693,
      "loss": 0.9798,
      "step": 502
    },
    {
      "epoch": 0.05501476539429071,
      "grad_norm": 0.8864844441413879,
      "learning_rate": 0.00019985296654873204,
      "loss": 0.8962,
      "step": 503
    },
    {
      "epoch": 0.05512413868533304,
      "grad_norm": 0.8665205836296082,
      "learning_rate": 0.0001998523443388168,
      "loss": 1.1352,
      "step": 504
    },
    {
      "epoch": 0.05523351197637537,
      "grad_norm": 1.2367112636566162,
      "learning_rate": 0.00019985172081613177,
      "loss": 0.9921,
      "step": 505
    },
    {
      "epoch": 0.055342885267417694,
      "grad_norm": 1.02898108959198,
      "learning_rate": 0.00019985109598068506,
      "loss": 0.9123,
      "step": 506
    },
    {
      "epoch": 0.055452258558460026,
      "grad_norm": 0.9751277565956116,
      "learning_rate": 0.000199850469832485,
      "loss": 1.0117,
      "step": 507
    },
    {
      "epoch": 0.05556163184950235,
      "grad_norm": 1.1283056735992432,
      "learning_rate": 0.00019984984237153973,
      "loss": 0.7363,
      "step": 508
    },
    {
      "epoch": 0.055671005140544676,
      "grad_norm": 1.480178952217102,
      "learning_rate": 0.0001998492135978575,
      "loss": 1.0154,
      "step": 509
    },
    {
      "epoch": 0.05578037843158701,
      "grad_norm": 1.3893234729766846,
      "learning_rate": 0.00019984858351144663,
      "loss": 0.6876,
      "step": 510
    },
    {
      "epoch": 0.05588975172262933,
      "grad_norm": 1.0186976194381714,
      "learning_rate": 0.00019984795211231535,
      "loss": 0.7121,
      "step": 511
    },
    {
      "epoch": 0.055999125013671665,
      "grad_norm": 1.1589125394821167,
      "learning_rate": 0.000199847319400472,
      "loss": 0.7955,
      "step": 512
    },
    {
      "epoch": 0.05610849830471399,
      "grad_norm": 1.0086039304733276,
      "learning_rate": 0.0001998466853759249,
      "loss": 0.8957,
      "step": 513
    },
    {
      "epoch": 0.056217871595756315,
      "grad_norm": 1.2082234621047974,
      "learning_rate": 0.00019984605003868237,
      "loss": 0.931,
      "step": 514
    },
    {
      "epoch": 0.05632724488679865,
      "grad_norm": 1.0067565441131592,
      "learning_rate": 0.0001998454133887528,
      "loss": 0.731,
      "step": 515
    },
    {
      "epoch": 0.05643661817784097,
      "grad_norm": 0.8393429517745972,
      "learning_rate": 0.00019984477542614446,
      "loss": 0.8231,
      "step": 516
    },
    {
      "epoch": 0.0565459914688833,
      "grad_norm": 0.9679846167564392,
      "learning_rate": 0.00019984413615086583,
      "loss": 1.0243,
      "step": 517
    },
    {
      "epoch": 0.05665536475992563,
      "grad_norm": 1.0620890855789185,
      "learning_rate": 0.0001998434955629253,
      "loss": 0.8942,
      "step": 518
    },
    {
      "epoch": 0.056764738050967954,
      "grad_norm": 0.8497173190116882,
      "learning_rate": 0.00019984285366233127,
      "loss": 0.8808,
      "step": 519
    },
    {
      "epoch": 0.05687411134201028,
      "grad_norm": 1.210013508796692,
      "learning_rate": 0.0001998422104490922,
      "loss": 0.6953,
      "step": 520
    },
    {
      "epoch": 0.05698348463305261,
      "grad_norm": 0.8720889091491699,
      "learning_rate": 0.00019984156592321652,
      "loss": 0.9666,
      "step": 521
    },
    {
      "epoch": 0.057092857924094936,
      "grad_norm": 1.122982144355774,
      "learning_rate": 0.00019984092008471272,
      "loss": 0.8495,
      "step": 522
    },
    {
      "epoch": 0.05720223121513726,
      "grad_norm": 1.1690536737442017,
      "learning_rate": 0.00019984027293358931,
      "loss": 1.202,
      "step": 523
    },
    {
      "epoch": 0.05731160450617959,
      "grad_norm": 1.0106743574142456,
      "learning_rate": 0.00019983962446985476,
      "loss": 0.9893,
      "step": 524
    },
    {
      "epoch": 0.05742097779722192,
      "grad_norm": 1.8566340208053589,
      "learning_rate": 0.0001998389746935176,
      "loss": 1.3652,
      "step": 525
    },
    {
      "epoch": 0.057530351088264244,
      "grad_norm": 0.9694240689277649,
      "learning_rate": 0.00019983832360458644,
      "loss": 0.6753,
      "step": 526
    },
    {
      "epoch": 0.057639724379306576,
      "grad_norm": 1.099011778831482,
      "learning_rate": 0.00019983767120306973,
      "loss": 1.549,
      "step": 527
    },
    {
      "epoch": 0.0577490976703489,
      "grad_norm": 1.0495198965072632,
      "learning_rate": 0.00019983701748897613,
      "loss": 1.1807,
      "step": 528
    },
    {
      "epoch": 0.057858470961391226,
      "grad_norm": 0.9285663962364197,
      "learning_rate": 0.0001998363624623142,
      "loss": 1.0697,
      "step": 529
    },
    {
      "epoch": 0.05796784425243356,
      "grad_norm": 1.0406607389450073,
      "learning_rate": 0.00019983570612309257,
      "loss": 1.0355,
      "step": 530
    },
    {
      "epoch": 0.05807721754347588,
      "grad_norm": 0.9569828510284424,
      "learning_rate": 0.00019983504847131985,
      "loss": 0.7724,
      "step": 531
    },
    {
      "epoch": 0.05818659083451821,
      "grad_norm": 1.041804313659668,
      "learning_rate": 0.0001998343895070047,
      "loss": 0.5987,
      "step": 532
    },
    {
      "epoch": 0.05829596412556054,
      "grad_norm": 1.242843508720398,
      "learning_rate": 0.00019983372923015576,
      "loss": 1.0367,
      "step": 533
    },
    {
      "epoch": 0.058405337416602865,
      "grad_norm": 1.2179800271987915,
      "learning_rate": 0.00019983306764078174,
      "loss": 0.8017,
      "step": 534
    },
    {
      "epoch": 0.05851471070764519,
      "grad_norm": 1.5981494188308716,
      "learning_rate": 0.00019983240473889132,
      "loss": 0.8737,
      "step": 535
    },
    {
      "epoch": 0.05862408399868752,
      "grad_norm": 1.071590781211853,
      "learning_rate": 0.00019983174052449324,
      "loss": 0.8819,
      "step": 536
    },
    {
      "epoch": 0.05873345728972985,
      "grad_norm": 0.9891796112060547,
      "learning_rate": 0.0001998310749975962,
      "loss": 1.1386,
      "step": 537
    },
    {
      "epoch": 0.05884283058077217,
      "grad_norm": 1.0623862743377686,
      "learning_rate": 0.00019983040815820896,
      "loss": 0.8083,
      "step": 538
    },
    {
      "epoch": 0.058952203871814504,
      "grad_norm": 0.9091552495956421,
      "learning_rate": 0.0001998297400063403,
      "loss": 0.5463,
      "step": 539
    },
    {
      "epoch": 0.05906157716285683,
      "grad_norm": 1.1463671922683716,
      "learning_rate": 0.000199829070541999,
      "loss": 0.8651,
      "step": 540
    },
    {
      "epoch": 0.05917095045389916,
      "grad_norm": 1.4799455404281616,
      "learning_rate": 0.00019982839976519386,
      "loss": 0.6439,
      "step": 541
    },
    {
      "epoch": 0.059280323744941486,
      "grad_norm": 1.2554148435592651,
      "learning_rate": 0.00019982772767593367,
      "loss": 0.9621,
      "step": 542
    },
    {
      "epoch": 0.05938969703598381,
      "grad_norm": 1.0151816606521606,
      "learning_rate": 0.00019982705427422733,
      "loss": 0.8456,
      "step": 543
    },
    {
      "epoch": 0.05949907032702614,
      "grad_norm": 0.9739223122596741,
      "learning_rate": 0.00019982637956008362,
      "loss": 1.0848,
      "step": 544
    },
    {
      "epoch": 0.05960844361806847,
      "grad_norm": 1.4318240880966187,
      "learning_rate": 0.00019982570353351147,
      "loss": 0.4684,
      "step": 545
    },
    {
      "epoch": 0.059717816909110794,
      "grad_norm": 1.1196770668029785,
      "learning_rate": 0.00019982502619451974,
      "loss": 0.7739,
      "step": 546
    },
    {
      "epoch": 0.059827190200153126,
      "grad_norm": 0.9427726864814758,
      "learning_rate": 0.00019982434754311733,
      "loss": 0.9338,
      "step": 547
    },
    {
      "epoch": 0.05993656349119545,
      "grad_norm": 1.3539577722549438,
      "learning_rate": 0.0001998236675793132,
      "loss": 0.9631,
      "step": 548
    },
    {
      "epoch": 0.060045936782237776,
      "grad_norm": 1.1712934970855713,
      "learning_rate": 0.00019982298630311622,
      "loss": 0.9422,
      "step": 549
    },
    {
      "epoch": 0.06015531007328011,
      "grad_norm": 1.177377700805664,
      "learning_rate": 0.0001998223037145354,
      "loss": 0.9431,
      "step": 550
    },
    {
      "epoch": 0.06026468336432243,
      "grad_norm": 1.0253443717956543,
      "learning_rate": 0.00019982161981357973,
      "loss": 1.1583,
      "step": 551
    },
    {
      "epoch": 0.06037405665536476,
      "grad_norm": 1.0737707614898682,
      "learning_rate": 0.00019982093460025815,
      "loss": 0.7857,
      "step": 552
    },
    {
      "epoch": 0.06048342994640709,
      "grad_norm": 1.4929778575897217,
      "learning_rate": 0.00019982024807457967,
      "loss": 1.0744,
      "step": 553
    },
    {
      "epoch": 0.060592803237449415,
      "grad_norm": 1.174723744392395,
      "learning_rate": 0.00019981956023655336,
      "loss": 1.124,
      "step": 554
    },
    {
      "epoch": 0.06070217652849174,
      "grad_norm": 1.4608044624328613,
      "learning_rate": 0.00019981887108618825,
      "loss": 0.91,
      "step": 555
    },
    {
      "epoch": 0.06081154981953407,
      "grad_norm": 1.2418204545974731,
      "learning_rate": 0.00019981818062349337,
      "loss": 0.6012,
      "step": 556
    },
    {
      "epoch": 0.0609209231105764,
      "grad_norm": 1.3971385955810547,
      "learning_rate": 0.0001998174888484778,
      "loss": 0.7114,
      "step": 557
    },
    {
      "epoch": 0.06103029640161872,
      "grad_norm": 1.189285397529602,
      "learning_rate": 0.0001998167957611507,
      "loss": 1.3319,
      "step": 558
    },
    {
      "epoch": 0.061139669692661054,
      "grad_norm": 1.088165521621704,
      "learning_rate": 0.0001998161013615211,
      "loss": 0.6337,
      "step": 559
    },
    {
      "epoch": 0.06124904298370338,
      "grad_norm": 1.2663531303405762,
      "learning_rate": 0.0001998154056495982,
      "loss": 0.7802,
      "step": 560
    },
    {
      "epoch": 0.061358416274745704,
      "grad_norm": 1.002173900604248,
      "learning_rate": 0.00019981470862539107,
      "loss": 0.8206,
      "step": 561
    },
    {
      "epoch": 0.061467789565788036,
      "grad_norm": 1.1963932514190674,
      "learning_rate": 0.00019981401028890895,
      "loss": 1.1556,
      "step": 562
    },
    {
      "epoch": 0.06157716285683036,
      "grad_norm": 1.1052930355072021,
      "learning_rate": 0.00019981331064016097,
      "loss": 0.9486,
      "step": 563
    },
    {
      "epoch": 0.061686536147872686,
      "grad_norm": 0.9965226054191589,
      "learning_rate": 0.00019981260967915634,
      "loss": 0.766,
      "step": 564
    },
    {
      "epoch": 0.06179590943891502,
      "grad_norm": 1.6856166124343872,
      "learning_rate": 0.0001998119074059043,
      "loss": 0.6992,
      "step": 565
    },
    {
      "epoch": 0.061905282729957344,
      "grad_norm": 1.4077011346817017,
      "learning_rate": 0.00019981120382041404,
      "loss": 0.8003,
      "step": 566
    },
    {
      "epoch": 0.06201465602099967,
      "grad_norm": 1.032565951347351,
      "learning_rate": 0.00019981049892269482,
      "loss": 0.7922,
      "step": 567
    },
    {
      "epoch": 0.062124029312042,
      "grad_norm": 1.1922955513000488,
      "learning_rate": 0.00019980979271275596,
      "loss": 0.7718,
      "step": 568
    },
    {
      "epoch": 0.062233402603084326,
      "grad_norm": 0.9688342213630676,
      "learning_rate": 0.00019980908519060667,
      "loss": 0.7989,
      "step": 569
    },
    {
      "epoch": 0.06234277589412666,
      "grad_norm": 1.5489237308502197,
      "learning_rate": 0.00019980837635625632,
      "loss": 0.8059,
      "step": 570
    },
    {
      "epoch": 0.06245214918516898,
      "grad_norm": 1.9893778562545776,
      "learning_rate": 0.0001998076662097142,
      "loss": 0.8632,
      "step": 571
    },
    {
      "epoch": 0.06256152247621131,
      "grad_norm": 1.1985156536102295,
      "learning_rate": 0.00019980695475098958,
      "loss": 1.0229,
      "step": 572
    },
    {
      "epoch": 0.06267089576725364,
      "grad_norm": 0.994389533996582,
      "learning_rate": 0.00019980624198009193,
      "loss": 1.1044,
      "step": 573
    },
    {
      "epoch": 0.06278026905829596,
      "grad_norm": 0.9276033043861389,
      "learning_rate": 0.00019980552789703056,
      "loss": 0.9062,
      "step": 574
    },
    {
      "epoch": 0.06288964234933829,
      "grad_norm": 1.2080670595169067,
      "learning_rate": 0.00019980481250181487,
      "loss": 0.769,
      "step": 575
    },
    {
      "epoch": 0.06299901564038062,
      "grad_norm": 1.1223119497299194,
      "learning_rate": 0.00019980409579445425,
      "loss": 1.137,
      "step": 576
    },
    {
      "epoch": 0.06310838893142294,
      "grad_norm": 1.0903812646865845,
      "learning_rate": 0.00019980337777495812,
      "loss": 0.9827,
      "step": 577
    },
    {
      "epoch": 0.06321776222246528,
      "grad_norm": 1.0898516178131104,
      "learning_rate": 0.00019980265844333594,
      "loss": 0.8881,
      "step": 578
    },
    {
      "epoch": 0.0633271355135076,
      "grad_norm": 0.9497270584106445,
      "learning_rate": 0.00019980193779959717,
      "loss": 0.9331,
      "step": 579
    },
    {
      "epoch": 0.06343650880454993,
      "grad_norm": 1.1686186790466309,
      "learning_rate": 0.00019980121584375126,
      "loss": 0.8766,
      "step": 580
    },
    {
      "epoch": 0.06354588209559225,
      "grad_norm": 1.187633991241455,
      "learning_rate": 0.00019980049257580773,
      "loss": 0.8418,
      "step": 581
    },
    {
      "epoch": 0.06365525538663458,
      "grad_norm": 1.136193037033081,
      "learning_rate": 0.00019979976799577607,
      "loss": 0.7776,
      "step": 582
    },
    {
      "epoch": 0.0637646286776769,
      "grad_norm": 1.1883234977722168,
      "learning_rate": 0.0001997990421036658,
      "loss": 0.8067,
      "step": 583
    },
    {
      "epoch": 0.06387400196871924,
      "grad_norm": 1.0206081867218018,
      "learning_rate": 0.0001997983148994865,
      "loss": 1.0334,
      "step": 584
    },
    {
      "epoch": 0.06398337525976157,
      "grad_norm": 0.9565343260765076,
      "learning_rate": 0.00019979758638324772,
      "loss": 0.9657,
      "step": 585
    },
    {
      "epoch": 0.0640927485508039,
      "grad_norm": 1.2159839868545532,
      "learning_rate": 0.00019979685655495896,
      "loss": 0.8276,
      "step": 586
    },
    {
      "epoch": 0.06420212184184622,
      "grad_norm": 1.3924200534820557,
      "learning_rate": 0.00019979612541462993,
      "loss": 0.8714,
      "step": 587
    },
    {
      "epoch": 0.06431149513288854,
      "grad_norm": 1.16556978225708,
      "learning_rate": 0.00019979539296227018,
      "loss": 0.8768,
      "step": 588
    },
    {
      "epoch": 0.06442086842393088,
      "grad_norm": 1.5815696716308594,
      "learning_rate": 0.00019979465919788933,
      "loss": 0.8323,
      "step": 589
    },
    {
      "epoch": 0.06453024171497321,
      "grad_norm": 1.1107839345932007,
      "learning_rate": 0.00019979392412149707,
      "loss": 0.8951,
      "step": 590
    },
    {
      "epoch": 0.06463961500601553,
      "grad_norm": 0.9651502966880798,
      "learning_rate": 0.00019979318773310302,
      "loss": 1.1726,
      "step": 591
    },
    {
      "epoch": 0.06474898829705786,
      "grad_norm": 1.1854195594787598,
      "learning_rate": 0.0001997924500327169,
      "loss": 0.7009,
      "step": 592
    },
    {
      "epoch": 0.06485836158810018,
      "grad_norm": 1.102640986442566,
      "learning_rate": 0.0001997917110203484,
      "loss": 0.7523,
      "step": 593
    },
    {
      "epoch": 0.06496773487914251,
      "grad_norm": 1.0900192260742188,
      "learning_rate": 0.00019979097069600717,
      "loss": 0.6592,
      "step": 594
    },
    {
      "epoch": 0.06507710817018485,
      "grad_norm": 1.2523647546768188,
      "learning_rate": 0.00019979022905970307,
      "loss": 0.7598,
      "step": 595
    },
    {
      "epoch": 0.06518648146122717,
      "grad_norm": 1.1489145755767822,
      "learning_rate": 0.00019978948611144574,
      "loss": 0.8636,
      "step": 596
    },
    {
      "epoch": 0.0652958547522695,
      "grad_norm": 1.1444084644317627,
      "learning_rate": 0.00019978874185124502,
      "loss": 0.8351,
      "step": 597
    },
    {
      "epoch": 0.06540522804331182,
      "grad_norm": 1.0838830471038818,
      "learning_rate": 0.00019978799627911063,
      "loss": 0.9453,
      "step": 598
    },
    {
      "epoch": 0.06551460133435415,
      "grad_norm": 0.9383161067962646,
      "learning_rate": 0.00019978724939505242,
      "loss": 0.7702,
      "step": 599
    },
    {
      "epoch": 0.06562397462539647,
      "grad_norm": 1.2142367362976074,
      "learning_rate": 0.00019978650119908018,
      "loss": 0.7413,
      "step": 600
    },
    {
      "epoch": 0.06562397462539647,
      "eval_loss": 0.817609429359436,
      "eval_runtime": 40.8601,
      "eval_samples_per_second": 18.013,
      "eval_steps_per_second": 4.503,
      "step": 600
    },
    {
      "epoch": 0.06573334791643881,
      "grad_norm": 1.1490843296051025,
      "learning_rate": 0.0001997857516912038,
      "loss": 1.2676,
      "step": 601
    },
    {
      "epoch": 0.06584272120748114,
      "grad_norm": 1.0191518068313599,
      "learning_rate": 0.00019978500087143307,
      "loss": 1.0855,
      "step": 602
    },
    {
      "epoch": 0.06595209449852346,
      "grad_norm": 1.3642194271087646,
      "learning_rate": 0.00019978424873977785,
      "loss": 0.6015,
      "step": 603
    },
    {
      "epoch": 0.06606146778956579,
      "grad_norm": 1.4552335739135742,
      "learning_rate": 0.00019978349529624812,
      "loss": 1.1351,
      "step": 604
    },
    {
      "epoch": 0.06617084108060811,
      "grad_norm": 1.0363779067993164,
      "learning_rate": 0.0001997827405408537,
      "loss": 0.6271,
      "step": 605
    },
    {
      "epoch": 0.06628021437165044,
      "grad_norm": 1.104835033416748,
      "learning_rate": 0.00019978198447360456,
      "loss": 0.789,
      "step": 606
    },
    {
      "epoch": 0.06638958766269278,
      "grad_norm": 1.1536211967468262,
      "learning_rate": 0.00019978122709451063,
      "loss": 0.8427,
      "step": 607
    },
    {
      "epoch": 0.0664989609537351,
      "grad_norm": 1.244495153427124,
      "learning_rate": 0.00019978046840358183,
      "loss": 0.8738,
      "step": 608
    },
    {
      "epoch": 0.06660833424477743,
      "grad_norm": 0.9507635831832886,
      "learning_rate": 0.00019977970840082818,
      "loss": 0.9701,
      "step": 609
    },
    {
      "epoch": 0.06671770753581975,
      "grad_norm": 1.0605548620224,
      "learning_rate": 0.00019977894708625966,
      "loss": 0.9389,
      "step": 610
    },
    {
      "epoch": 0.06682708082686208,
      "grad_norm": 1.1662912368774414,
      "learning_rate": 0.0001997781844598863,
      "loss": 0.8314,
      "step": 611
    },
    {
      "epoch": 0.0669364541179044,
      "grad_norm": 1.1008390188217163,
      "learning_rate": 0.00019977742052171803,
      "loss": 0.9678,
      "step": 612
    },
    {
      "epoch": 0.06704582740894674,
      "grad_norm": 0.9262655377388,
      "learning_rate": 0.00019977665527176502,
      "loss": 1.1337,
      "step": 613
    },
    {
      "epoch": 0.06715520069998906,
      "grad_norm": 1.0576245784759521,
      "learning_rate": 0.00019977588871003727,
      "loss": 0.8009,
      "step": 614
    },
    {
      "epoch": 0.06726457399103139,
      "grad_norm": 1.2124804258346558,
      "learning_rate": 0.00019977512083654486,
      "loss": 0.9089,
      "step": 615
    },
    {
      "epoch": 0.06737394728207372,
      "grad_norm": 1.283664584159851,
      "learning_rate": 0.0001997743516512979,
      "loss": 0.8328,
      "step": 616
    },
    {
      "epoch": 0.06748332057311604,
      "grad_norm": 1.108501672744751,
      "learning_rate": 0.0001997735811543065,
      "loss": 0.8678,
      "step": 617
    },
    {
      "epoch": 0.06759269386415838,
      "grad_norm": 1.1499704122543335,
      "learning_rate": 0.00019977280934558076,
      "loss": 0.9058,
      "step": 618
    },
    {
      "epoch": 0.0677020671552007,
      "grad_norm": 1.1553590297698975,
      "learning_rate": 0.00019977203622513086,
      "loss": 0.7613,
      "step": 619
    },
    {
      "epoch": 0.06781144044624303,
      "grad_norm": 1.5791667699813843,
      "learning_rate": 0.00019977126179296693,
      "loss": 0.7606,
      "step": 620
    },
    {
      "epoch": 0.06792081373728535,
      "grad_norm": 1.0687192678451538,
      "learning_rate": 0.0001997704860490992,
      "loss": 0.7789,
      "step": 621
    },
    {
      "epoch": 0.06803018702832768,
      "grad_norm": 1.2858752012252808,
      "learning_rate": 0.00019976970899353785,
      "loss": 1.04,
      "step": 622
    },
    {
      "epoch": 0.06813956031937,
      "grad_norm": 1.2823305130004883,
      "learning_rate": 0.00019976893062629308,
      "loss": 0.7686,
      "step": 623
    },
    {
      "epoch": 0.06824893361041234,
      "grad_norm": 0.7791513800621033,
      "learning_rate": 0.00019976815094737514,
      "loss": 0.9096,
      "step": 624
    },
    {
      "epoch": 0.06835830690145467,
      "grad_norm": 1.144914984703064,
      "learning_rate": 0.00019976736995679426,
      "loss": 1.0989,
      "step": 625
    },
    {
      "epoch": 0.068467680192497,
      "grad_norm": 1.3526418209075928,
      "learning_rate": 0.00019976658765456074,
      "loss": 0.9081,
      "step": 626
    },
    {
      "epoch": 0.06857705348353932,
      "grad_norm": 1.377889633178711,
      "learning_rate": 0.0001997658040406848,
      "loss": 0.8414,
      "step": 627
    },
    {
      "epoch": 0.06868642677458164,
      "grad_norm": 1.0736886262893677,
      "learning_rate": 0.00019976501911517683,
      "loss": 0.9343,
      "step": 628
    },
    {
      "epoch": 0.06879580006562397,
      "grad_norm": 1.338830590248108,
      "learning_rate": 0.00019976423287804712,
      "loss": 1.1015,
      "step": 629
    },
    {
      "epoch": 0.06890517335666631,
      "grad_norm": 0.9553831219673157,
      "learning_rate": 0.00019976344532930597,
      "loss": 0.7355,
      "step": 630
    },
    {
      "epoch": 0.06901454664770863,
      "grad_norm": 0.9868148565292358,
      "learning_rate": 0.00019976265646896377,
      "loss": 0.9508,
      "step": 631
    },
    {
      "epoch": 0.06912391993875096,
      "grad_norm": 1.1125775575637817,
      "learning_rate": 0.00019976186629703087,
      "loss": 0.9547,
      "step": 632
    },
    {
      "epoch": 0.06923329322979328,
      "grad_norm": 0.9383817911148071,
      "learning_rate": 0.0001997610748135177,
      "loss": 0.8079,
      "step": 633
    },
    {
      "epoch": 0.06934266652083561,
      "grad_norm": 1.1855041980743408,
      "learning_rate": 0.0001997602820184346,
      "loss": 0.9058,
      "step": 634
    },
    {
      "epoch": 0.06945203981187793,
      "grad_norm": 0.9881440997123718,
      "learning_rate": 0.00019975948791179203,
      "loss": 0.9206,
      "step": 635
    },
    {
      "epoch": 0.06956141310292027,
      "grad_norm": 0.9503551125526428,
      "learning_rate": 0.00019975869249360043,
      "loss": 0.8653,
      "step": 636
    },
    {
      "epoch": 0.0696707863939626,
      "grad_norm": 1.2306631803512573,
      "learning_rate": 0.00019975789576387028,
      "loss": 0.9693,
      "step": 637
    },
    {
      "epoch": 0.06978015968500492,
      "grad_norm": 1.0904885530471802,
      "learning_rate": 0.000199757097722612,
      "loss": 0.4848,
      "step": 638
    },
    {
      "epoch": 0.06988953297604725,
      "grad_norm": 1.0348321199417114,
      "learning_rate": 0.00019975629836983612,
      "loss": 0.7544,
      "step": 639
    },
    {
      "epoch": 0.06999890626708957,
      "grad_norm": 1.4437801837921143,
      "learning_rate": 0.00019975549770555312,
      "loss": 0.8284,
      "step": 640
    },
    {
      "epoch": 0.0701082795581319,
      "grad_norm": 1.0044362545013428,
      "learning_rate": 0.0001997546957297736,
      "loss": 0.8013,
      "step": 641
    },
    {
      "epoch": 0.07021765284917424,
      "grad_norm": 0.8750835657119751,
      "learning_rate": 0.00019975389244250802,
      "loss": 0.9223,
      "step": 642
    },
    {
      "epoch": 0.07032702614021656,
      "grad_norm": 0.9822641611099243,
      "learning_rate": 0.00019975308784376695,
      "loss": 0.503,
      "step": 643
    },
    {
      "epoch": 0.07043639943125889,
      "grad_norm": 1.0298289060592651,
      "learning_rate": 0.00019975228193356103,
      "loss": 0.7897,
      "step": 644
    },
    {
      "epoch": 0.07054577272230121,
      "grad_norm": 1.4158082008361816,
      "learning_rate": 0.0001997514747119008,
      "loss": 0.7782,
      "step": 645
    },
    {
      "epoch": 0.07065514601334354,
      "grad_norm": 1.096412181854248,
      "learning_rate": 0.0001997506661787969,
      "loss": 1.014,
      "step": 646
    },
    {
      "epoch": 0.07076451930438588,
      "grad_norm": 1.2402337789535522,
      "learning_rate": 0.00019974985633425995,
      "loss": 0.9853,
      "step": 647
    },
    {
      "epoch": 0.0708738925954282,
      "grad_norm": 1.048528790473938,
      "learning_rate": 0.00019974904517830057,
      "loss": 0.7008,
      "step": 648
    },
    {
      "epoch": 0.07098326588647053,
      "grad_norm": 1.127461552619934,
      "learning_rate": 0.00019974823271092946,
      "loss": 0.8591,
      "step": 649
    },
    {
      "epoch": 0.07109263917751285,
      "grad_norm": 1.5449364185333252,
      "learning_rate": 0.00019974741893215729,
      "loss": 0.6911,
      "step": 650
    },
    {
      "epoch": 0.07120201246855518,
      "grad_norm": 1.1602526903152466,
      "learning_rate": 0.00019974660384199474,
      "loss": 0.7851,
      "step": 651
    },
    {
      "epoch": 0.0713113857595975,
      "grad_norm": 1.5102430582046509,
      "learning_rate": 0.0001997457874404526,
      "loss": 0.5834,
      "step": 652
    },
    {
      "epoch": 0.07142075905063984,
      "grad_norm": 0.9589799642562866,
      "learning_rate": 0.0001997449697275415,
      "loss": 1.086,
      "step": 653
    },
    {
      "epoch": 0.07153013234168216,
      "grad_norm": 0.9409639239311218,
      "learning_rate": 0.00019974415070327228,
      "loss": 0.6376,
      "step": 654
    },
    {
      "epoch": 0.07163950563272449,
      "grad_norm": 1.3825045824050903,
      "learning_rate": 0.00019974333036765565,
      "loss": 1.05,
      "step": 655
    },
    {
      "epoch": 0.07174887892376682,
      "grad_norm": 1.228034257888794,
      "learning_rate": 0.0001997425087207024,
      "loss": 0.756,
      "step": 656
    },
    {
      "epoch": 0.07185825221480914,
      "grad_norm": 1.1063343286514282,
      "learning_rate": 0.00019974168576242333,
      "loss": 0.94,
      "step": 657
    },
    {
      "epoch": 0.07196762550585147,
      "grad_norm": 1.1796149015426636,
      "learning_rate": 0.0001997408614928293,
      "loss": 1.1948,
      "step": 658
    },
    {
      "epoch": 0.0720769987968938,
      "grad_norm": 1.2910804748535156,
      "learning_rate": 0.00019974003591193113,
      "loss": 0.7471,
      "step": 659
    },
    {
      "epoch": 0.07218637208793613,
      "grad_norm": 0.950053334236145,
      "learning_rate": 0.00019973920901973966,
      "loss": 0.8559,
      "step": 660
    },
    {
      "epoch": 0.07229574537897845,
      "grad_norm": 1.1288427114486694,
      "learning_rate": 0.00019973838081626576,
      "loss": 0.7652,
      "step": 661
    },
    {
      "epoch": 0.07240511867002078,
      "grad_norm": 1.3732799291610718,
      "learning_rate": 0.00019973755130152032,
      "loss": 0.9279,
      "step": 662
    },
    {
      "epoch": 0.0725144919610631,
      "grad_norm": 1.5457011461257935,
      "learning_rate": 0.00019973672047551426,
      "loss": 1.0739,
      "step": 663
    },
    {
      "epoch": 0.07262386525210543,
      "grad_norm": 1.3835077285766602,
      "learning_rate": 0.0001997358883382585,
      "loss": 0.9601,
      "step": 664
    },
    {
      "epoch": 0.07273323854314777,
      "grad_norm": 1.0740020275115967,
      "learning_rate": 0.00019973505488976394,
      "loss": 0.8934,
      "step": 665
    },
    {
      "epoch": 0.0728426118341901,
      "grad_norm": 1.0193759202957153,
      "learning_rate": 0.0001997342201300416,
      "loss": 0.8884,
      "step": 666
    },
    {
      "epoch": 0.07295198512523242,
      "grad_norm": 1.0482374429702759,
      "learning_rate": 0.00019973338405910243,
      "loss": 0.9933,
      "step": 667
    },
    {
      "epoch": 0.07306135841627474,
      "grad_norm": 0.8073828816413879,
      "learning_rate": 0.0001997325466769574,
      "loss": 0.4287,
      "step": 668
    },
    {
      "epoch": 0.07317073170731707,
      "grad_norm": 1.123384952545166,
      "learning_rate": 0.0001997317079836176,
      "loss": 1.0069,
      "step": 669
    },
    {
      "epoch": 0.0732801049983594,
      "grad_norm": 1.0574086904525757,
      "learning_rate": 0.00019973086797909391,
      "loss": 0.9728,
      "step": 670
    },
    {
      "epoch": 0.07338947828940173,
      "grad_norm": 1.0201141834259033,
      "learning_rate": 0.0001997300266633975,
      "loss": 1.0972,
      "step": 671
    },
    {
      "epoch": 0.07349885158044406,
      "grad_norm": 1.225523591041565,
      "learning_rate": 0.00019972918403653934,
      "loss": 0.8404,
      "step": 672
    },
    {
      "epoch": 0.07360822487148638,
      "grad_norm": 1.357897162437439,
      "learning_rate": 0.00019972834009853062,
      "loss": 1.0389,
      "step": 673
    },
    {
      "epoch": 0.07371759816252871,
      "grad_norm": 1.0925666093826294,
      "learning_rate": 0.00019972749484938233,
      "loss": 0.9689,
      "step": 674
    },
    {
      "epoch": 0.07382697145357103,
      "grad_norm": 1.1267412900924683,
      "learning_rate": 0.00019972664828910564,
      "loss": 0.7727,
      "step": 675
    },
    {
      "epoch": 0.07393634474461337,
      "grad_norm": 1.2903382778167725,
      "learning_rate": 0.00019972580041771165,
      "loss": 1.1321,
      "step": 676
    },
    {
      "epoch": 0.0740457180356557,
      "grad_norm": 1.1655809879302979,
      "learning_rate": 0.00019972495123521156,
      "loss": 0.9803,
      "step": 677
    },
    {
      "epoch": 0.07415509132669802,
      "grad_norm": 0.9937360286712646,
      "learning_rate": 0.00019972410074161644,
      "loss": 1.2199,
      "step": 678
    },
    {
      "epoch": 0.07426446461774035,
      "grad_norm": 1.1037606000900269,
      "learning_rate": 0.00019972324893693756,
      "loss": 0.8067,
      "step": 679
    },
    {
      "epoch": 0.07437383790878267,
      "grad_norm": 1.7199792861938477,
      "learning_rate": 0.0001997223958211861,
      "loss": 0.9226,
      "step": 680
    },
    {
      "epoch": 0.074483211199825,
      "grad_norm": 1.2497960329055786,
      "learning_rate": 0.00019972154139437324,
      "loss": 1.2316,
      "step": 681
    },
    {
      "epoch": 0.07459258449086734,
      "grad_norm": 1.2246016263961792,
      "learning_rate": 0.00019972068565651024,
      "loss": 0.7142,
      "step": 682
    },
    {
      "epoch": 0.07470195778190966,
      "grad_norm": 1.1919150352478027,
      "learning_rate": 0.00019971982860760834,
      "loss": 0.8632,
      "step": 683
    },
    {
      "epoch": 0.07481133107295199,
      "grad_norm": 1.457666039466858,
      "learning_rate": 0.00019971897024767882,
      "loss": 0.8739,
      "step": 684
    },
    {
      "epoch": 0.07492070436399431,
      "grad_norm": 1.2749696969985962,
      "learning_rate": 0.00019971811057673295,
      "loss": 0.6209,
      "step": 685
    },
    {
      "epoch": 0.07503007765503664,
      "grad_norm": 2.0851213932037354,
      "learning_rate": 0.00019971724959478202,
      "loss": 0.9724,
      "step": 686
    },
    {
      "epoch": 0.07513945094607896,
      "grad_norm": 1.120041847229004,
      "learning_rate": 0.00019971638730183742,
      "loss": 1.0215,
      "step": 687
    },
    {
      "epoch": 0.0752488242371213,
      "grad_norm": 1.146913766860962,
      "learning_rate": 0.0001997155236979104,
      "loss": 0.9925,
      "step": 688
    },
    {
      "epoch": 0.07535819752816363,
      "grad_norm": 1.2135933637619019,
      "learning_rate": 0.00019971465878301236,
      "loss": 0.6812,
      "step": 689
    },
    {
      "epoch": 0.07546757081920595,
      "grad_norm": 1.5919603109359741,
      "learning_rate": 0.00019971379255715466,
      "loss": 0.9658,
      "step": 690
    },
    {
      "epoch": 0.07557694411024828,
      "grad_norm": 0.9288296699523926,
      "learning_rate": 0.00019971292502034868,
      "loss": 1.1744,
      "step": 691
    },
    {
      "epoch": 0.0756863174012906,
      "grad_norm": 1.343369960784912,
      "learning_rate": 0.00019971205617260585,
      "loss": 0.9064,
      "step": 692
    },
    {
      "epoch": 0.07579569069233293,
      "grad_norm": 1.2773042917251587,
      "learning_rate": 0.00019971118601393756,
      "loss": 0.5802,
      "step": 693
    },
    {
      "epoch": 0.07590506398337526,
      "grad_norm": 1.0229064226150513,
      "learning_rate": 0.0001997103145443553,
      "loss": 0.8091,
      "step": 694
    },
    {
      "epoch": 0.07601443727441759,
      "grad_norm": 1.152958869934082,
      "learning_rate": 0.00019970944176387047,
      "loss": 0.7775,
      "step": 695
    },
    {
      "epoch": 0.07612381056545992,
      "grad_norm": 0.848763644695282,
      "learning_rate": 0.00019970856767249456,
      "loss": 0.7118,
      "step": 696
    },
    {
      "epoch": 0.07623318385650224,
      "grad_norm": 1.7074475288391113,
      "learning_rate": 0.0001997076922702391,
      "loss": 0.9012,
      "step": 697
    },
    {
      "epoch": 0.07634255714754457,
      "grad_norm": 0.8505508899688721,
      "learning_rate": 0.00019970681555711556,
      "loss": 0.9937,
      "step": 698
    },
    {
      "epoch": 0.07645193043858689,
      "grad_norm": 1.1460299491882324,
      "learning_rate": 0.0001997059375331355,
      "loss": 0.5383,
      "step": 699
    },
    {
      "epoch": 0.07656130372962923,
      "grad_norm": 1.167402982711792,
      "learning_rate": 0.00019970505819831043,
      "loss": 0.692,
      "step": 700
    },
    {
      "epoch": 0.07667067702067155,
      "grad_norm": 1.3995429277420044,
      "learning_rate": 0.0001997041775526519,
      "loss": 0.8846,
      "step": 701
    },
    {
      "epoch": 0.07678005031171388,
      "grad_norm": 1.0239083766937256,
      "learning_rate": 0.0001997032955961715,
      "loss": 0.8172,
      "step": 702
    },
    {
      "epoch": 0.0768894236027562,
      "grad_norm": 1.228286862373352,
      "learning_rate": 0.00019970241232888087,
      "loss": 0.8918,
      "step": 703
    },
    {
      "epoch": 0.07699879689379853,
      "grad_norm": 1.2466994524002075,
      "learning_rate": 0.00019970152775079157,
      "loss": 0.9824,
      "step": 704
    },
    {
      "epoch": 0.07710817018484087,
      "grad_norm": 1.0454096794128418,
      "learning_rate": 0.00019970064186191524,
      "loss": 0.7876,
      "step": 705
    },
    {
      "epoch": 0.0772175434758832,
      "grad_norm": 1.3275943994522095,
      "learning_rate": 0.00019969975466226352,
      "loss": 0.7415,
      "step": 706
    },
    {
      "epoch": 0.07732691676692552,
      "grad_norm": 1.2628555297851562,
      "learning_rate": 0.00019969886615184813,
      "loss": 0.9612,
      "step": 707
    },
    {
      "epoch": 0.07743629005796784,
      "grad_norm": 1.2491726875305176,
      "learning_rate": 0.00019969797633068067,
      "loss": 0.9752,
      "step": 708
    },
    {
      "epoch": 0.07754566334901017,
      "grad_norm": 1.105066180229187,
      "learning_rate": 0.0001996970851987729,
      "loss": 0.8346,
      "step": 709
    },
    {
      "epoch": 0.0776550366400525,
      "grad_norm": 1.2142994403839111,
      "learning_rate": 0.00019969619275613649,
      "loss": 0.7027,
      "step": 710
    },
    {
      "epoch": 0.07776440993109483,
      "grad_norm": 0.9537602663040161,
      "learning_rate": 0.0001996952990027832,
      "loss": 1.044,
      "step": 711
    },
    {
      "epoch": 0.07787378322213716,
      "grad_norm": 1.3910495042800903,
      "learning_rate": 0.00019969440393872482,
      "loss": 1.0096,
      "step": 712
    },
    {
      "epoch": 0.07798315651317948,
      "grad_norm": 1.3613632917404175,
      "learning_rate": 0.00019969350756397303,
      "loss": 0.8662,
      "step": 713
    },
    {
      "epoch": 0.07809252980422181,
      "grad_norm": 1.2845927476882935,
      "learning_rate": 0.00019969260987853966,
      "loss": 0.5798,
      "step": 714
    },
    {
      "epoch": 0.07820190309526413,
      "grad_norm": 1.6404705047607422,
      "learning_rate": 0.00019969171088243654,
      "loss": 0.7121,
      "step": 715
    },
    {
      "epoch": 0.07831127638630646,
      "grad_norm": 0.8574418425559998,
      "learning_rate": 0.00019969081057567544,
      "loss": 0.8782,
      "step": 716
    },
    {
      "epoch": 0.0784206496773488,
      "grad_norm": 1.0659464597702026,
      "learning_rate": 0.00019968990895826824,
      "loss": 0.9873,
      "step": 717
    },
    {
      "epoch": 0.07853002296839112,
      "grad_norm": 1.3987879753112793,
      "learning_rate": 0.00019968900603022674,
      "loss": 1.043,
      "step": 718
    },
    {
      "epoch": 0.07863939625943345,
      "grad_norm": 1.4074671268463135,
      "learning_rate": 0.00019968810179156284,
      "loss": 0.5627,
      "step": 719
    },
    {
      "epoch": 0.07874876955047577,
      "grad_norm": 1.5267953872680664,
      "learning_rate": 0.0001996871962422884,
      "loss": 0.8376,
      "step": 720
    },
    {
      "epoch": 0.0788581428415181,
      "grad_norm": 1.3651149272918701,
      "learning_rate": 0.00019968628938241544,
      "loss": 0.5277,
      "step": 721
    },
    {
      "epoch": 0.07896751613256042,
      "grad_norm": 1.42264723777771,
      "learning_rate": 0.00019968538121195573,
      "loss": 0.8679,
      "step": 722
    },
    {
      "epoch": 0.07907688942360276,
      "grad_norm": 0.9253861904144287,
      "learning_rate": 0.00019968447173092127,
      "loss": 0.6319,
      "step": 723
    },
    {
      "epoch": 0.07918626271464509,
      "grad_norm": 1.3918668031692505,
      "learning_rate": 0.00019968356093932408,
      "loss": 0.9424,
      "step": 724
    },
    {
      "epoch": 0.07929563600568741,
      "grad_norm": 1.2722500562667847,
      "learning_rate": 0.00019968264883717603,
      "loss": 0.7896,
      "step": 725
    },
    {
      "epoch": 0.07940500929672974,
      "grad_norm": 1.1754547357559204,
      "learning_rate": 0.00019968173542448918,
      "loss": 0.7964,
      "step": 726
    },
    {
      "epoch": 0.07951438258777206,
      "grad_norm": 1.2456198930740356,
      "learning_rate": 0.0001996808207012755,
      "loss": 0.9675,
      "step": 727
    },
    {
      "epoch": 0.07962375587881439,
      "grad_norm": 1.112210750579834,
      "learning_rate": 0.00019967990466754706,
      "loss": 0.8094,
      "step": 728
    },
    {
      "epoch": 0.07973312916985673,
      "grad_norm": 1.4162180423736572,
      "learning_rate": 0.00019967898732331589,
      "loss": 0.7958,
      "step": 729
    },
    {
      "epoch": 0.07984250246089905,
      "grad_norm": 1.1824671030044556,
      "learning_rate": 0.00019967806866859399,
      "loss": 0.9652,
      "step": 730
    },
    {
      "epoch": 0.07995187575194138,
      "grad_norm": 1.1127402782440186,
      "learning_rate": 0.00019967714870339353,
      "loss": 1.0534,
      "step": 731
    },
    {
      "epoch": 0.0800612490429837,
      "grad_norm": 1.2103041410446167,
      "learning_rate": 0.00019967622742772653,
      "loss": 0.8203,
      "step": 732
    },
    {
      "epoch": 0.08017062233402603,
      "grad_norm": 1.122659683227539,
      "learning_rate": 0.00019967530484160515,
      "loss": 1.0141,
      "step": 733
    },
    {
      "epoch": 0.08027999562506836,
      "grad_norm": 1.188337802886963,
      "learning_rate": 0.0001996743809450415,
      "loss": 0.8292,
      "step": 734
    },
    {
      "epoch": 0.08038936891611069,
      "grad_norm": 1.3577244281768799,
      "learning_rate": 0.00019967345573804773,
      "loss": 0.7919,
      "step": 735
    },
    {
      "epoch": 0.08049874220715302,
      "grad_norm": 1.403151035308838,
      "learning_rate": 0.00019967252922063598,
      "loss": 0.7486,
      "step": 736
    },
    {
      "epoch": 0.08060811549819534,
      "grad_norm": 1.0413349866867065,
      "learning_rate": 0.00019967160139281847,
      "loss": 0.7938,
      "step": 737
    },
    {
      "epoch": 0.08071748878923767,
      "grad_norm": 1.182256817817688,
      "learning_rate": 0.00019967067225460739,
      "loss": 1.0254,
      "step": 738
    },
    {
      "epoch": 0.08082686208027999,
      "grad_norm": 1.1335121393203735,
      "learning_rate": 0.00019966974180601495,
      "loss": 0.9295,
      "step": 739
    },
    {
      "epoch": 0.08093623537132233,
      "grad_norm": 0.9481456875801086,
      "learning_rate": 0.00019966881004705335,
      "loss": 0.7879,
      "step": 740
    },
    {
      "epoch": 0.08104560866236465,
      "grad_norm": 1.5649831295013428,
      "learning_rate": 0.00019966787697773487,
      "loss": 0.8673,
      "step": 741
    },
    {
      "epoch": 0.08115498195340698,
      "grad_norm": 0.9668005108833313,
      "learning_rate": 0.00019966694259807182,
      "loss": 1.0657,
      "step": 742
    },
    {
      "epoch": 0.0812643552444493,
      "grad_norm": 1.3596941232681274,
      "learning_rate": 0.00019966600690807641,
      "loss": 0.8447,
      "step": 743
    },
    {
      "epoch": 0.08137372853549163,
      "grad_norm": 1.0048425197601318,
      "learning_rate": 0.000199665069907761,
      "loss": 1.0387,
      "step": 744
    },
    {
      "epoch": 0.08148310182653395,
      "grad_norm": 1.011863350868225,
      "learning_rate": 0.00019966413159713784,
      "loss": 0.572,
      "step": 745
    },
    {
      "epoch": 0.0815924751175763,
      "grad_norm": 1.1538282632827759,
      "learning_rate": 0.00019966319197621933,
      "loss": 0.8894,
      "step": 746
    },
    {
      "epoch": 0.08170184840861862,
      "grad_norm": 1.2780123949050903,
      "learning_rate": 0.0001996622510450178,
      "loss": 0.7546,
      "step": 747
    },
    {
      "epoch": 0.08181122169966094,
      "grad_norm": 1.2636635303497314,
      "learning_rate": 0.00019966130880354563,
      "loss": 1.0885,
      "step": 748
    },
    {
      "epoch": 0.08192059499070327,
      "grad_norm": 1.4378074407577515,
      "learning_rate": 0.00019966036525181517,
      "loss": 0.8398,
      "step": 749
    },
    {
      "epoch": 0.0820299682817456,
      "grad_norm": 0.9686568975448608,
      "learning_rate": 0.0001996594203898389,
      "loss": 0.8958,
      "step": 750
    },
    {
      "epoch": 0.08213934157278792,
      "grad_norm": 0.9453415274620056,
      "learning_rate": 0.00019965847421762916,
      "loss": 0.7573,
      "step": 751
    },
    {
      "epoch": 0.08224871486383026,
      "grad_norm": 1.0684524774551392,
      "learning_rate": 0.00019965752673519843,
      "loss": 1.0317,
      "step": 752
    },
    {
      "epoch": 0.08235808815487258,
      "grad_norm": 1.2976714372634888,
      "learning_rate": 0.00019965657794255917,
      "loss": 0.8801,
      "step": 753
    },
    {
      "epoch": 0.08246746144591491,
      "grad_norm": 1.2436695098876953,
      "learning_rate": 0.00019965562783972384,
      "loss": 0.9685,
      "step": 754
    },
    {
      "epoch": 0.08257683473695723,
      "grad_norm": 1.6265769004821777,
      "learning_rate": 0.00019965467642670494,
      "loss": 0.8696,
      "step": 755
    },
    {
      "epoch": 0.08268620802799956,
      "grad_norm": 1.113477110862732,
      "learning_rate": 0.00019965372370351497,
      "loss": 0.7968,
      "step": 756
    },
    {
      "epoch": 0.08279558131904188,
      "grad_norm": 1.1436411142349243,
      "learning_rate": 0.00019965276967016647,
      "loss": 0.8767,
      "step": 757
    },
    {
      "epoch": 0.08290495461008422,
      "grad_norm": 1.0350077152252197,
      "learning_rate": 0.000199651814326672,
      "loss": 0.8886,
      "step": 758
    },
    {
      "epoch": 0.08301432790112655,
      "grad_norm": 1.208807110786438,
      "learning_rate": 0.00019965085767304408,
      "loss": 0.6376,
      "step": 759
    },
    {
      "epoch": 0.08312370119216887,
      "grad_norm": 1.3621273040771484,
      "learning_rate": 0.00019964989970929525,
      "loss": 0.8308,
      "step": 760
    },
    {
      "epoch": 0.0832330744832112,
      "grad_norm": 1.2521097660064697,
      "learning_rate": 0.00019964894043543823,
      "loss": 0.8721,
      "step": 761
    },
    {
      "epoch": 0.08334244777425352,
      "grad_norm": 1.5560908317565918,
      "learning_rate": 0.00019964797985148552,
      "loss": 1.0384,
      "step": 762
    },
    {
      "epoch": 0.08345182106529586,
      "grad_norm": 0.8045756220817566,
      "learning_rate": 0.0001996470179574498,
      "loss": 0.6202,
      "step": 763
    },
    {
      "epoch": 0.08356119435633819,
      "grad_norm": 1.2550946474075317,
      "learning_rate": 0.00019964605475334367,
      "loss": 0.6782,
      "step": 764
    },
    {
      "epoch": 0.08367056764738051,
      "grad_norm": 1.165345311164856,
      "learning_rate": 0.00019964509023917985,
      "loss": 0.9765,
      "step": 765
    },
    {
      "epoch": 0.08377994093842284,
      "grad_norm": 1.181070327758789,
      "learning_rate": 0.00019964412441497102,
      "loss": 0.9072,
      "step": 766
    },
    {
      "epoch": 0.08388931422946516,
      "grad_norm": 1.2799577713012695,
      "learning_rate": 0.00019964315728072983,
      "loss": 0.7609,
      "step": 767
    },
    {
      "epoch": 0.08399868752050749,
      "grad_norm": 1.2581814527511597,
      "learning_rate": 0.00019964218883646901,
      "loss": 1.0167,
      "step": 768
    },
    {
      "epoch": 0.08410806081154983,
      "grad_norm": 1.2967522144317627,
      "learning_rate": 0.00019964121908220132,
      "loss": 1.0021,
      "step": 769
    },
    {
      "epoch": 0.08421743410259215,
      "grad_norm": 1.5000118017196655,
      "learning_rate": 0.00019964024801793947,
      "loss": 0.7812,
      "step": 770
    },
    {
      "epoch": 0.08432680739363448,
      "grad_norm": 1.1445389986038208,
      "learning_rate": 0.00019963927564369625,
      "loss": 0.7056,
      "step": 771
    },
    {
      "epoch": 0.0844361806846768,
      "grad_norm": 1.3679161071777344,
      "learning_rate": 0.00019963830195948446,
      "loss": 0.6822,
      "step": 772
    },
    {
      "epoch": 0.08454555397571913,
      "grad_norm": 1.0828126668930054,
      "learning_rate": 0.0001996373269653169,
      "loss": 0.7763,
      "step": 773
    },
    {
      "epoch": 0.08465492726676145,
      "grad_norm": 1.3515561819076538,
      "learning_rate": 0.00019963635066120634,
      "loss": 0.8533,
      "step": 774
    },
    {
      "epoch": 0.08476430055780379,
      "grad_norm": 1.3976073265075684,
      "learning_rate": 0.00019963537304716568,
      "loss": 0.9915,
      "step": 775
    },
    {
      "epoch": 0.08487367384884612,
      "grad_norm": 0.981069803237915,
      "learning_rate": 0.00019963439412320767,
      "loss": 0.6723,
      "step": 776
    },
    {
      "epoch": 0.08498304713988844,
      "grad_norm": 1.1897884607315063,
      "learning_rate": 0.0001996334138893453,
      "loss": 0.8058,
      "step": 777
    },
    {
      "epoch": 0.08509242043093077,
      "grad_norm": 1.029106855392456,
      "learning_rate": 0.00019963243234559142,
      "loss": 0.7647,
      "step": 778
    },
    {
      "epoch": 0.08520179372197309,
      "grad_norm": 1.119536280632019,
      "learning_rate": 0.0001996314494919589,
      "loss": 0.7175,
      "step": 779
    },
    {
      "epoch": 0.08531116701301542,
      "grad_norm": 1.2119157314300537,
      "learning_rate": 0.00019963046532846067,
      "loss": 0.7693,
      "step": 780
    },
    {
      "epoch": 0.08542054030405775,
      "grad_norm": 1.2779622077941895,
      "learning_rate": 0.00019962947985510972,
      "loss": 1.0908,
      "step": 781
    },
    {
      "epoch": 0.08552991359510008,
      "grad_norm": 1.5152631998062134,
      "learning_rate": 0.00019962849307191894,
      "loss": 0.9018,
      "step": 782
    },
    {
      "epoch": 0.0856392868861424,
      "grad_norm": 1.2640904188156128,
      "learning_rate": 0.00019962750497890132,
      "loss": 1.1887,
      "step": 783
    },
    {
      "epoch": 0.08574866017718473,
      "grad_norm": 1.3365931510925293,
      "learning_rate": 0.00019962651557606988,
      "loss": 0.7064,
      "step": 784
    },
    {
      "epoch": 0.08585803346822705,
      "grad_norm": 1.191049575805664,
      "learning_rate": 0.0001996255248634376,
      "loss": 0.9107,
      "step": 785
    },
    {
      "epoch": 0.08596740675926938,
      "grad_norm": 1.3733034133911133,
      "learning_rate": 0.00019962453284101754,
      "loss": 0.8751,
      "step": 786
    },
    {
      "epoch": 0.08607678005031172,
      "grad_norm": 1.3037829399108887,
      "learning_rate": 0.00019962353950882272,
      "loss": 1.1918,
      "step": 787
    },
    {
      "epoch": 0.08618615334135404,
      "grad_norm": 1.273435354232788,
      "learning_rate": 0.00019962254486686616,
      "loss": 0.6163,
      "step": 788
    },
    {
      "epoch": 0.08629552663239637,
      "grad_norm": 1.2746548652648926,
      "learning_rate": 0.00019962154891516097,
      "loss": 0.8341,
      "step": 789
    },
    {
      "epoch": 0.0864048999234387,
      "grad_norm": 0.8775056600570679,
      "learning_rate": 0.00019962055165372028,
      "loss": 0.5022,
      "step": 790
    },
    {
      "epoch": 0.08651427321448102,
      "grad_norm": 1.1755577325820923,
      "learning_rate": 0.00019961955308255718,
      "loss": 0.7566,
      "step": 791
    },
    {
      "epoch": 0.08662364650552336,
      "grad_norm": 1.5284981727600098,
      "learning_rate": 0.00019961855320168475,
      "loss": 0.6847,
      "step": 792
    },
    {
      "epoch": 0.08673301979656568,
      "grad_norm": 1.4542872905731201,
      "learning_rate": 0.00019961755201111618,
      "loss": 1.0386,
      "step": 793
    },
    {
      "epoch": 0.08684239308760801,
      "grad_norm": 1.3919121026992798,
      "learning_rate": 0.0001996165495108646,
      "loss": 0.9977,
      "step": 794
    },
    {
      "epoch": 0.08695176637865033,
      "grad_norm": 1.5708112716674805,
      "learning_rate": 0.00019961554570094325,
      "loss": 0.6402,
      "step": 795
    },
    {
      "epoch": 0.08706113966969266,
      "grad_norm": 0.9465711712837219,
      "learning_rate": 0.0001996145405813653,
      "loss": 0.9086,
      "step": 796
    },
    {
      "epoch": 0.08717051296073498,
      "grad_norm": 1.1368910074234009,
      "learning_rate": 0.00019961353415214394,
      "loss": 0.7948,
      "step": 797
    },
    {
      "epoch": 0.08727988625177732,
      "grad_norm": 1.1227450370788574,
      "learning_rate": 0.00019961252641329243,
      "loss": 0.7257,
      "step": 798
    },
    {
      "epoch": 0.08738925954281965,
      "grad_norm": 1.1165131330490112,
      "learning_rate": 0.000199611517364824,
      "loss": 0.6876,
      "step": 799
    },
    {
      "epoch": 0.08749863283386197,
      "grad_norm": 0.9231796264648438,
      "learning_rate": 0.0001996105070067519,
      "loss": 0.8655,
      "step": 800
    },
    {
      "epoch": 0.08749863283386197,
      "eval_loss": 0.8182419538497925,
      "eval_runtime": 40.9467,
      "eval_samples_per_second": 17.975,
      "eval_steps_per_second": 4.494,
      "step": 800
    },
    {
      "epoch": 0.0876080061249043,
      "grad_norm": 0.9535033702850342,
      "learning_rate": 0.00019960949533908947,
      "loss": 0.5837,
      "step": 801
    },
    {
      "epoch": 0.08771737941594662,
      "grad_norm": 1.0001469850540161,
      "learning_rate": 0.00019960848236184994,
      "loss": 0.8218,
      "step": 802
    },
    {
      "epoch": 0.08782675270698895,
      "grad_norm": 0.9336425065994263,
      "learning_rate": 0.0001996074680750467,
      "loss": 0.7247,
      "step": 803
    },
    {
      "epoch": 0.08793612599803129,
      "grad_norm": 1.1211315393447876,
      "learning_rate": 0.00019960645247869306,
      "loss": 0.932,
      "step": 804
    },
    {
      "epoch": 0.08804549928907361,
      "grad_norm": 1.1419967412948608,
      "learning_rate": 0.00019960543557280232,
      "loss": 0.8864,
      "step": 805
    },
    {
      "epoch": 0.08815487258011594,
      "grad_norm": 1.0939565896987915,
      "learning_rate": 0.0001996044173573879,
      "loss": 1.049,
      "step": 806
    },
    {
      "epoch": 0.08826424587115826,
      "grad_norm": 1.215834617614746,
      "learning_rate": 0.00019960339783246317,
      "loss": 0.7574,
      "step": 807
    },
    {
      "epoch": 0.08837361916220059,
      "grad_norm": 1.1480846405029297,
      "learning_rate": 0.00019960237699804157,
      "loss": 1.0014,
      "step": 808
    },
    {
      "epoch": 0.08848299245324291,
      "grad_norm": 0.9107721447944641,
      "learning_rate": 0.0001996013548541365,
      "loss": 0.9391,
      "step": 809
    },
    {
      "epoch": 0.08859236574428525,
      "grad_norm": 1.5890494585037231,
      "learning_rate": 0.00019960033140076135,
      "loss": 0.8012,
      "step": 810
    },
    {
      "epoch": 0.08870173903532758,
      "grad_norm": 0.8832481503486633,
      "learning_rate": 0.00019959930663792963,
      "loss": 1.1373,
      "step": 811
    },
    {
      "epoch": 0.0888111123263699,
      "grad_norm": 1.0795847177505493,
      "learning_rate": 0.00019959828056565482,
      "loss": 0.7,
      "step": 812
    },
    {
      "epoch": 0.08892048561741223,
      "grad_norm": 0.908379077911377,
      "learning_rate": 0.00019959725318395037,
      "loss": 0.9298,
      "step": 813
    },
    {
      "epoch": 0.08902985890845455,
      "grad_norm": 1.1739095449447632,
      "learning_rate": 0.0001995962244928298,
      "loss": 0.7351,
      "step": 814
    },
    {
      "epoch": 0.08913923219949688,
      "grad_norm": 1.2324635982513428,
      "learning_rate": 0.00019959519449230665,
      "loss": 1.0177,
      "step": 815
    },
    {
      "epoch": 0.08924860549053922,
      "grad_norm": 1.2192935943603516,
      "learning_rate": 0.00019959416318239445,
      "loss": 0.5567,
      "step": 816
    },
    {
      "epoch": 0.08935797878158154,
      "grad_norm": 1.4438891410827637,
      "learning_rate": 0.00019959313056310677,
      "loss": 1.223,
      "step": 817
    },
    {
      "epoch": 0.08946735207262387,
      "grad_norm": 1.1402913331985474,
      "learning_rate": 0.00019959209663445715,
      "loss": 1.3433,
      "step": 818
    },
    {
      "epoch": 0.08957672536366619,
      "grad_norm": 1.3516430854797363,
      "learning_rate": 0.00019959106139645925,
      "loss": 0.9054,
      "step": 819
    },
    {
      "epoch": 0.08968609865470852,
      "grad_norm": 1.0977493524551392,
      "learning_rate": 0.0001995900248491266,
      "loss": 0.8874,
      "step": 820
    },
    {
      "epoch": 0.08979547194575085,
      "grad_norm": 1.1743345260620117,
      "learning_rate": 0.00019958898699247289,
      "loss": 0.8661,
      "step": 821
    },
    {
      "epoch": 0.08990484523679318,
      "grad_norm": 1.2266860008239746,
      "learning_rate": 0.00019958794782651173,
      "loss": 0.6191,
      "step": 822
    },
    {
      "epoch": 0.0900142185278355,
      "grad_norm": 0.9657822251319885,
      "learning_rate": 0.00019958690735125682,
      "loss": 0.871,
      "step": 823
    },
    {
      "epoch": 0.09012359181887783,
      "grad_norm": 1.24700927734375,
      "learning_rate": 0.00019958586556672177,
      "loss": 0.566,
      "step": 824
    },
    {
      "epoch": 0.09023296510992015,
      "grad_norm": 1.1197797060012817,
      "learning_rate": 0.00019958482247292033,
      "loss": 0.8812,
      "step": 825
    },
    {
      "epoch": 0.09034233840096248,
      "grad_norm": 1.1232218742370605,
      "learning_rate": 0.00019958377806986624,
      "loss": 0.8536,
      "step": 826
    },
    {
      "epoch": 0.09045171169200482,
      "grad_norm": 1.542871117591858,
      "learning_rate": 0.00019958273235757317,
      "loss": 1.0144,
      "step": 827
    },
    {
      "epoch": 0.09056108498304714,
      "grad_norm": 1.1551693677902222,
      "learning_rate": 0.00019958168533605491,
      "loss": 0.9076,
      "step": 828
    },
    {
      "epoch": 0.09067045827408947,
      "grad_norm": 1.194580078125,
      "learning_rate": 0.00019958063700532515,
      "loss": 0.8739,
      "step": 829
    },
    {
      "epoch": 0.0907798315651318,
      "grad_norm": 1.5410252809524536,
      "learning_rate": 0.0001995795873653978,
      "loss": 0.9722,
      "step": 830
    },
    {
      "epoch": 0.09088920485617412,
      "grad_norm": 1.229311466217041,
      "learning_rate": 0.00019957853641628656,
      "loss": 0.9499,
      "step": 831
    },
    {
      "epoch": 0.09099857814721644,
      "grad_norm": 1.1045327186584473,
      "learning_rate": 0.0001995774841580053,
      "loss": 0.685,
      "step": 832
    },
    {
      "epoch": 0.09110795143825878,
      "grad_norm": 1.4332363605499268,
      "learning_rate": 0.00019957643059056781,
      "loss": 0.7151,
      "step": 833
    },
    {
      "epoch": 0.09121732472930111,
      "grad_norm": 1.2968801259994507,
      "learning_rate": 0.00019957537571398796,
      "loss": 0.7946,
      "step": 834
    },
    {
      "epoch": 0.09132669802034343,
      "grad_norm": 1.0148797035217285,
      "learning_rate": 0.00019957431952827962,
      "loss": 0.8544,
      "step": 835
    },
    {
      "epoch": 0.09143607131138576,
      "grad_norm": 0.9621775150299072,
      "learning_rate": 0.00019957326203345668,
      "loss": 0.9745,
      "step": 836
    },
    {
      "epoch": 0.09154544460242808,
      "grad_norm": 1.2392730712890625,
      "learning_rate": 0.00019957220322953302,
      "loss": 0.4786,
      "step": 837
    },
    {
      "epoch": 0.09165481789347041,
      "grad_norm": 1.4548712968826294,
      "learning_rate": 0.00019957114311652262,
      "loss": 0.6708,
      "step": 838
    },
    {
      "epoch": 0.09176419118451275,
      "grad_norm": 1.454961895942688,
      "learning_rate": 0.00019957008169443937,
      "loss": 1.0329,
      "step": 839
    },
    {
      "epoch": 0.09187356447555507,
      "grad_norm": 1.2699053287506104,
      "learning_rate": 0.00019956901896329724,
      "loss": 0.6117,
      "step": 840
    },
    {
      "epoch": 0.0919829377665974,
      "grad_norm": 1.3051475286483765,
      "learning_rate": 0.00019956795492311014,
      "loss": 0.9572,
      "step": 841
    },
    {
      "epoch": 0.09209231105763972,
      "grad_norm": 1.2349427938461304,
      "learning_rate": 0.00019956688957389215,
      "loss": 0.7841,
      "step": 842
    },
    {
      "epoch": 0.09220168434868205,
      "grad_norm": 1.0892583131790161,
      "learning_rate": 0.00019956582291565724,
      "loss": 0.6221,
      "step": 843
    },
    {
      "epoch": 0.09231105763972437,
      "grad_norm": 1.7155765295028687,
      "learning_rate": 0.00019956475494841943,
      "loss": 0.8352,
      "step": 844
    },
    {
      "epoch": 0.09242043093076671,
      "grad_norm": 1.3395003080368042,
      "learning_rate": 0.00019956368567219276,
      "loss": 0.8833,
      "step": 845
    },
    {
      "epoch": 0.09252980422180904,
      "grad_norm": 1.1988462209701538,
      "learning_rate": 0.00019956261508699132,
      "loss": 0.8453,
      "step": 846
    },
    {
      "epoch": 0.09263917751285136,
      "grad_norm": 1.2849291563034058,
      "learning_rate": 0.00019956154319282913,
      "loss": 0.9758,
      "step": 847
    },
    {
      "epoch": 0.09274855080389369,
      "grad_norm": 0.9945152401924133,
      "learning_rate": 0.0001995604699897203,
      "loss": 0.7195,
      "step": 848
    },
    {
      "epoch": 0.09285792409493601,
      "grad_norm": 1.1506707668304443,
      "learning_rate": 0.00019955939547767896,
      "loss": 0.8726,
      "step": 849
    },
    {
      "epoch": 0.09296729738597835,
      "grad_norm": 1.3727513551712036,
      "learning_rate": 0.00019955831965671921,
      "loss": 1.0069,
      "step": 850
    },
    {
      "epoch": 0.09307667067702068,
      "grad_norm": 1.1457537412643433,
      "learning_rate": 0.00019955724252685526,
      "loss": 1.0295,
      "step": 851
    },
    {
      "epoch": 0.093186043968063,
      "grad_norm": 1.3083910942077637,
      "learning_rate": 0.0001995561640881012,
      "loss": 0.8109,
      "step": 852
    },
    {
      "epoch": 0.09329541725910533,
      "grad_norm": 1.1764094829559326,
      "learning_rate": 0.00019955508434047118,
      "loss": 0.6939,
      "step": 853
    },
    {
      "epoch": 0.09340479055014765,
      "grad_norm": 1.1331216096878052,
      "learning_rate": 0.0001995540032839795,
      "loss": 1.1515,
      "step": 854
    },
    {
      "epoch": 0.09351416384118998,
      "grad_norm": 1.0536712408065796,
      "learning_rate": 0.00019955292091864029,
      "loss": 0.6403,
      "step": 855
    },
    {
      "epoch": 0.09362353713223232,
      "grad_norm": 0.8079434037208557,
      "learning_rate": 0.0001995518372444678,
      "loss": 0.7601,
      "step": 856
    },
    {
      "epoch": 0.09373291042327464,
      "grad_norm": 1.0035877227783203,
      "learning_rate": 0.0001995507522614763,
      "loss": 0.8642,
      "step": 857
    },
    {
      "epoch": 0.09384228371431697,
      "grad_norm": 0.9096612930297852,
      "learning_rate": 0.00019954966596968002,
      "loss": 1.1461,
      "step": 858
    },
    {
      "epoch": 0.09395165700535929,
      "grad_norm": 1.1789451837539673,
      "learning_rate": 0.00019954857836909328,
      "loss": 1.1652,
      "step": 859
    },
    {
      "epoch": 0.09406103029640162,
      "grad_norm": 1.2239881753921509,
      "learning_rate": 0.00019954748945973037,
      "loss": 1.2469,
      "step": 860
    },
    {
      "epoch": 0.09417040358744394,
      "grad_norm": 1.324474811553955,
      "learning_rate": 0.00019954639924160556,
      "loss": 0.9968,
      "step": 861
    },
    {
      "epoch": 0.09427977687848628,
      "grad_norm": 1.157252550125122,
      "learning_rate": 0.00019954530771473325,
      "loss": 1.1599,
      "step": 862
    },
    {
      "epoch": 0.0943891501695286,
      "grad_norm": 0.7629270553588867,
      "learning_rate": 0.00019954421487912774,
      "loss": 0.7209,
      "step": 863
    },
    {
      "epoch": 0.09449852346057093,
      "grad_norm": 1.4981436729431152,
      "learning_rate": 0.00019954312073480345,
      "loss": 0.7902,
      "step": 864
    },
    {
      "epoch": 0.09460789675161325,
      "grad_norm": 1.2095366716384888,
      "learning_rate": 0.00019954202528177465,
      "loss": 1.0945,
      "step": 865
    },
    {
      "epoch": 0.09471727004265558,
      "grad_norm": 1.2913610935211182,
      "learning_rate": 0.00019954092852005588,
      "loss": 0.7072,
      "step": 866
    },
    {
      "epoch": 0.0948266433336979,
      "grad_norm": 1.056751012802124,
      "learning_rate": 0.00019953983044966153,
      "loss": 0.9528,
      "step": 867
    },
    {
      "epoch": 0.09493601662474024,
      "grad_norm": 1.055098533630371,
      "learning_rate": 0.00019953873107060596,
      "loss": 0.984,
      "step": 868
    },
    {
      "epoch": 0.09504538991578257,
      "grad_norm": 1.341044545173645,
      "learning_rate": 0.00019953763038290368,
      "loss": 0.7982,
      "step": 869
    },
    {
      "epoch": 0.0951547632068249,
      "grad_norm": 0.9234110713005066,
      "learning_rate": 0.00019953652838656917,
      "loss": 0.7717,
      "step": 870
    },
    {
      "epoch": 0.09526413649786722,
      "grad_norm": 1.9180636405944824,
      "learning_rate": 0.00019953542508161689,
      "loss": 1.0908,
      "step": 871
    },
    {
      "epoch": 0.09537350978890954,
      "grad_norm": 1.0126632452011108,
      "learning_rate": 0.00019953432046806137,
      "loss": 0.8611,
      "step": 872
    },
    {
      "epoch": 0.09548288307995187,
      "grad_norm": 0.9232673645019531,
      "learning_rate": 0.00019953321454591709,
      "loss": 0.8924,
      "step": 873
    },
    {
      "epoch": 0.09559225637099421,
      "grad_norm": 1.4557191133499146,
      "learning_rate": 0.00019953210731519865,
      "loss": 0.7869,
      "step": 874
    },
    {
      "epoch": 0.09570162966203653,
      "grad_norm": 1.2406479120254517,
      "learning_rate": 0.00019953099877592057,
      "loss": 0.9444,
      "step": 875
    },
    {
      "epoch": 0.09581100295307886,
      "grad_norm": 1.7575751543045044,
      "learning_rate": 0.00019952988892809744,
      "loss": 0.9689,
      "step": 876
    },
    {
      "epoch": 0.09592037624412118,
      "grad_norm": 1.237321376800537,
      "learning_rate": 0.0001995287777717438,
      "loss": 0.9258,
      "step": 877
    },
    {
      "epoch": 0.09602974953516351,
      "grad_norm": 1.3944149017333984,
      "learning_rate": 0.00019952766530687433,
      "loss": 0.7997,
      "step": 878
    },
    {
      "epoch": 0.09613912282620585,
      "grad_norm": 1.2106367349624634,
      "learning_rate": 0.0001995265515335036,
      "loss": 0.7602,
      "step": 879
    },
    {
      "epoch": 0.09624849611724817,
      "grad_norm": 1.1708970069885254,
      "learning_rate": 0.0001995254364516463,
      "loss": 0.9178,
      "step": 880
    },
    {
      "epoch": 0.0963578694082905,
      "grad_norm": 1.2044042348861694,
      "learning_rate": 0.00019952432006131707,
      "loss": 0.8981,
      "step": 881
    },
    {
      "epoch": 0.09646724269933282,
      "grad_norm": 1.2091017961502075,
      "learning_rate": 0.0001995232023625306,
      "loss": 1.0984,
      "step": 882
    },
    {
      "epoch": 0.09657661599037515,
      "grad_norm": 1.210006833076477,
      "learning_rate": 0.00019952208335530155,
      "loss": 0.6739,
      "step": 883
    },
    {
      "epoch": 0.09668598928141747,
      "grad_norm": 1.1765155792236328,
      "learning_rate": 0.00019952096303964463,
      "loss": 0.6625,
      "step": 884
    },
    {
      "epoch": 0.09679536257245981,
      "grad_norm": 1.6544713973999023,
      "learning_rate": 0.0001995198414155746,
      "loss": 0.8313,
      "step": 885
    },
    {
      "epoch": 0.09690473586350214,
      "grad_norm": 1.509202480316162,
      "learning_rate": 0.00019951871848310622,
      "loss": 0.8709,
      "step": 886
    },
    {
      "epoch": 0.09701410915454446,
      "grad_norm": 0.8444991707801819,
      "learning_rate": 0.00019951759424225422,
      "loss": 0.7864,
      "step": 887
    },
    {
      "epoch": 0.09712348244558679,
      "grad_norm": 1.0528488159179688,
      "learning_rate": 0.0001995164686930334,
      "loss": 1.0549,
      "step": 888
    },
    {
      "epoch": 0.09723285573662911,
      "grad_norm": 1.2691233158111572,
      "learning_rate": 0.00019951534183545856,
      "loss": 0.8455,
      "step": 889
    },
    {
      "epoch": 0.09734222902767144,
      "grad_norm": 1.04086172580719,
      "learning_rate": 0.00019951421366954446,
      "loss": 1.1132,
      "step": 890
    },
    {
      "epoch": 0.09745160231871378,
      "grad_norm": 1.0036054849624634,
      "learning_rate": 0.00019951308419530599,
      "loss": 0.794,
      "step": 891
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 1.2341976165771484,
      "learning_rate": 0.00019951195341275798,
      "loss": 0.8283,
      "step": 892
    },
    {
      "epoch": 0.09767034890079843,
      "grad_norm": 1.5961192846298218,
      "learning_rate": 0.0001995108213219153,
      "loss": 0.704,
      "step": 893
    },
    {
      "epoch": 0.09777972219184075,
      "grad_norm": 0.947320282459259,
      "learning_rate": 0.00019950968792279287,
      "loss": 0.852,
      "step": 894
    },
    {
      "epoch": 0.09788909548288308,
      "grad_norm": 1.3363678455352783,
      "learning_rate": 0.00019950855321540555,
      "loss": 0.883,
      "step": 895
    },
    {
      "epoch": 0.0979984687739254,
      "grad_norm": 0.8344139456748962,
      "learning_rate": 0.00019950741719976825,
      "loss": 0.9032,
      "step": 896
    },
    {
      "epoch": 0.09810784206496774,
      "grad_norm": 1.7639341354370117,
      "learning_rate": 0.0001995062798758959,
      "loss": 0.8914,
      "step": 897
    },
    {
      "epoch": 0.09821721535601007,
      "grad_norm": 1.239662766456604,
      "learning_rate": 0.0001995051412438035,
      "loss": 0.4648,
      "step": 898
    },
    {
      "epoch": 0.09832658864705239,
      "grad_norm": 1.1349619626998901,
      "learning_rate": 0.00019950400130350597,
      "loss": 0.8947,
      "step": 899
    },
    {
      "epoch": 0.09843596193809472,
      "grad_norm": 1.0377110242843628,
      "learning_rate": 0.00019950286005501833,
      "loss": 1.0922,
      "step": 900
    },
    {
      "epoch": 0.09854533522913704,
      "grad_norm": 1.5270278453826904,
      "learning_rate": 0.00019950171749835558,
      "loss": 0.7132,
      "step": 901
    },
    {
      "epoch": 0.09865470852017937,
      "grad_norm": 1.3682656288146973,
      "learning_rate": 0.00019950057363353273,
      "loss": 0.6956,
      "step": 902
    },
    {
      "epoch": 0.0987640818112217,
      "grad_norm": 1.4862194061279297,
      "learning_rate": 0.0001994994284605648,
      "loss": 1.1994,
      "step": 903
    },
    {
      "epoch": 0.09887345510226403,
      "grad_norm": 1.3727412223815918,
      "learning_rate": 0.0001994982819794669,
      "loss": 0.9017,
      "step": 904
    },
    {
      "epoch": 0.09898282839330635,
      "grad_norm": 1.2614322900772095,
      "learning_rate": 0.00019949713419025407,
      "loss": 0.8639,
      "step": 905
    },
    {
      "epoch": 0.09909220168434868,
      "grad_norm": 0.9942101240158081,
      "learning_rate": 0.00019949598509294138,
      "loss": 0.9419,
      "step": 906
    },
    {
      "epoch": 0.099201574975391,
      "grad_norm": 1.2384140491485596,
      "learning_rate": 0.00019949483468754395,
      "loss": 0.7995,
      "step": 907
    },
    {
      "epoch": 0.09931094826643334,
      "grad_norm": 1.643040418624878,
      "learning_rate": 0.00019949368297407695,
      "loss": 0.5917,
      "step": 908
    },
    {
      "epoch": 0.09942032155747567,
      "grad_norm": 1.224613904953003,
      "learning_rate": 0.00019949252995255545,
      "loss": 0.7475,
      "step": 909
    },
    {
      "epoch": 0.099529694848518,
      "grad_norm": 1.0784614086151123,
      "learning_rate": 0.00019949137562299467,
      "loss": 0.7325,
      "step": 910
    },
    {
      "epoch": 0.09963906813956032,
      "grad_norm": 1.1546502113342285,
      "learning_rate": 0.00019949021998540975,
      "loss": 0.706,
      "step": 911
    },
    {
      "epoch": 0.09974844143060264,
      "grad_norm": 0.9804129600524902,
      "learning_rate": 0.0001994890630398159,
      "loss": 0.914,
      "step": 912
    },
    {
      "epoch": 0.09985781472164497,
      "grad_norm": 1.2071402072906494,
      "learning_rate": 0.00019948790478622832,
      "loss": 1.1277,
      "step": 913
    },
    {
      "epoch": 0.09996718801268731,
      "grad_norm": 1.15370512008667,
      "learning_rate": 0.00019948674522466222,
      "loss": 0.8028,
      "step": 914
    },
    {
      "epoch": 0.10007656130372963,
      "grad_norm": 1.122122049331665,
      "learning_rate": 0.00019948558435513286,
      "loss": 0.9196,
      "step": 915
    },
    {
      "epoch": 0.10018593459477196,
      "grad_norm": 1.3481228351593018,
      "learning_rate": 0.00019948442217765556,
      "loss": 0.829,
      "step": 916
    },
    {
      "epoch": 0.10029530788581428,
      "grad_norm": 1.224122405052185,
      "learning_rate": 0.00019948325869224552,
      "loss": 0.896,
      "step": 917
    },
    {
      "epoch": 0.10040468117685661,
      "grad_norm": 1.0718632936477661,
      "learning_rate": 0.00019948209389891806,
      "loss": 0.9488,
      "step": 918
    },
    {
      "epoch": 0.10051405446789893,
      "grad_norm": 1.2147067785263062,
      "learning_rate": 0.00019948092779768848,
      "loss": 0.4492,
      "step": 919
    },
    {
      "epoch": 0.10062342775894127,
      "grad_norm": 1.484676718711853,
      "learning_rate": 0.00019947976038857217,
      "loss": 0.8467,
      "step": 920
    },
    {
      "epoch": 0.1007328010499836,
      "grad_norm": 1.0704717636108398,
      "learning_rate": 0.0001994785916715844,
      "loss": 0.8564,
      "step": 921
    },
    {
      "epoch": 0.10084217434102592,
      "grad_norm": 0.9627458453178406,
      "learning_rate": 0.0001994774216467406,
      "loss": 0.7387,
      "step": 922
    },
    {
      "epoch": 0.10095154763206825,
      "grad_norm": 1.1271440982818604,
      "learning_rate": 0.0001994762503140561,
      "loss": 0.6338,
      "step": 923
    },
    {
      "epoch": 0.10106092092311057,
      "grad_norm": 1.3446354866027832,
      "learning_rate": 0.00019947507767354634,
      "loss": 0.806,
      "step": 924
    },
    {
      "epoch": 0.1011702942141529,
      "grad_norm": 1.4003483057022095,
      "learning_rate": 0.0001994739037252267,
      "loss": 1.168,
      "step": 925
    },
    {
      "epoch": 0.10127966750519524,
      "grad_norm": 1.1401091814041138,
      "learning_rate": 0.00019947272846911266,
      "loss": 1.0078,
      "step": 926
    },
    {
      "epoch": 0.10138904079623756,
      "grad_norm": 0.9426333904266357,
      "learning_rate": 0.00019947155190521963,
      "loss": 1.2029,
      "step": 927
    },
    {
      "epoch": 0.10149841408727989,
      "grad_norm": 1.6015233993530273,
      "learning_rate": 0.00019947037403356311,
      "loss": 0.8601,
      "step": 928
    },
    {
      "epoch": 0.10160778737832221,
      "grad_norm": 1.1976593732833862,
      "learning_rate": 0.00019946919485415855,
      "loss": 0.7789,
      "step": 929
    },
    {
      "epoch": 0.10171716066936454,
      "grad_norm": 1.0622069835662842,
      "learning_rate": 0.00019946801436702147,
      "loss": 0.7763,
      "step": 930
    },
    {
      "epoch": 0.10182653396040686,
      "grad_norm": 1.2237211465835571,
      "learning_rate": 0.0001994668325721674,
      "loss": 0.5661,
      "step": 931
    },
    {
      "epoch": 0.1019359072514492,
      "grad_norm": 1.0646111965179443,
      "learning_rate": 0.00019946564946961187,
      "loss": 0.8108,
      "step": 932
    },
    {
      "epoch": 0.10204528054249153,
      "grad_norm": 1.4957557916641235,
      "learning_rate": 0.00019946446505937046,
      "loss": 0.8712,
      "step": 933
    },
    {
      "epoch": 0.10215465383353385,
      "grad_norm": 1.1500412225723267,
      "learning_rate": 0.0001994632793414587,
      "loss": 0.8437,
      "step": 934
    },
    {
      "epoch": 0.10226402712457618,
      "grad_norm": 1.8560198545455933,
      "learning_rate": 0.00019946209231589218,
      "loss": 1.0932,
      "step": 935
    },
    {
      "epoch": 0.1023734004156185,
      "grad_norm": 0.9968304634094238,
      "learning_rate": 0.00019946090398268652,
      "loss": 0.6757,
      "step": 936
    },
    {
      "epoch": 0.10248277370666084,
      "grad_norm": 1.1971726417541504,
      "learning_rate": 0.00019945971434185737,
      "loss": 0.8077,
      "step": 937
    },
    {
      "epoch": 0.10259214699770317,
      "grad_norm": 1.1957237720489502,
      "learning_rate": 0.00019945852339342033,
      "loss": 1.1207,
      "step": 938
    },
    {
      "epoch": 0.10270152028874549,
      "grad_norm": 1.2771124839782715,
      "learning_rate": 0.00019945733113739108,
      "loss": 0.8313,
      "step": 939
    },
    {
      "epoch": 0.10281089357978782,
      "grad_norm": 1.0227628946304321,
      "learning_rate": 0.00019945613757378525,
      "loss": 0.9256,
      "step": 940
    },
    {
      "epoch": 0.10292026687083014,
      "grad_norm": 1.058546781539917,
      "learning_rate": 0.0001994549427026186,
      "loss": 0.6399,
      "step": 941
    },
    {
      "epoch": 0.10302964016187247,
      "grad_norm": 1.2029428482055664,
      "learning_rate": 0.0001994537465239068,
      "loss": 0.9822,
      "step": 942
    },
    {
      "epoch": 0.1031390134529148,
      "grad_norm": 1.2278274297714233,
      "learning_rate": 0.0001994525490376656,
      "loss": 1.0237,
      "step": 943
    },
    {
      "epoch": 0.10324838674395713,
      "grad_norm": 1.1156113147735596,
      "learning_rate": 0.0001994513502439107,
      "loss": 1.0659,
      "step": 944
    },
    {
      "epoch": 0.10335776003499945,
      "grad_norm": 1.2822253704071045,
      "learning_rate": 0.0001994501501426579,
      "loss": 0.8882,
      "step": 945
    },
    {
      "epoch": 0.10346713332604178,
      "grad_norm": 1.2395724058151245,
      "learning_rate": 0.00019944894873392296,
      "loss": 0.9022,
      "step": 946
    },
    {
      "epoch": 0.1035765066170841,
      "grad_norm": 1.5277762413024902,
      "learning_rate": 0.0001994477460177217,
      "loss": 0.7879,
      "step": 947
    },
    {
      "epoch": 0.10368587990812643,
      "grad_norm": 1.5508108139038086,
      "learning_rate": 0.0001994465419940699,
      "loss": 0.6595,
      "step": 948
    },
    {
      "epoch": 0.10379525319916877,
      "grad_norm": 1.7353811264038086,
      "learning_rate": 0.0001994453366629834,
      "loss": 0.7912,
      "step": 949
    },
    {
      "epoch": 0.1039046264902111,
      "grad_norm": 1.2597202062606812,
      "learning_rate": 0.00019944413002447804,
      "loss": 0.9122,
      "step": 950
    },
    {
      "epoch": 0.10401399978125342,
      "grad_norm": 0.8856161236763,
      "learning_rate": 0.00019944292207856973,
      "loss": 0.958,
      "step": 951
    },
    {
      "epoch": 0.10412337307229574,
      "grad_norm": 1.1142675876617432,
      "learning_rate": 0.00019944171282527427,
      "loss": 0.8487,
      "step": 952
    },
    {
      "epoch": 0.10423274636333807,
      "grad_norm": 0.9531697630882263,
      "learning_rate": 0.00019944050226460762,
      "loss": 0.6694,
      "step": 953
    },
    {
      "epoch": 0.1043421196543804,
      "grad_norm": 1.542277455329895,
      "learning_rate": 0.0001994392903965857,
      "loss": 0.8129,
      "step": 954
    },
    {
      "epoch": 0.10445149294542273,
      "grad_norm": 1.6822351217269897,
      "learning_rate": 0.00019943807722122437,
      "loss": 0.7299,
      "step": 955
    },
    {
      "epoch": 0.10456086623646506,
      "grad_norm": 1.0231963396072388,
      "learning_rate": 0.00019943686273853965,
      "loss": 1.0218,
      "step": 956
    },
    {
      "epoch": 0.10467023952750738,
      "grad_norm": 1.1323602199554443,
      "learning_rate": 0.00019943564694854747,
      "loss": 0.8256,
      "step": 957
    },
    {
      "epoch": 0.10477961281854971,
      "grad_norm": 1.0868875980377197,
      "learning_rate": 0.0001994344298512639,
      "loss": 0.8666,
      "step": 958
    },
    {
      "epoch": 0.10488898610959203,
      "grad_norm": 1.1038410663604736,
      "learning_rate": 0.0001994332114467048,
      "loss": 1.0306,
      "step": 959
    },
    {
      "epoch": 0.10499835940063436,
      "grad_norm": 1.2264528274536133,
      "learning_rate": 0.0001994319917348863,
      "loss": 0.9931,
      "step": 960
    },
    {
      "epoch": 0.1051077326916767,
      "grad_norm": 1.3099048137664795,
      "learning_rate": 0.00019943077071582437,
      "loss": 0.9738,
      "step": 961
    },
    {
      "epoch": 0.10521710598271902,
      "grad_norm": 1.1323615312576294,
      "learning_rate": 0.0001994295483895351,
      "loss": 0.7654,
      "step": 962
    },
    {
      "epoch": 0.10532647927376135,
      "grad_norm": 1.001363754272461,
      "learning_rate": 0.00019942832475603454,
      "loss": 1.1669,
      "step": 963
    },
    {
      "epoch": 0.10543585256480367,
      "grad_norm": 1.0181318521499634,
      "learning_rate": 0.00019942709981533881,
      "loss": 0.9308,
      "step": 964
    },
    {
      "epoch": 0.105545225855846,
      "grad_norm": 1.2028900384902954,
      "learning_rate": 0.00019942587356746398,
      "loss": 0.9537,
      "step": 965
    },
    {
      "epoch": 0.10565459914688834,
      "grad_norm": 1.0889387130737305,
      "learning_rate": 0.0001994246460124262,
      "loss": 0.7132,
      "step": 966
    },
    {
      "epoch": 0.10576397243793066,
      "grad_norm": 1.1687062978744507,
      "learning_rate": 0.00019942341715024155,
      "loss": 0.9255,
      "step": 967
    },
    {
      "epoch": 0.10587334572897299,
      "grad_norm": 1.1625901460647583,
      "learning_rate": 0.00019942218698092626,
      "loss": 0.7728,
      "step": 968
    },
    {
      "epoch": 0.10598271902001531,
      "grad_norm": 1.3105515241622925,
      "learning_rate": 0.00019942095550449645,
      "loss": 0.9576,
      "step": 969
    },
    {
      "epoch": 0.10609209231105764,
      "grad_norm": 1.375712513923645,
      "learning_rate": 0.00019941972272096833,
      "loss": 0.7845,
      "step": 970
    },
    {
      "epoch": 0.10620146560209996,
      "grad_norm": 1.5827556848526,
      "learning_rate": 0.00019941848863035813,
      "loss": 0.9851,
      "step": 971
    },
    {
      "epoch": 0.1063108388931423,
      "grad_norm": 1.2516840696334839,
      "learning_rate": 0.00019941725323268202,
      "loss": 0.8683,
      "step": 972
    },
    {
      "epoch": 0.10642021218418463,
      "grad_norm": 1.6476911306381226,
      "learning_rate": 0.00019941601652795633,
      "loss": 0.9048,
      "step": 973
    },
    {
      "epoch": 0.10652958547522695,
      "grad_norm": 1.3262258768081665,
      "learning_rate": 0.00019941477851619723,
      "loss": 0.8709,
      "step": 974
    },
    {
      "epoch": 0.10663895876626928,
      "grad_norm": 1.1338956356048584,
      "learning_rate": 0.00019941353919742102,
      "loss": 0.9728,
      "step": 975
    },
    {
      "epoch": 0.1067483320573116,
      "grad_norm": 1.1912635564804077,
      "learning_rate": 0.00019941229857164402,
      "loss": 0.6258,
      "step": 976
    },
    {
      "epoch": 0.10685770534835393,
      "grad_norm": 1.1130871772766113,
      "learning_rate": 0.00019941105663888253,
      "loss": 0.6532,
      "step": 977
    },
    {
      "epoch": 0.10696707863939627,
      "grad_norm": 1.2323254346847534,
      "learning_rate": 0.00019940981339915286,
      "loss": 0.6111,
      "step": 978
    },
    {
      "epoch": 0.10707645193043859,
      "grad_norm": 1.1015089750289917,
      "learning_rate": 0.00019940856885247138,
      "loss": 0.9297,
      "step": 979
    },
    {
      "epoch": 0.10718582522148092,
      "grad_norm": 1.60472571849823,
      "learning_rate": 0.0001994073229988544,
      "loss": 0.9731,
      "step": 980
    },
    {
      "epoch": 0.10729519851252324,
      "grad_norm": 1.131201982498169,
      "learning_rate": 0.00019940607583831838,
      "loss": 0.767,
      "step": 981
    },
    {
      "epoch": 0.10740457180356557,
      "grad_norm": 1.0429736375808716,
      "learning_rate": 0.00019940482737087966,
      "loss": 0.9091,
      "step": 982
    },
    {
      "epoch": 0.10751394509460789,
      "grad_norm": 0.9605562686920166,
      "learning_rate": 0.0001994035775965547,
      "loss": 0.9739,
      "step": 983
    },
    {
      "epoch": 0.10762331838565023,
      "grad_norm": 1.3917828798294067,
      "learning_rate": 0.00019940232651535986,
      "loss": 0.8524,
      "step": 984
    },
    {
      "epoch": 0.10773269167669255,
      "grad_norm": 1.0217057466506958,
      "learning_rate": 0.0001994010741273116,
      "loss": 0.915,
      "step": 985
    },
    {
      "epoch": 0.10784206496773488,
      "grad_norm": 1.0886435508728027,
      "learning_rate": 0.00019939982043242648,
      "loss": 1.2458,
      "step": 986
    },
    {
      "epoch": 0.1079514382587772,
      "grad_norm": 1.5309573411941528,
      "learning_rate": 0.0001993985654307209,
      "loss": 1.2238,
      "step": 987
    },
    {
      "epoch": 0.10806081154981953,
      "grad_norm": 1.0701981782913208,
      "learning_rate": 0.00019939730912221136,
      "loss": 0.784,
      "step": 988
    },
    {
      "epoch": 0.10817018484086185,
      "grad_norm": 1.0573891401290894,
      "learning_rate": 0.0001993960515069144,
      "loss": 1.1575,
      "step": 989
    },
    {
      "epoch": 0.1082795581319042,
      "grad_norm": 1.0976394414901733,
      "learning_rate": 0.00019939479258484656,
      "loss": 0.9163,
      "step": 990
    },
    {
      "epoch": 0.10838893142294652,
      "grad_norm": 1.4406991004943848,
      "learning_rate": 0.00019939353235602433,
      "loss": 0.873,
      "step": 991
    },
    {
      "epoch": 0.10849830471398884,
      "grad_norm": 1.3609410524368286,
      "learning_rate": 0.00019939227082046437,
      "loss": 1.0543,
      "step": 992
    },
    {
      "epoch": 0.10860767800503117,
      "grad_norm": 1.1519649028778076,
      "learning_rate": 0.0001993910079781832,
      "loss": 0.784,
      "step": 993
    },
    {
      "epoch": 0.1087170512960735,
      "grad_norm": 1.45655357837677,
      "learning_rate": 0.00019938974382919747,
      "loss": 1.0298,
      "step": 994
    },
    {
      "epoch": 0.10882642458711583,
      "grad_norm": 1.1427465677261353,
      "learning_rate": 0.00019938847837352376,
      "loss": 0.7725,
      "step": 995
    },
    {
      "epoch": 0.10893579787815816,
      "grad_norm": 1.272451639175415,
      "learning_rate": 0.0001993872116111787,
      "loss": 0.799,
      "step": 996
    },
    {
      "epoch": 0.10904517116920048,
      "grad_norm": 1.3818475008010864,
      "learning_rate": 0.000199385943542179,
      "loss": 0.8428,
      "step": 997
    },
    {
      "epoch": 0.10915454446024281,
      "grad_norm": 1.7960386276245117,
      "learning_rate": 0.00019938467416654126,
      "loss": 0.9058,
      "step": 998
    },
    {
      "epoch": 0.10926391775128513,
      "grad_norm": 1.2292323112487793,
      "learning_rate": 0.00019938340348428223,
      "loss": 1.2595,
      "step": 999
    },
    {
      "epoch": 0.10937329104232746,
      "grad_norm": 1.3317714929580688,
      "learning_rate": 0.0001993821314954186,
      "loss": 0.5897,
      "step": 1000
    },
    {
      "epoch": 0.10937329104232746,
      "eval_loss": 0.8338143825531006,
      "eval_runtime": 40.981,
      "eval_samples_per_second": 17.96,
      "eval_steps_per_second": 4.49,
      "step": 1000
    },
    {
      "epoch": 0.1094826643333698,
      "grad_norm": 1.3029085397720337,
      "learning_rate": 0.00019938085819996707,
      "loss": 0.7051,
      "step": 1001
    },
    {
      "epoch": 0.10959203762441212,
      "grad_norm": 1.3885273933410645,
      "learning_rate": 0.0001993795835979444,
      "loss": 0.8482,
      "step": 1002
    },
    {
      "epoch": 0.10970141091545445,
      "grad_norm": 1.3138833045959473,
      "learning_rate": 0.00019937830768936734,
      "loss": 0.9426,
      "step": 1003
    },
    {
      "epoch": 0.10981078420649677,
      "grad_norm": 1.165816068649292,
      "learning_rate": 0.00019937703047425266,
      "loss": 0.8463,
      "step": 1004
    },
    {
      "epoch": 0.1099201574975391,
      "grad_norm": 1.4749541282653809,
      "learning_rate": 0.00019937575195261715,
      "loss": 0.8877,
      "step": 1005
    },
    {
      "epoch": 0.11002953078858142,
      "grad_norm": 1.2052497863769531,
      "learning_rate": 0.00019937447212447766,
      "loss": 0.7496,
      "step": 1006
    },
    {
      "epoch": 0.11013890407962376,
      "grad_norm": 1.328574776649475,
      "learning_rate": 0.00019937319098985097,
      "loss": 0.9381,
      "step": 1007
    },
    {
      "epoch": 0.11024827737066609,
      "grad_norm": 1.0889531373977661,
      "learning_rate": 0.00019937190854875392,
      "loss": 0.9546,
      "step": 1008
    },
    {
      "epoch": 0.11035765066170841,
      "grad_norm": 1.0116822719573975,
      "learning_rate": 0.0001993706248012034,
      "loss": 0.8989,
      "step": 1009
    },
    {
      "epoch": 0.11046702395275074,
      "grad_norm": 1.2166699171066284,
      "learning_rate": 0.00019936933974721628,
      "loss": 0.9835,
      "step": 1010
    },
    {
      "epoch": 0.11057639724379306,
      "grad_norm": 1.2124526500701904,
      "learning_rate": 0.0001993680533868094,
      "loss": 0.6474,
      "step": 1011
    },
    {
      "epoch": 0.11068577053483539,
      "grad_norm": 1.3906617164611816,
      "learning_rate": 0.0001993667657199998,
      "loss": 0.7466,
      "step": 1012
    },
    {
      "epoch": 0.11079514382587773,
      "grad_norm": 1.261439561843872,
      "learning_rate": 0.0001993654767468043,
      "loss": 0.7484,
      "step": 1013
    },
    {
      "epoch": 0.11090451711692005,
      "grad_norm": 1.1208627223968506,
      "learning_rate": 0.00019936418646723984,
      "loss": 0.5607,
      "step": 1014
    },
    {
      "epoch": 0.11101389040796238,
      "grad_norm": 0.9825077652931213,
      "learning_rate": 0.00019936289488132344,
      "loss": 1.061,
      "step": 1015
    },
    {
      "epoch": 0.1111232636990047,
      "grad_norm": 1.037803053855896,
      "learning_rate": 0.00019936160198907207,
      "loss": 1.2085,
      "step": 1016
    },
    {
      "epoch": 0.11123263699004703,
      "grad_norm": 0.9930386543273926,
      "learning_rate": 0.0001993603077905027,
      "loss": 0.8792,
      "step": 1017
    },
    {
      "epoch": 0.11134201028108935,
      "grad_norm": 1.240291953086853,
      "learning_rate": 0.00019935901228563242,
      "loss": 1.0581,
      "step": 1018
    },
    {
      "epoch": 0.11145138357213169,
      "grad_norm": 1.1221569776535034,
      "learning_rate": 0.00019935771547447813,
      "loss": 1.2503,
      "step": 1019
    },
    {
      "epoch": 0.11156075686317402,
      "grad_norm": 1.0757321119308472,
      "learning_rate": 0.000199356417357057,
      "loss": 0.8737,
      "step": 1020
    },
    {
      "epoch": 0.11167013015421634,
      "grad_norm": 1.155308723449707,
      "learning_rate": 0.00019935511793338603,
      "loss": 1.0213,
      "step": 1021
    },
    {
      "epoch": 0.11177950344525867,
      "grad_norm": 1.37980318069458,
      "learning_rate": 0.00019935381720348233,
      "loss": 0.5977,
      "step": 1022
    },
    {
      "epoch": 0.11188887673630099,
      "grad_norm": 1.43512761592865,
      "learning_rate": 0.000199352515167363,
      "loss": 0.7591,
      "step": 1023
    },
    {
      "epoch": 0.11199825002734333,
      "grad_norm": 1.7773255109786987,
      "learning_rate": 0.00019935121182504514,
      "loss": 0.7283,
      "step": 1024
    },
    {
      "epoch": 0.11210762331838565,
      "grad_norm": 1.696868896484375,
      "learning_rate": 0.00019934990717654594,
      "loss": 0.7844,
      "step": 1025
    },
    {
      "epoch": 0.11221699660942798,
      "grad_norm": 1.143088936805725,
      "learning_rate": 0.00019934860122188246,
      "loss": 0.9878,
      "step": 1026
    },
    {
      "epoch": 0.1123263699004703,
      "grad_norm": 1.112352728843689,
      "learning_rate": 0.00019934729396107196,
      "loss": 0.7798,
      "step": 1027
    },
    {
      "epoch": 0.11243574319151263,
      "grad_norm": 1.8689332008361816,
      "learning_rate": 0.00019934598539413155,
      "loss": 0.612,
      "step": 1028
    },
    {
      "epoch": 0.11254511648255495,
      "grad_norm": 0.9889987707138062,
      "learning_rate": 0.00019934467552107848,
      "loss": 1.0343,
      "step": 1029
    },
    {
      "epoch": 0.1126544897735973,
      "grad_norm": 1.5130908489227295,
      "learning_rate": 0.00019934336434192996,
      "loss": 0.7711,
      "step": 1030
    },
    {
      "epoch": 0.11276386306463962,
      "grad_norm": 1.0466634035110474,
      "learning_rate": 0.00019934205185670326,
      "loss": 1.0756,
      "step": 1031
    },
    {
      "epoch": 0.11287323635568194,
      "grad_norm": 1.2362555265426636,
      "learning_rate": 0.0001993407380654156,
      "loss": 0.8143,
      "step": 1032
    },
    {
      "epoch": 0.11298260964672427,
      "grad_norm": 1.537784218788147,
      "learning_rate": 0.00019933942296808423,
      "loss": 0.9417,
      "step": 1033
    },
    {
      "epoch": 0.1130919829377666,
      "grad_norm": 1.2751325368881226,
      "learning_rate": 0.0001993381065647265,
      "loss": 0.7144,
      "step": 1034
    },
    {
      "epoch": 0.11320135622880892,
      "grad_norm": 1.2967792749404907,
      "learning_rate": 0.00019933678885535966,
      "loss": 0.4835,
      "step": 1035
    },
    {
      "epoch": 0.11331072951985126,
      "grad_norm": 1.3515509366989136,
      "learning_rate": 0.00019933546984000105,
      "loss": 1.0139,
      "step": 1036
    },
    {
      "epoch": 0.11342010281089358,
      "grad_norm": 1.2777903079986572,
      "learning_rate": 0.00019933414951866808,
      "loss": 0.5097,
      "step": 1037
    },
    {
      "epoch": 0.11352947610193591,
      "grad_norm": 1.5770107507705688,
      "learning_rate": 0.00019933282789137797,
      "loss": 0.7356,
      "step": 1038
    },
    {
      "epoch": 0.11363884939297823,
      "grad_norm": 1.1685065031051636,
      "learning_rate": 0.00019933150495814823,
      "loss": 0.8904,
      "step": 1039
    },
    {
      "epoch": 0.11374822268402056,
      "grad_norm": 1.177513599395752,
      "learning_rate": 0.0001993301807189962,
      "loss": 0.626,
      "step": 1040
    },
    {
      "epoch": 0.11385759597506288,
      "grad_norm": 1.173245906829834,
      "learning_rate": 0.00019932885517393923,
      "loss": 0.8395,
      "step": 1041
    },
    {
      "epoch": 0.11396696926610522,
      "grad_norm": 1.0264663696289062,
      "learning_rate": 0.00019932752832299485,
      "loss": 1.2055,
      "step": 1042
    },
    {
      "epoch": 0.11407634255714755,
      "grad_norm": 0.9537520408630371,
      "learning_rate": 0.00019932620016618047,
      "loss": 0.8463,
      "step": 1043
    },
    {
      "epoch": 0.11418571584818987,
      "grad_norm": 1.092235803604126,
      "learning_rate": 0.00019932487070351348,
      "loss": 0.9027,
      "step": 1044
    },
    {
      "epoch": 0.1142950891392322,
      "grad_norm": 1.0555747747421265,
      "learning_rate": 0.00019932353993501147,
      "loss": 0.9653,
      "step": 1045
    },
    {
      "epoch": 0.11440446243027452,
      "grad_norm": 1.4583306312561035,
      "learning_rate": 0.00019932220786069186,
      "loss": 0.7427,
      "step": 1046
    },
    {
      "epoch": 0.11451383572131685,
      "grad_norm": 1.2356376647949219,
      "learning_rate": 0.00019932087448057222,
      "loss": 0.9556,
      "step": 1047
    },
    {
      "epoch": 0.11462320901235919,
      "grad_norm": 1.3306739330291748,
      "learning_rate": 0.00019931953979467003,
      "loss": 0.8455,
      "step": 1048
    },
    {
      "epoch": 0.11473258230340151,
      "grad_norm": 1.1184591054916382,
      "learning_rate": 0.00019931820380300283,
      "loss": 0.9796,
      "step": 1049
    },
    {
      "epoch": 0.11484195559444384,
      "grad_norm": 1.4422471523284912,
      "learning_rate": 0.00019931686650558823,
      "loss": 0.9608,
      "step": 1050
    },
    {
      "epoch": 0.11495132888548616,
      "grad_norm": 1.1774966716766357,
      "learning_rate": 0.00019931552790244378,
      "loss": 0.757,
      "step": 1051
    },
    {
      "epoch": 0.11506070217652849,
      "grad_norm": 1.2277871370315552,
      "learning_rate": 0.0001993141879935871,
      "loss": 0.834,
      "step": 1052
    },
    {
      "epoch": 0.11517007546757083,
      "grad_norm": 1.1363190412521362,
      "learning_rate": 0.0001993128467790358,
      "loss": 0.9226,
      "step": 1053
    },
    {
      "epoch": 0.11527944875861315,
      "grad_norm": 1.0564334392547607,
      "learning_rate": 0.00019931150425880748,
      "loss": 0.6555,
      "step": 1054
    },
    {
      "epoch": 0.11538882204965548,
      "grad_norm": 1.293544888496399,
      "learning_rate": 0.00019931016043291987,
      "loss": 0.7078,
      "step": 1055
    },
    {
      "epoch": 0.1154981953406978,
      "grad_norm": 1.206676959991455,
      "learning_rate": 0.00019930881530139054,
      "loss": 0.9896,
      "step": 1056
    },
    {
      "epoch": 0.11560756863174013,
      "grad_norm": 1.0558228492736816,
      "learning_rate": 0.00019930746886423725,
      "loss": 0.6931,
      "step": 1057
    },
    {
      "epoch": 0.11571694192278245,
      "grad_norm": 1.3015742301940918,
      "learning_rate": 0.00019930612112147765,
      "loss": 1.2273,
      "step": 1058
    },
    {
      "epoch": 0.11582631521382479,
      "grad_norm": 1.342544674873352,
      "learning_rate": 0.0001993047720731295,
      "loss": 0.8942,
      "step": 1059
    },
    {
      "epoch": 0.11593568850486712,
      "grad_norm": 1.1139742136001587,
      "learning_rate": 0.0001993034217192105,
      "loss": 0.7389,
      "step": 1060
    },
    {
      "epoch": 0.11604506179590944,
      "grad_norm": 1.322803020477295,
      "learning_rate": 0.00019930207005973842,
      "loss": 0.9694,
      "step": 1061
    },
    {
      "epoch": 0.11615443508695177,
      "grad_norm": 1.2623871564865112,
      "learning_rate": 0.00019930071709473103,
      "loss": 0.9898,
      "step": 1062
    },
    {
      "epoch": 0.11626380837799409,
      "grad_norm": 1.0599974393844604,
      "learning_rate": 0.00019929936282420615,
      "loss": 0.9961,
      "step": 1063
    },
    {
      "epoch": 0.11637318166903642,
      "grad_norm": 1.2263879776000977,
      "learning_rate": 0.0001992980072481815,
      "loss": 0.4677,
      "step": 1064
    },
    {
      "epoch": 0.11648255496007875,
      "grad_norm": 1.2485893964767456,
      "learning_rate": 0.000199296650366675,
      "loss": 1.1383,
      "step": 1065
    },
    {
      "epoch": 0.11659192825112108,
      "grad_norm": 1.6170319318771362,
      "learning_rate": 0.00019929529217970444,
      "loss": 0.9048,
      "step": 1066
    },
    {
      "epoch": 0.1167013015421634,
      "grad_norm": 0.994527280330658,
      "learning_rate": 0.00019929393268728766,
      "loss": 0.83,
      "step": 1067
    },
    {
      "epoch": 0.11681067483320573,
      "grad_norm": 1.3639914989471436,
      "learning_rate": 0.00019929257188944254,
      "loss": 0.7648,
      "step": 1068
    },
    {
      "epoch": 0.11692004812424805,
      "grad_norm": 1.3566858768463135,
      "learning_rate": 0.00019929120978618702,
      "loss": 1.5462,
      "step": 1069
    },
    {
      "epoch": 0.11702942141529038,
      "grad_norm": 1.0730218887329102,
      "learning_rate": 0.00019928984637753895,
      "loss": 0.9189,
      "step": 1070
    },
    {
      "epoch": 0.11713879470633272,
      "grad_norm": 1.2467161417007446,
      "learning_rate": 0.0001992884816635163,
      "loss": 0.8266,
      "step": 1071
    },
    {
      "epoch": 0.11724816799737504,
      "grad_norm": 1.2138983011245728,
      "learning_rate": 0.00019928711564413698,
      "loss": 0.9357,
      "step": 1072
    },
    {
      "epoch": 0.11735754128841737,
      "grad_norm": 0.8668559789657593,
      "learning_rate": 0.00019928574831941896,
      "loss": 1.117,
      "step": 1073
    },
    {
      "epoch": 0.1174669145794597,
      "grad_norm": 0.9239852428436279,
      "learning_rate": 0.00019928437968938018,
      "loss": 0.9012,
      "step": 1074
    },
    {
      "epoch": 0.11757628787050202,
      "grad_norm": 1.2964130640029907,
      "learning_rate": 0.00019928300975403872,
      "loss": 0.8682,
      "step": 1075
    },
    {
      "epoch": 0.11768566116154434,
      "grad_norm": 1.0370787382125854,
      "learning_rate": 0.00019928163851341252,
      "loss": 0.6719,
      "step": 1076
    },
    {
      "epoch": 0.11779503445258668,
      "grad_norm": 1.2623294591903687,
      "learning_rate": 0.0001992802659675196,
      "loss": 1.0522,
      "step": 1077
    },
    {
      "epoch": 0.11790440774362901,
      "grad_norm": 1.4693111181259155,
      "learning_rate": 0.00019927889211637806,
      "loss": 0.7086,
      "step": 1078
    },
    {
      "epoch": 0.11801378103467133,
      "grad_norm": 1.454908013343811,
      "learning_rate": 0.00019927751696000593,
      "loss": 0.8227,
      "step": 1079
    },
    {
      "epoch": 0.11812315432571366,
      "grad_norm": 1.383716106414795,
      "learning_rate": 0.0001992761404984213,
      "loss": 1.182,
      "step": 1080
    },
    {
      "epoch": 0.11823252761675598,
      "grad_norm": 1.179354190826416,
      "learning_rate": 0.00019927476273164224,
      "loss": 0.7411,
      "step": 1081
    },
    {
      "epoch": 0.11834190090779832,
      "grad_norm": 0.9849554300308228,
      "learning_rate": 0.00019927338365968692,
      "loss": 0.6861,
      "step": 1082
    },
    {
      "epoch": 0.11845127419884065,
      "grad_norm": 1.0321458578109741,
      "learning_rate": 0.0001992720032825734,
      "loss": 0.8398,
      "step": 1083
    },
    {
      "epoch": 0.11856064748988297,
      "grad_norm": 1.5221078395843506,
      "learning_rate": 0.00019927062160031986,
      "loss": 0.8207,
      "step": 1084
    },
    {
      "epoch": 0.1186700207809253,
      "grad_norm": 1.4993456602096558,
      "learning_rate": 0.0001992692386129445,
      "loss": 0.7561,
      "step": 1085
    },
    {
      "epoch": 0.11877939407196762,
      "grad_norm": 1.4102402925491333,
      "learning_rate": 0.0001992678543204654,
      "loss": 0.933,
      "step": 1086
    },
    {
      "epoch": 0.11888876736300995,
      "grad_norm": 1.0773838758468628,
      "learning_rate": 0.00019926646872290088,
      "loss": 0.7729,
      "step": 1087
    },
    {
      "epoch": 0.11899814065405229,
      "grad_norm": 1.2041819095611572,
      "learning_rate": 0.00019926508182026913,
      "loss": 0.8254,
      "step": 1088
    },
    {
      "epoch": 0.11910751394509461,
      "grad_norm": 1.418381929397583,
      "learning_rate": 0.00019926369361258832,
      "loss": 0.7871,
      "step": 1089
    },
    {
      "epoch": 0.11921688723613694,
      "grad_norm": 1.7194627523422241,
      "learning_rate": 0.00019926230409987675,
      "loss": 0.7651,
      "step": 1090
    },
    {
      "epoch": 0.11932626052717926,
      "grad_norm": 1.5855488777160645,
      "learning_rate": 0.00019926091328215266,
      "loss": 0.684,
      "step": 1091
    },
    {
      "epoch": 0.11943563381822159,
      "grad_norm": 1.3664424419403076,
      "learning_rate": 0.0001992595211594344,
      "loss": 0.6464,
      "step": 1092
    },
    {
      "epoch": 0.11954500710926391,
      "grad_norm": 1.0810177326202393,
      "learning_rate": 0.0001992581277317402,
      "loss": 0.8314,
      "step": 1093
    },
    {
      "epoch": 0.11965438040030625,
      "grad_norm": 1.5367647409439087,
      "learning_rate": 0.00019925673299908838,
      "loss": 0.8573,
      "step": 1094
    },
    {
      "epoch": 0.11976375369134858,
      "grad_norm": 1.0480715036392212,
      "learning_rate": 0.00019925533696149735,
      "loss": 0.9109,
      "step": 1095
    },
    {
      "epoch": 0.1198731269823909,
      "grad_norm": 1.2405263185501099,
      "learning_rate": 0.00019925393961898539,
      "loss": 0.6391,
      "step": 1096
    },
    {
      "epoch": 0.11998250027343323,
      "grad_norm": 1.4140928983688354,
      "learning_rate": 0.00019925254097157092,
      "loss": 0.7935,
      "step": 1097
    },
    {
      "epoch": 0.12009187356447555,
      "grad_norm": 1.4065182209014893,
      "learning_rate": 0.00019925114101927225,
      "loss": 0.7938,
      "step": 1098
    },
    {
      "epoch": 0.12020124685551788,
      "grad_norm": 1.0741873979568481,
      "learning_rate": 0.0001992497397621079,
      "loss": 0.7147,
      "step": 1099
    },
    {
      "epoch": 0.12031062014656022,
      "grad_norm": 1.3996561765670776,
      "learning_rate": 0.0001992483372000962,
      "loss": 0.9493,
      "step": 1100
    },
    {
      "epoch": 0.12041999343760254,
      "grad_norm": 1.484931468963623,
      "learning_rate": 0.0001992469333332556,
      "loss": 0.8729,
      "step": 1101
    },
    {
      "epoch": 0.12052936672864487,
      "grad_norm": 0.9832516312599182,
      "learning_rate": 0.00019924552816160464,
      "loss": 0.9246,
      "step": 1102
    },
    {
      "epoch": 0.12063874001968719,
      "grad_norm": 1.0356745719909668,
      "learning_rate": 0.0001992441216851617,
      "loss": 0.9765,
      "step": 1103
    },
    {
      "epoch": 0.12074811331072952,
      "grad_norm": 1.0596363544464111,
      "learning_rate": 0.00019924271390394532,
      "loss": 0.9123,
      "step": 1104
    },
    {
      "epoch": 0.12085748660177184,
      "grad_norm": 1.7950572967529297,
      "learning_rate": 0.000199241304817974,
      "loss": 0.8213,
      "step": 1105
    },
    {
      "epoch": 0.12096685989281418,
      "grad_norm": 0.9297881722450256,
      "learning_rate": 0.0001992398944272662,
      "loss": 1.1188,
      "step": 1106
    },
    {
      "epoch": 0.1210762331838565,
      "grad_norm": 1.061532735824585,
      "learning_rate": 0.00019923848273184058,
      "loss": 0.9044,
      "step": 1107
    },
    {
      "epoch": 0.12118560647489883,
      "grad_norm": 1.096557378768921,
      "learning_rate": 0.00019923706973171563,
      "loss": 0.846,
      "step": 1108
    },
    {
      "epoch": 0.12129497976594115,
      "grad_norm": 1.3972960710525513,
      "learning_rate": 0.00019923565542690993,
      "loss": 0.8833,
      "step": 1109
    },
    {
      "epoch": 0.12140435305698348,
      "grad_norm": 1.532752513885498,
      "learning_rate": 0.0001992342398174421,
      "loss": 0.7579,
      "step": 1110
    },
    {
      "epoch": 0.12151372634802582,
      "grad_norm": 1.148959994316101,
      "learning_rate": 0.0001992328229033307,
      "loss": 0.7295,
      "step": 1111
    },
    {
      "epoch": 0.12162309963906814,
      "grad_norm": 1.2855503559112549,
      "learning_rate": 0.0001992314046845944,
      "loss": 0.9969,
      "step": 1112
    },
    {
      "epoch": 0.12173247293011047,
      "grad_norm": 1.0899553298950195,
      "learning_rate": 0.00019922998516125185,
      "loss": 0.7102,
      "step": 1113
    },
    {
      "epoch": 0.1218418462211528,
      "grad_norm": 1.3407875299453735,
      "learning_rate": 0.0001992285643333217,
      "loss": 1.1831,
      "step": 1114
    },
    {
      "epoch": 0.12195121951219512,
      "grad_norm": 1.2431249618530273,
      "learning_rate": 0.0001992271422008226,
      "loss": 0.8133,
      "step": 1115
    },
    {
      "epoch": 0.12206059280323744,
      "grad_norm": 1.2989228963851929,
      "learning_rate": 0.0001992257187637733,
      "loss": 0.8056,
      "step": 1116
    },
    {
      "epoch": 0.12216996609427978,
      "grad_norm": 1.095529317855835,
      "learning_rate": 0.0001992242940221925,
      "loss": 0.6483,
      "step": 1117
    },
    {
      "epoch": 0.12227933938532211,
      "grad_norm": 1.3520126342773438,
      "learning_rate": 0.00019922286797609888,
      "loss": 0.9471,
      "step": 1118
    },
    {
      "epoch": 0.12238871267636443,
      "grad_norm": 1.8333226442337036,
      "learning_rate": 0.00019922144062551125,
      "loss": 0.7729,
      "step": 1119
    },
    {
      "epoch": 0.12249808596740676,
      "grad_norm": 1.2174628973007202,
      "learning_rate": 0.00019922001197044838,
      "loss": 0.4531,
      "step": 1120
    },
    {
      "epoch": 0.12260745925844908,
      "grad_norm": 1.4901436567306519,
      "learning_rate": 0.000199218582010929,
      "loss": 0.8785,
      "step": 1121
    },
    {
      "epoch": 0.12271683254949141,
      "grad_norm": 1.0166181325912476,
      "learning_rate": 0.00019921715074697194,
      "loss": 0.7703,
      "step": 1122
    },
    {
      "epoch": 0.12282620584053375,
      "grad_norm": 1.2441827058792114,
      "learning_rate": 0.00019921571817859603,
      "loss": 0.7874,
      "step": 1123
    },
    {
      "epoch": 0.12293557913157607,
      "grad_norm": 1.4978913068771362,
      "learning_rate": 0.00019921428430582006,
      "loss": 0.9589,
      "step": 1124
    },
    {
      "epoch": 0.1230449524226184,
      "grad_norm": 1.4298309087753296,
      "learning_rate": 0.00019921284912866293,
      "loss": 1.298,
      "step": 1125
    },
    {
      "epoch": 0.12315432571366072,
      "grad_norm": 1.5720001459121704,
      "learning_rate": 0.00019921141264714348,
      "loss": 0.8474,
      "step": 1126
    },
    {
      "epoch": 0.12326369900470305,
      "grad_norm": 1.0151737928390503,
      "learning_rate": 0.00019920997486128062,
      "loss": 0.7808,
      "step": 1127
    },
    {
      "epoch": 0.12337307229574537,
      "grad_norm": 1.2106924057006836,
      "learning_rate": 0.00019920853577109324,
      "loss": 0.79,
      "step": 1128
    },
    {
      "epoch": 0.12348244558678771,
      "grad_norm": 1.8042259216308594,
      "learning_rate": 0.00019920709537660022,
      "loss": 0.9876,
      "step": 1129
    },
    {
      "epoch": 0.12359181887783004,
      "grad_norm": 1.0035299062728882,
      "learning_rate": 0.00019920565367782057,
      "loss": 0.8032,
      "step": 1130
    },
    {
      "epoch": 0.12370119216887236,
      "grad_norm": 1.1379562616348267,
      "learning_rate": 0.00019920421067477323,
      "loss": 0.8979,
      "step": 1131
    },
    {
      "epoch": 0.12381056545991469,
      "grad_norm": 1.1526437997817993,
      "learning_rate": 0.0001992027663674771,
      "loss": 1.0357,
      "step": 1132
    },
    {
      "epoch": 0.12391993875095701,
      "grad_norm": 1.051604986190796,
      "learning_rate": 0.0001992013207559512,
      "loss": 1.0486,
      "step": 1133
    },
    {
      "epoch": 0.12402931204199934,
      "grad_norm": 1.2010759115219116,
      "learning_rate": 0.0001991998738402146,
      "loss": 0.9433,
      "step": 1134
    },
    {
      "epoch": 0.12413868533304168,
      "grad_norm": 1.3235198259353638,
      "learning_rate": 0.00019919842562028626,
      "loss": 0.7923,
      "step": 1135
    },
    {
      "epoch": 0.124248058624084,
      "grad_norm": 0.9957483410835266,
      "learning_rate": 0.00019919697609618525,
      "loss": 1.0645,
      "step": 1136
    },
    {
      "epoch": 0.12435743191512633,
      "grad_norm": 1.2724521160125732,
      "learning_rate": 0.0001991955252679306,
      "loss": 1.0377,
      "step": 1137
    },
    {
      "epoch": 0.12446680520616865,
      "grad_norm": 1.3119345903396606,
      "learning_rate": 0.00019919407313554138,
      "loss": 0.7862,
      "step": 1138
    },
    {
      "epoch": 0.12457617849721098,
      "grad_norm": 1.2742271423339844,
      "learning_rate": 0.00019919261969903671,
      "loss": 0.9688,
      "step": 1139
    },
    {
      "epoch": 0.12468555178825332,
      "grad_norm": 1.2832351922988892,
      "learning_rate": 0.0001991911649584357,
      "loss": 1.1382,
      "step": 1140
    },
    {
      "epoch": 0.12479492507929564,
      "grad_norm": 1.3655825853347778,
      "learning_rate": 0.00019918970891375746,
      "loss": 0.8288,
      "step": 1141
    },
    {
      "epoch": 0.12490429837033797,
      "grad_norm": 1.0857080221176147,
      "learning_rate": 0.00019918825156502114,
      "loss": 0.8168,
      "step": 1142
    },
    {
      "epoch": 0.1250136716613803,
      "grad_norm": 1.2224301099777222,
      "learning_rate": 0.00019918679291224586,
      "loss": 0.9368,
      "step": 1143
    },
    {
      "epoch": 0.12512304495242263,
      "grad_norm": 1.4159595966339111,
      "learning_rate": 0.0001991853329554509,
      "loss": 0.8871,
      "step": 1144
    },
    {
      "epoch": 0.12523241824346495,
      "grad_norm": 1.4155634641647339,
      "learning_rate": 0.00019918387169465533,
      "loss": 0.8518,
      "step": 1145
    },
    {
      "epoch": 0.12534179153450728,
      "grad_norm": 1.4374167919158936,
      "learning_rate": 0.00019918240912987842,
      "loss": 0.7717,
      "step": 1146
    },
    {
      "epoch": 0.1254511648255496,
      "grad_norm": 1.1448475122451782,
      "learning_rate": 0.0001991809452611394,
      "loss": 0.6022,
      "step": 1147
    },
    {
      "epoch": 0.12556053811659193,
      "grad_norm": 0.9821136593818665,
      "learning_rate": 0.00019917948008845753,
      "loss": 0.6242,
      "step": 1148
    },
    {
      "epoch": 0.12566991140763425,
      "grad_norm": 1.2750651836395264,
      "learning_rate": 0.00019917801361185204,
      "loss": 0.8082,
      "step": 1149
    },
    {
      "epoch": 0.12577928469867658,
      "grad_norm": 1.1319009065628052,
      "learning_rate": 0.00019917654583134225,
      "loss": 0.8886,
      "step": 1150
    },
    {
      "epoch": 0.1258886579897189,
      "grad_norm": 1.2455142736434937,
      "learning_rate": 0.0001991750767469474,
      "loss": 0.8096,
      "step": 1151
    },
    {
      "epoch": 0.12599803128076123,
      "grad_norm": 1.2706987857818604,
      "learning_rate": 0.00019917360635868684,
      "loss": 0.9701,
      "step": 1152
    },
    {
      "epoch": 0.12610740457180356,
      "grad_norm": 1.1013381481170654,
      "learning_rate": 0.0001991721346665799,
      "loss": 0.8405,
      "step": 1153
    },
    {
      "epoch": 0.12621677786284588,
      "grad_norm": 1.1269696950912476,
      "learning_rate": 0.00019917066167064596,
      "loss": 0.8827,
      "step": 1154
    },
    {
      "epoch": 0.12632615115388823,
      "grad_norm": 0.9169305562973022,
      "learning_rate": 0.00019916918737090432,
      "loss": 1.1303,
      "step": 1155
    },
    {
      "epoch": 0.12643552444493056,
      "grad_norm": 1.2457066774368286,
      "learning_rate": 0.00019916771176737438,
      "loss": 0.9553,
      "step": 1156
    },
    {
      "epoch": 0.12654489773597288,
      "grad_norm": 1.1359801292419434,
      "learning_rate": 0.00019916623486007558,
      "loss": 0.7936,
      "step": 1157
    },
    {
      "epoch": 0.1266542710270152,
      "grad_norm": 0.9293884038925171,
      "learning_rate": 0.0001991647566490273,
      "loss": 1.0059,
      "step": 1158
    },
    {
      "epoch": 0.12676364431805753,
      "grad_norm": 1.308838129043579,
      "learning_rate": 0.00019916327713424898,
      "loss": 0.7944,
      "step": 1159
    },
    {
      "epoch": 0.12687301760909986,
      "grad_norm": 1.5240777730941772,
      "learning_rate": 0.0001991617963157601,
      "loss": 0.9551,
      "step": 1160
    },
    {
      "epoch": 0.12698239090014218,
      "grad_norm": 1.5669020414352417,
      "learning_rate": 0.0001991603141935801,
      "loss": 0.9669,
      "step": 1161
    },
    {
      "epoch": 0.1270917641911845,
      "grad_norm": 1.2006747722625732,
      "learning_rate": 0.00019915883076772843,
      "loss": 0.8208,
      "step": 1162
    },
    {
      "epoch": 0.12720113748222683,
      "grad_norm": 1.2349430322647095,
      "learning_rate": 0.0001991573460382247,
      "loss": 0.8721,
      "step": 1163
    },
    {
      "epoch": 0.12731051077326916,
      "grad_norm": 1.797431230545044,
      "learning_rate": 0.00019915586000508832,
      "loss": 0.902,
      "step": 1164
    },
    {
      "epoch": 0.12741988406431148,
      "grad_norm": 1.2186940908432007,
      "learning_rate": 0.00019915437266833887,
      "loss": 0.7599,
      "step": 1165
    },
    {
      "epoch": 0.1275292573553538,
      "grad_norm": 1.0212209224700928,
      "learning_rate": 0.00019915288402799593,
      "loss": 0.6746,
      "step": 1166
    },
    {
      "epoch": 0.12763863064639616,
      "grad_norm": 1.100295066833496,
      "learning_rate": 0.000199151394084079,
      "loss": 0.5582,
      "step": 1167
    },
    {
      "epoch": 0.1277480039374385,
      "grad_norm": 1.4582090377807617,
      "learning_rate": 0.00019914990283660778,
      "loss": 0.6041,
      "step": 1168
    },
    {
      "epoch": 0.1278573772284808,
      "grad_norm": 1.051195740699768,
      "learning_rate": 0.00019914841028560176,
      "loss": 0.7052,
      "step": 1169
    },
    {
      "epoch": 0.12796675051952314,
      "grad_norm": 0.9294663071632385,
      "learning_rate": 0.00019914691643108063,
      "loss": 0.9169,
      "step": 1170
    },
    {
      "epoch": 0.12807612381056546,
      "grad_norm": 0.9807643890380859,
      "learning_rate": 0.000199145421273064,
      "loss": 0.9336,
      "step": 1171
    },
    {
      "epoch": 0.1281854971016078,
      "grad_norm": 0.9529501795768738,
      "learning_rate": 0.00019914392481157155,
      "loss": 1.1272,
      "step": 1172
    },
    {
      "epoch": 0.1282948703926501,
      "grad_norm": 1.2981410026550293,
      "learning_rate": 0.00019914242704662294,
      "loss": 0.712,
      "step": 1173
    },
    {
      "epoch": 0.12840424368369244,
      "grad_norm": 1.2535361051559448,
      "learning_rate": 0.00019914092797823787,
      "loss": 1.066,
      "step": 1174
    },
    {
      "epoch": 0.12851361697473476,
      "grad_norm": 1.397220492362976,
      "learning_rate": 0.00019913942760643605,
      "loss": 0.9287,
      "step": 1175
    },
    {
      "epoch": 0.1286229902657771,
      "grad_norm": 1.3122884035110474,
      "learning_rate": 0.0001991379259312372,
      "loss": 0.6698,
      "step": 1176
    },
    {
      "epoch": 0.1287323635568194,
      "grad_norm": 1.3286000490188599,
      "learning_rate": 0.00019913642295266105,
      "loss": 0.9913,
      "step": 1177
    },
    {
      "epoch": 0.12884173684786177,
      "grad_norm": 1.4312903881072998,
      "learning_rate": 0.0001991349186707274,
      "loss": 0.4617,
      "step": 1178
    },
    {
      "epoch": 0.1289511101389041,
      "grad_norm": 1.5219992399215698,
      "learning_rate": 0.00019913341308545594,
      "loss": 0.7244,
      "step": 1179
    },
    {
      "epoch": 0.12906048342994642,
      "grad_norm": 1.6054514646530151,
      "learning_rate": 0.00019913190619686656,
      "loss": 0.9323,
      "step": 1180
    },
    {
      "epoch": 0.12916985672098874,
      "grad_norm": 1.4119715690612793,
      "learning_rate": 0.00019913039800497904,
      "loss": 0.6748,
      "step": 1181
    },
    {
      "epoch": 0.12927923001203107,
      "grad_norm": 1.5069162845611572,
      "learning_rate": 0.00019912888850981322,
      "loss": 0.8644,
      "step": 1182
    },
    {
      "epoch": 0.1293886033030734,
      "grad_norm": 1.1927472352981567,
      "learning_rate": 0.0001991273777113889,
      "loss": 0.8217,
      "step": 1183
    },
    {
      "epoch": 0.12949797659411572,
      "grad_norm": 1.1643022298812866,
      "learning_rate": 0.00019912586560972593,
      "loss": 1.3568,
      "step": 1184
    },
    {
      "epoch": 0.12960734988515804,
      "grad_norm": 1.0532258749008179,
      "learning_rate": 0.00019912435220484432,
      "loss": 0.7766,
      "step": 1185
    },
    {
      "epoch": 0.12971672317620037,
      "grad_norm": 1.3390288352966309,
      "learning_rate": 0.00019912283749676382,
      "loss": 1.0758,
      "step": 1186
    },
    {
      "epoch": 0.1298260964672427,
      "grad_norm": 1.5281256437301636,
      "learning_rate": 0.00019912132148550442,
      "loss": 1.2493,
      "step": 1187
    },
    {
      "epoch": 0.12993546975828502,
      "grad_norm": 1.247615933418274,
      "learning_rate": 0.000199119804171086,
      "loss": 0.8196,
      "step": 1188
    },
    {
      "epoch": 0.13004484304932734,
      "grad_norm": 1.2227741479873657,
      "learning_rate": 0.00019911828555352858,
      "loss": 1.0889,
      "step": 1189
    },
    {
      "epoch": 0.1301542163403697,
      "grad_norm": 1.300849199295044,
      "learning_rate": 0.0001991167656328521,
      "loss": 0.6247,
      "step": 1190
    },
    {
      "epoch": 0.13026358963141202,
      "grad_norm": 1.6125165224075317,
      "learning_rate": 0.00019911524440907648,
      "loss": 0.7632,
      "step": 1191
    },
    {
      "epoch": 0.13037296292245434,
      "grad_norm": 1.1194360256195068,
      "learning_rate": 0.00019911372188222178,
      "loss": 0.8288,
      "step": 1192
    },
    {
      "epoch": 0.13048233621349667,
      "grad_norm": 1.2267982959747314,
      "learning_rate": 0.00019911219805230802,
      "loss": 0.7094,
      "step": 1193
    },
    {
      "epoch": 0.130591709504539,
      "grad_norm": 1.1485017538070679,
      "learning_rate": 0.0001991106729193552,
      "loss": 0.7989,
      "step": 1194
    },
    {
      "epoch": 0.13070108279558132,
      "grad_norm": 1.6542736291885376,
      "learning_rate": 0.00019910914648338341,
      "loss": 0.7139,
      "step": 1195
    },
    {
      "epoch": 0.13081045608662364,
      "grad_norm": 1.1246317625045776,
      "learning_rate": 0.0001991076187444127,
      "loss": 0.9496,
      "step": 1196
    },
    {
      "epoch": 0.13091982937766597,
      "grad_norm": 1.0850814580917358,
      "learning_rate": 0.00019910608970246315,
      "loss": 1.0239,
      "step": 1197
    },
    {
      "epoch": 0.1310292026687083,
      "grad_norm": 1.57297682762146,
      "learning_rate": 0.00019910455935755485,
      "loss": 0.7393,
      "step": 1198
    },
    {
      "epoch": 0.13113857595975062,
      "grad_norm": 1.0131975412368774,
      "learning_rate": 0.00019910302770970794,
      "loss": 0.7418,
      "step": 1199
    },
    {
      "epoch": 0.13124794925079294,
      "grad_norm": 1.0881329774856567,
      "learning_rate": 0.00019910149475894259,
      "loss": 0.866,
      "step": 1200
    },
    {
      "epoch": 0.13124794925079294,
      "eval_loss": 0.8312067985534668,
      "eval_runtime": 40.9154,
      "eval_samples_per_second": 17.988,
      "eval_steps_per_second": 4.497,
      "step": 1200
    },
    {
      "epoch": 0.1313573225418353,
      "grad_norm": 1.4450033903121948,
      "learning_rate": 0.00019909996050527888,
      "loss": 0.8049,
      "step": 1201
    },
    {
      "epoch": 0.13146669583287762,
      "grad_norm": 1.3853977918624878,
      "learning_rate": 0.00019909842494873702,
      "loss": 1.1377,
      "step": 1202
    },
    {
      "epoch": 0.13157606912391995,
      "grad_norm": 1.3726768493652344,
      "learning_rate": 0.00019909688808933718,
      "loss": 0.7274,
      "step": 1203
    },
    {
      "epoch": 0.13168544241496227,
      "grad_norm": 1.0252834558486938,
      "learning_rate": 0.00019909534992709963,
      "loss": 0.9952,
      "step": 1204
    },
    {
      "epoch": 0.1317948157060046,
      "grad_norm": 1.1816951036453247,
      "learning_rate": 0.00019909381046204452,
      "loss": 0.7428,
      "step": 1205
    },
    {
      "epoch": 0.13190418899704692,
      "grad_norm": 1.3335750102996826,
      "learning_rate": 0.0001990922696941921,
      "loss": 0.917,
      "step": 1206
    },
    {
      "epoch": 0.13201356228808925,
      "grad_norm": 1.2397119998931885,
      "learning_rate": 0.00019909072762356263,
      "loss": 0.8642,
      "step": 1207
    },
    {
      "epoch": 0.13212293557913157,
      "grad_norm": 1.4454095363616943,
      "learning_rate": 0.00019908918425017643,
      "loss": 0.7159,
      "step": 1208
    },
    {
      "epoch": 0.1322323088701739,
      "grad_norm": 1.0113486051559448,
      "learning_rate": 0.00019908763957405374,
      "loss": 0.5676,
      "step": 1209
    },
    {
      "epoch": 0.13234168216121622,
      "grad_norm": 1.2884767055511475,
      "learning_rate": 0.00019908609359521487,
      "loss": 0.7862,
      "step": 1210
    },
    {
      "epoch": 0.13245105545225855,
      "grad_norm": 1.352392315864563,
      "learning_rate": 0.00019908454631368017,
      "loss": 0.8751,
      "step": 1211
    },
    {
      "epoch": 0.13256042874330087,
      "grad_norm": 1.321605920791626,
      "learning_rate": 0.00019908299772946995,
      "loss": 0.8701,
      "step": 1212
    },
    {
      "epoch": 0.13266980203434323,
      "grad_norm": 1.563302993774414,
      "learning_rate": 0.0001990814478426046,
      "loss": 0.7621,
      "step": 1213
    },
    {
      "epoch": 0.13277917532538555,
      "grad_norm": 1.2672288417816162,
      "learning_rate": 0.0001990798966531045,
      "loss": 0.9917,
      "step": 1214
    },
    {
      "epoch": 0.13288854861642788,
      "grad_norm": 1.4309278726577759,
      "learning_rate": 0.00019907834416099004,
      "loss": 0.9358,
      "step": 1215
    },
    {
      "epoch": 0.1329979219074702,
      "grad_norm": 1.324981689453125,
      "learning_rate": 0.00019907679036628158,
      "loss": 1.0276,
      "step": 1216
    },
    {
      "epoch": 0.13310729519851253,
      "grad_norm": 1.6899940967559814,
      "learning_rate": 0.0001990752352689996,
      "loss": 1.0495,
      "step": 1217
    },
    {
      "epoch": 0.13321666848955485,
      "grad_norm": 1.40802800655365,
      "learning_rate": 0.00019907367886916455,
      "loss": 1.0022,
      "step": 1218
    },
    {
      "epoch": 0.13332604178059718,
      "grad_norm": 1.25163996219635,
      "learning_rate": 0.00019907212116679685,
      "loss": 0.781,
      "step": 1219
    },
    {
      "epoch": 0.1334354150716395,
      "grad_norm": 1.5142436027526855,
      "learning_rate": 0.000199070562161917,
      "loss": 0.8624,
      "step": 1220
    },
    {
      "epoch": 0.13354478836268183,
      "grad_norm": 1.7423028945922852,
      "learning_rate": 0.00019906900185454553,
      "loss": 1.1806,
      "step": 1221
    },
    {
      "epoch": 0.13365416165372415,
      "grad_norm": 1.3047839403152466,
      "learning_rate": 0.00019906744024470295,
      "loss": 1.0223,
      "step": 1222
    },
    {
      "epoch": 0.13376353494476648,
      "grad_norm": 1.2250339984893799,
      "learning_rate": 0.00019906587733240972,
      "loss": 0.9334,
      "step": 1223
    },
    {
      "epoch": 0.1338729082358088,
      "grad_norm": 1.6344289779663086,
      "learning_rate": 0.00019906431311768642,
      "loss": 0.8382,
      "step": 1224
    },
    {
      "epoch": 0.13398228152685115,
      "grad_norm": 1.3012244701385498,
      "learning_rate": 0.0001990627476005537,
      "loss": 0.7952,
      "step": 1225
    },
    {
      "epoch": 0.13409165481789348,
      "grad_norm": 1.321818470954895,
      "learning_rate": 0.000199061180781032,
      "loss": 1.0363,
      "step": 1226
    },
    {
      "epoch": 0.1342010281089358,
      "grad_norm": 1.1936602592468262,
      "learning_rate": 0.000199059612659142,
      "loss": 0.771,
      "step": 1227
    },
    {
      "epoch": 0.13431040139997813,
      "grad_norm": 1.7952005863189697,
      "learning_rate": 0.00019905804323490432,
      "loss": 0.8584,
      "step": 1228
    },
    {
      "epoch": 0.13441977469102045,
      "grad_norm": 1.147356629371643,
      "learning_rate": 0.00019905647250833956,
      "loss": 0.9632,
      "step": 1229
    },
    {
      "epoch": 0.13452914798206278,
      "grad_norm": 0.9150287508964539,
      "learning_rate": 0.0001990549004794684,
      "loss": 1.0553,
      "step": 1230
    },
    {
      "epoch": 0.1346385212731051,
      "grad_norm": 1.4733471870422363,
      "learning_rate": 0.00019905332714831149,
      "loss": 0.8838,
      "step": 1231
    },
    {
      "epoch": 0.13474789456414743,
      "grad_norm": 0.9057783484458923,
      "learning_rate": 0.00019905175251488954,
      "loss": 0.6519,
      "step": 1232
    },
    {
      "epoch": 0.13485726785518976,
      "grad_norm": 1.003832459449768,
      "learning_rate": 0.00019905017657922324,
      "loss": 0.8934,
      "step": 1233
    },
    {
      "epoch": 0.13496664114623208,
      "grad_norm": 1.4523720741271973,
      "learning_rate": 0.00019904859934133327,
      "loss": 0.7496,
      "step": 1234
    },
    {
      "epoch": 0.1350760144372744,
      "grad_norm": 1.5943773984909058,
      "learning_rate": 0.0001990470208012404,
      "loss": 0.81,
      "step": 1235
    },
    {
      "epoch": 0.13518538772831676,
      "grad_norm": 1.4647760391235352,
      "learning_rate": 0.0001990454409589654,
      "loss": 0.685,
      "step": 1236
    },
    {
      "epoch": 0.13529476101935908,
      "grad_norm": 1.0640710592269897,
      "learning_rate": 0.00019904385981452905,
      "loss": 1.0492,
      "step": 1237
    },
    {
      "epoch": 0.1354041343104014,
      "grad_norm": 1.2380677461624146,
      "learning_rate": 0.00019904227736795206,
      "loss": 0.6507,
      "step": 1238
    },
    {
      "epoch": 0.13551350760144373,
      "grad_norm": 1.4155107736587524,
      "learning_rate": 0.0001990406936192553,
      "loss": 0.8304,
      "step": 1239
    },
    {
      "epoch": 0.13562288089248606,
      "grad_norm": 1.4900351762771606,
      "learning_rate": 0.00019903910856845956,
      "loss": 0.8339,
      "step": 1240
    },
    {
      "epoch": 0.13573225418352838,
      "grad_norm": 1.5656943321228027,
      "learning_rate": 0.00019903752221558574,
      "loss": 0.8266,
      "step": 1241
    },
    {
      "epoch": 0.1358416274745707,
      "grad_norm": 1.0937628746032715,
      "learning_rate": 0.0001990359345606546,
      "loss": 1.0124,
      "step": 1242
    },
    {
      "epoch": 0.13595100076561303,
      "grad_norm": 1.2953020334243774,
      "learning_rate": 0.0001990343456036871,
      "loss": 0.8379,
      "step": 1243
    },
    {
      "epoch": 0.13606037405665536,
      "grad_norm": 1.5445834398269653,
      "learning_rate": 0.0001990327553447041,
      "loss": 0.8043,
      "step": 1244
    },
    {
      "epoch": 0.13616974734769768,
      "grad_norm": 1.6298121213912964,
      "learning_rate": 0.00019903116378372645,
      "loss": 0.8297,
      "step": 1245
    },
    {
      "epoch": 0.13627912063874,
      "grad_norm": 1.5033830404281616,
      "learning_rate": 0.00019902957092077518,
      "loss": 0.6852,
      "step": 1246
    },
    {
      "epoch": 0.13638849392978233,
      "grad_norm": 1.1886252164840698,
      "learning_rate": 0.00019902797675587115,
      "loss": 0.803,
      "step": 1247
    },
    {
      "epoch": 0.1364978672208247,
      "grad_norm": 1.216243863105774,
      "learning_rate": 0.00019902638128903535,
      "loss": 0.9977,
      "step": 1248
    },
    {
      "epoch": 0.136607240511867,
      "grad_norm": 1.4907606840133667,
      "learning_rate": 0.00019902478452028875,
      "loss": 0.8494,
      "step": 1249
    },
    {
      "epoch": 0.13671661380290934,
      "grad_norm": 1.387757658958435,
      "learning_rate": 0.00019902318644965234,
      "loss": 1.0733,
      "step": 1250
    },
    {
      "epoch": 0.13682598709395166,
      "grad_norm": 1.418609619140625,
      "learning_rate": 0.00019902158707714714,
      "loss": 0.8953,
      "step": 1251
    },
    {
      "epoch": 0.136935360384994,
      "grad_norm": 1.2187076807022095,
      "learning_rate": 0.00019901998640279418,
      "loss": 0.7233,
      "step": 1252
    },
    {
      "epoch": 0.1370447336760363,
      "grad_norm": 1.5095491409301758,
      "learning_rate": 0.0001990183844266145,
      "loss": 0.9251,
      "step": 1253
    },
    {
      "epoch": 0.13715410696707864,
      "grad_norm": 1.2181601524353027,
      "learning_rate": 0.00019901678114862917,
      "loss": 0.7486,
      "step": 1254
    },
    {
      "epoch": 0.13726348025812096,
      "grad_norm": 1.432478666305542,
      "learning_rate": 0.00019901517656885923,
      "loss": 1.0862,
      "step": 1255
    },
    {
      "epoch": 0.1373728535491633,
      "grad_norm": 1.0717029571533203,
      "learning_rate": 0.00019901357068732577,
      "loss": 0.6119,
      "step": 1256
    },
    {
      "epoch": 0.1374822268402056,
      "grad_norm": 1.1415666341781616,
      "learning_rate": 0.00019901196350404998,
      "loss": 0.7756,
      "step": 1257
    },
    {
      "epoch": 0.13759160013124794,
      "grad_norm": 1.0101507902145386,
      "learning_rate": 0.00019901035501905293,
      "loss": 0.9983,
      "step": 1258
    },
    {
      "epoch": 0.1377009734222903,
      "grad_norm": 1.7728488445281982,
      "learning_rate": 0.00019900874523235578,
      "loss": 0.9716,
      "step": 1259
    },
    {
      "epoch": 0.13781034671333262,
      "grad_norm": 1.482842206954956,
      "learning_rate": 0.00019900713414397968,
      "loss": 0.9112,
      "step": 1260
    },
    {
      "epoch": 0.13791972000437494,
      "grad_norm": 1.1647096872329712,
      "learning_rate": 0.00019900552175394586,
      "loss": 0.8918,
      "step": 1261
    },
    {
      "epoch": 0.13802909329541727,
      "grad_norm": 1.4008877277374268,
      "learning_rate": 0.00019900390806227547,
      "loss": 0.6757,
      "step": 1262
    },
    {
      "epoch": 0.1381384665864596,
      "grad_norm": 1.1786069869995117,
      "learning_rate": 0.00019900229306898975,
      "loss": 0.7931,
      "step": 1263
    },
    {
      "epoch": 0.13824783987750192,
      "grad_norm": 1.0978976488113403,
      "learning_rate": 0.00019900067677410988,
      "loss": 0.8839,
      "step": 1264
    },
    {
      "epoch": 0.13835721316854424,
      "grad_norm": 1.1017560958862305,
      "learning_rate": 0.0001989990591776572,
      "loss": 0.9369,
      "step": 1265
    },
    {
      "epoch": 0.13846658645958657,
      "grad_norm": 1.1316092014312744,
      "learning_rate": 0.00019899744027965292,
      "loss": 0.8511,
      "step": 1266
    },
    {
      "epoch": 0.1385759597506289,
      "grad_norm": 1.189332127571106,
      "learning_rate": 0.00019899582008011833,
      "loss": 0.8724,
      "step": 1267
    },
    {
      "epoch": 0.13868533304167122,
      "grad_norm": 1.3983025550842285,
      "learning_rate": 0.00019899419857907473,
      "loss": 0.6759,
      "step": 1268
    },
    {
      "epoch": 0.13879470633271354,
      "grad_norm": 0.9870102405548096,
      "learning_rate": 0.0001989925757765434,
      "loss": 0.7991,
      "step": 1269
    },
    {
      "epoch": 0.13890407962375587,
      "grad_norm": 1.3650133609771729,
      "learning_rate": 0.00019899095167254577,
      "loss": 1.065,
      "step": 1270
    },
    {
      "epoch": 0.13901345291479822,
      "grad_norm": 1.0879632234573364,
      "learning_rate": 0.00019898932626710313,
      "loss": 0.8213,
      "step": 1271
    },
    {
      "epoch": 0.13912282620584054,
      "grad_norm": 1.3493596315383911,
      "learning_rate": 0.00019898769956023683,
      "loss": 1.0474,
      "step": 1272
    },
    {
      "epoch": 0.13923219949688287,
      "grad_norm": 1.4854204654693604,
      "learning_rate": 0.00019898607155196833,
      "loss": 0.543,
      "step": 1273
    },
    {
      "epoch": 0.1393415727879252,
      "grad_norm": 1.355569839477539,
      "learning_rate": 0.00019898444224231897,
      "loss": 0.9195,
      "step": 1274
    },
    {
      "epoch": 0.13945094607896752,
      "grad_norm": 0.9457685947418213,
      "learning_rate": 0.00019898281163131017,
      "loss": 1.0232,
      "step": 1275
    },
    {
      "epoch": 0.13956031937000984,
      "grad_norm": 1.2054322957992554,
      "learning_rate": 0.00019898117971896338,
      "loss": 0.9148,
      "step": 1276
    },
    {
      "epoch": 0.13966969266105217,
      "grad_norm": 1.2978698015213013,
      "learning_rate": 0.00019897954650530011,
      "loss": 0.9338,
      "step": 1277
    },
    {
      "epoch": 0.1397790659520945,
      "grad_norm": 1.433168888092041,
      "learning_rate": 0.00019897791199034175,
      "loss": 0.8646,
      "step": 1278
    },
    {
      "epoch": 0.13988843924313682,
      "grad_norm": 1.4227919578552246,
      "learning_rate": 0.00019897627617410983,
      "loss": 0.7242,
      "step": 1279
    },
    {
      "epoch": 0.13999781253417914,
      "grad_norm": 1.235701322555542,
      "learning_rate": 0.00019897463905662585,
      "loss": 0.8947,
      "step": 1280
    },
    {
      "epoch": 0.14010718582522147,
      "grad_norm": 1.1992274522781372,
      "learning_rate": 0.00019897300063791132,
      "loss": 0.8932,
      "step": 1281
    },
    {
      "epoch": 0.1402165591162638,
      "grad_norm": 1.3948328495025635,
      "learning_rate": 0.00019897136091798781,
      "loss": 0.8331,
      "step": 1282
    },
    {
      "epoch": 0.14032593240730615,
      "grad_norm": 1.330905795097351,
      "learning_rate": 0.00019896971989687688,
      "loss": 0.8722,
      "step": 1283
    },
    {
      "epoch": 0.14043530569834847,
      "grad_norm": 1.051833987236023,
      "learning_rate": 0.00019896807757460003,
      "loss": 0.747,
      "step": 1284
    },
    {
      "epoch": 0.1405446789893908,
      "grad_norm": 1.7666586637496948,
      "learning_rate": 0.00019896643395117894,
      "loss": 0.7577,
      "step": 1285
    },
    {
      "epoch": 0.14065405228043312,
      "grad_norm": 1.2675107717514038,
      "learning_rate": 0.0001989647890266352,
      "loss": 0.7789,
      "step": 1286
    },
    {
      "epoch": 0.14076342557147545,
      "grad_norm": 1.593224287033081,
      "learning_rate": 0.00019896314280099038,
      "loss": 0.8443,
      "step": 1287
    },
    {
      "epoch": 0.14087279886251777,
      "grad_norm": 1.2290527820587158,
      "learning_rate": 0.0001989614952742662,
      "loss": 1.0003,
      "step": 1288
    },
    {
      "epoch": 0.1409821721535601,
      "grad_norm": 1.5133509635925293,
      "learning_rate": 0.00019895984644648426,
      "loss": 0.9221,
      "step": 1289
    },
    {
      "epoch": 0.14109154544460242,
      "grad_norm": 1.005330204963684,
      "learning_rate": 0.00019895819631766628,
      "loss": 0.8675,
      "step": 1290
    },
    {
      "epoch": 0.14120091873564475,
      "grad_norm": 1.7682890892028809,
      "learning_rate": 0.00019895654488783396,
      "loss": 0.815,
      "step": 1291
    },
    {
      "epoch": 0.14131029202668707,
      "grad_norm": 1.1472705602645874,
      "learning_rate": 0.00019895489215700896,
      "loss": 0.6013,
      "step": 1292
    },
    {
      "epoch": 0.1414196653177294,
      "grad_norm": 2.014301300048828,
      "learning_rate": 0.00019895323812521302,
      "loss": 0.6484,
      "step": 1293
    },
    {
      "epoch": 0.14152903860877175,
      "grad_norm": 1.667834758758545,
      "learning_rate": 0.00019895158279246796,
      "loss": 0.5929,
      "step": 1294
    },
    {
      "epoch": 0.14163841189981408,
      "grad_norm": 1.2010897397994995,
      "learning_rate": 0.00019894992615879543,
      "loss": 1.1385,
      "step": 1295
    },
    {
      "epoch": 0.1417477851908564,
      "grad_norm": 1.8050376176834106,
      "learning_rate": 0.00019894826822421728,
      "loss": 0.7875,
      "step": 1296
    },
    {
      "epoch": 0.14185715848189873,
      "grad_norm": 1.1445764303207397,
      "learning_rate": 0.0001989466089887553,
      "loss": 0.8346,
      "step": 1297
    },
    {
      "epoch": 0.14196653177294105,
      "grad_norm": 1.3288732767105103,
      "learning_rate": 0.00019894494845243128,
      "loss": 0.8347,
      "step": 1298
    },
    {
      "epoch": 0.14207590506398338,
      "grad_norm": 2.197702646255493,
      "learning_rate": 0.0001989432866152671,
      "loss": 0.8339,
      "step": 1299
    },
    {
      "epoch": 0.1421852783550257,
      "grad_norm": 1.3687258958816528,
      "learning_rate": 0.00019894162347728456,
      "loss": 0.8043,
      "step": 1300
    },
    {
      "epoch": 0.14229465164606803,
      "grad_norm": 1.918575406074524,
      "learning_rate": 0.00019893995903850554,
      "loss": 1.0886,
      "step": 1301
    },
    {
      "epoch": 0.14240402493711035,
      "grad_norm": 1.3542847633361816,
      "learning_rate": 0.0001989382932989519,
      "loss": 1.2997,
      "step": 1302
    },
    {
      "epoch": 0.14251339822815268,
      "grad_norm": 1.8041226863861084,
      "learning_rate": 0.00019893662625864562,
      "loss": 0.995,
      "step": 1303
    },
    {
      "epoch": 0.142622771519195,
      "grad_norm": 1.1469374895095825,
      "learning_rate": 0.00019893495791760852,
      "loss": 0.8043,
      "step": 1304
    },
    {
      "epoch": 0.14273214481023733,
      "grad_norm": 1.0283957719802856,
      "learning_rate": 0.0001989332882758626,
      "loss": 0.9582,
      "step": 1305
    },
    {
      "epoch": 0.14284151810127968,
      "grad_norm": 1.3918421268463135,
      "learning_rate": 0.00019893161733342975,
      "loss": 0.9409,
      "step": 1306
    },
    {
      "epoch": 0.142950891392322,
      "grad_norm": 1.1873068809509277,
      "learning_rate": 0.000198929945090332,
      "loss": 0.8272,
      "step": 1307
    },
    {
      "epoch": 0.14306026468336433,
      "grad_norm": 1.0391401052474976,
      "learning_rate": 0.0001989282715465913,
      "loss": 0.743,
      "step": 1308
    },
    {
      "epoch": 0.14316963797440665,
      "grad_norm": 0.9347202777862549,
      "learning_rate": 0.00019892659670222966,
      "loss": 0.9824,
      "step": 1309
    },
    {
      "epoch": 0.14327901126544898,
      "grad_norm": 1.2760140895843506,
      "learning_rate": 0.00019892492055726912,
      "loss": 0.7222,
      "step": 1310
    },
    {
      "epoch": 0.1433883845564913,
      "grad_norm": 1.3573187589645386,
      "learning_rate": 0.0001989232431117317,
      "loss": 0.9713,
      "step": 1311
    },
    {
      "epoch": 0.14349775784753363,
      "grad_norm": 1.5151350498199463,
      "learning_rate": 0.00019892156436563941,
      "loss": 0.8673,
      "step": 1312
    },
    {
      "epoch": 0.14360713113857596,
      "grad_norm": 1.1117901802062988,
      "learning_rate": 0.0001989198843190144,
      "loss": 0.9669,
      "step": 1313
    },
    {
      "epoch": 0.14371650442961828,
      "grad_norm": 1.1102594137191772,
      "learning_rate": 0.00019891820297187872,
      "loss": 0.8136,
      "step": 1314
    },
    {
      "epoch": 0.1438258777206606,
      "grad_norm": 1.0395758152008057,
      "learning_rate": 0.00019891652032425446,
      "loss": 0.7556,
      "step": 1315
    },
    {
      "epoch": 0.14393525101170293,
      "grad_norm": 1.0732916593551636,
      "learning_rate": 0.00019891483637616376,
      "loss": 0.9965,
      "step": 1316
    },
    {
      "epoch": 0.14404462430274528,
      "grad_norm": 1.6103031635284424,
      "learning_rate": 0.00019891315112762872,
      "loss": 0.8578,
      "step": 1317
    },
    {
      "epoch": 0.1441539975937876,
      "grad_norm": 1.5338727235794067,
      "learning_rate": 0.00019891146457867156,
      "loss": 0.8031,
      "step": 1318
    },
    {
      "epoch": 0.14426337088482993,
      "grad_norm": 1.0858309268951416,
      "learning_rate": 0.00019890977672931443,
      "loss": 0.8685,
      "step": 1319
    },
    {
      "epoch": 0.14437274417587226,
      "grad_norm": 1.1474350690841675,
      "learning_rate": 0.0001989080875795795,
      "loss": 0.922,
      "step": 1320
    },
    {
      "epoch": 0.14448211746691458,
      "grad_norm": 1.2947766780853271,
      "learning_rate": 0.000198906397129489,
      "loss": 0.8175,
      "step": 1321
    },
    {
      "epoch": 0.1445914907579569,
      "grad_norm": 1.7123373746871948,
      "learning_rate": 0.00019890470537906518,
      "loss": 0.9249,
      "step": 1322
    },
    {
      "epoch": 0.14470086404899923,
      "grad_norm": 1.4728519916534424,
      "learning_rate": 0.0001989030123283302,
      "loss": 0.701,
      "step": 1323
    },
    {
      "epoch": 0.14481023734004156,
      "grad_norm": 1.6449192762374878,
      "learning_rate": 0.0001989013179773064,
      "loss": 0.7727,
      "step": 1324
    },
    {
      "epoch": 0.14491961063108388,
      "grad_norm": 1.6379886865615845,
      "learning_rate": 0.000198899622326016,
      "loss": 0.9266,
      "step": 1325
    },
    {
      "epoch": 0.1450289839221262,
      "grad_norm": 1.3292016983032227,
      "learning_rate": 0.00019889792537448132,
      "loss": 0.9376,
      "step": 1326
    },
    {
      "epoch": 0.14513835721316853,
      "grad_norm": 1.370091199874878,
      "learning_rate": 0.00019889622712272468,
      "loss": 0.7698,
      "step": 1327
    },
    {
      "epoch": 0.14524773050421086,
      "grad_norm": 1.2836308479309082,
      "learning_rate": 0.00019889452757076837,
      "loss": 1.0549,
      "step": 1328
    },
    {
      "epoch": 0.1453571037952532,
      "grad_norm": 1.3008925914764404,
      "learning_rate": 0.00019889282671863479,
      "loss": 1.1469,
      "step": 1329
    },
    {
      "epoch": 0.14546647708629554,
      "grad_norm": 1.0805034637451172,
      "learning_rate": 0.00019889112456634626,
      "loss": 0.9019,
      "step": 1330
    },
    {
      "epoch": 0.14557585037733786,
      "grad_norm": 1.3450411558151245,
      "learning_rate": 0.00019888942111392512,
      "loss": 0.8756,
      "step": 1331
    },
    {
      "epoch": 0.1456852236683802,
      "grad_norm": 1.472870945930481,
      "learning_rate": 0.00019888771636139384,
      "loss": 1.1762,
      "step": 1332
    },
    {
      "epoch": 0.1457945969594225,
      "grad_norm": 1.6283928155899048,
      "learning_rate": 0.00019888601030877484,
      "loss": 0.7255,
      "step": 1333
    },
    {
      "epoch": 0.14590397025046484,
      "grad_norm": 1.1767903566360474,
      "learning_rate": 0.00019888430295609047,
      "loss": 0.8443,
      "step": 1334
    },
    {
      "epoch": 0.14601334354150716,
      "grad_norm": 1.3466321229934692,
      "learning_rate": 0.00019888259430336325,
      "loss": 1.0804,
      "step": 1335
    },
    {
      "epoch": 0.1461227168325495,
      "grad_norm": 0.9327676892280579,
      "learning_rate": 0.00019888088435061557,
      "loss": 1.0759,
      "step": 1336
    },
    {
      "epoch": 0.1462320901235918,
      "grad_norm": 1.3020119667053223,
      "learning_rate": 0.00019887917309787003,
      "loss": 0.9431,
      "step": 1337
    },
    {
      "epoch": 0.14634146341463414,
      "grad_norm": 1.3907805681228638,
      "learning_rate": 0.000198877460545149,
      "loss": 0.7569,
      "step": 1338
    },
    {
      "epoch": 0.14645083670567646,
      "grad_norm": 1.8734911680221558,
      "learning_rate": 0.00019887574669247507,
      "loss": 0.9455,
      "step": 1339
    },
    {
      "epoch": 0.1465602099967188,
      "grad_norm": 1.3019437789916992,
      "learning_rate": 0.0001988740315398707,
      "loss": 0.847,
      "step": 1340
    },
    {
      "epoch": 0.14666958328776114,
      "grad_norm": 1.0235811471939087,
      "learning_rate": 0.00019887231508735855,
      "loss": 0.7818,
      "step": 1341
    },
    {
      "epoch": 0.14677895657880347,
      "grad_norm": 1.4977604150772095,
      "learning_rate": 0.00019887059733496112,
      "loss": 0.8976,
      "step": 1342
    },
    {
      "epoch": 0.1468883298698458,
      "grad_norm": 1.5260249376296997,
      "learning_rate": 0.000198868878282701,
      "loss": 0.7457,
      "step": 1343
    },
    {
      "epoch": 0.14699770316088812,
      "grad_norm": 1.0140836238861084,
      "learning_rate": 0.00019886715793060079,
      "loss": 1.1424,
      "step": 1344
    },
    {
      "epoch": 0.14710707645193044,
      "grad_norm": 1.3300782442092896,
      "learning_rate": 0.00019886543627868308,
      "loss": 0.9799,
      "step": 1345
    },
    {
      "epoch": 0.14721644974297277,
      "grad_norm": 1.432807207107544,
      "learning_rate": 0.00019886371332697057,
      "loss": 0.6344,
      "step": 1346
    },
    {
      "epoch": 0.1473258230340151,
      "grad_norm": 1.6012585163116455,
      "learning_rate": 0.00019886198907548587,
      "loss": 0.862,
      "step": 1347
    },
    {
      "epoch": 0.14743519632505742,
      "grad_norm": 1.0878487825393677,
      "learning_rate": 0.00019886026352425163,
      "loss": 0.878,
      "step": 1348
    },
    {
      "epoch": 0.14754456961609974,
      "grad_norm": 1.2399684190750122,
      "learning_rate": 0.0001988585366732906,
      "loss": 1.0422,
      "step": 1349
    },
    {
      "epoch": 0.14765394290714207,
      "grad_norm": 1.8239383697509766,
      "learning_rate": 0.0001988568085226254,
      "loss": 0.8317,
      "step": 1350
    },
    {
      "epoch": 0.1477633161981844,
      "grad_norm": 1.4150322675704956,
      "learning_rate": 0.00019885507907227881,
      "loss": 0.7806,
      "step": 1351
    },
    {
      "epoch": 0.14787268948922674,
      "grad_norm": 1.182781457901001,
      "learning_rate": 0.00019885334832227356,
      "loss": 1.1287,
      "step": 1352
    },
    {
      "epoch": 0.14798206278026907,
      "grad_norm": 1.1663532257080078,
      "learning_rate": 0.00019885161627263237,
      "loss": 1.1032,
      "step": 1353
    },
    {
      "epoch": 0.1480914360713114,
      "grad_norm": 1.7171438932418823,
      "learning_rate": 0.00019884988292337807,
      "loss": 0.9727,
      "step": 1354
    },
    {
      "epoch": 0.14820080936235372,
      "grad_norm": 1.317341923713684,
      "learning_rate": 0.00019884814827453342,
      "loss": 0.688,
      "step": 1355
    },
    {
      "epoch": 0.14831018265339604,
      "grad_norm": 1.0706037282943726,
      "learning_rate": 0.0001988464123261212,
      "loss": 1.058,
      "step": 1356
    },
    {
      "epoch": 0.14841955594443837,
      "grad_norm": 1.1368889808654785,
      "learning_rate": 0.00019884467507816424,
      "loss": 0.6506,
      "step": 1357
    },
    {
      "epoch": 0.1485289292354807,
      "grad_norm": 1.3398265838623047,
      "learning_rate": 0.00019884293653068543,
      "loss": 0.775,
      "step": 1358
    },
    {
      "epoch": 0.14863830252652302,
      "grad_norm": 1.1798793077468872,
      "learning_rate": 0.00019884119668370754,
      "loss": 0.8756,
      "step": 1359
    },
    {
      "epoch": 0.14874767581756534,
      "grad_norm": 0.9610666036605835,
      "learning_rate": 0.00019883945553725353,
      "loss": 0.8017,
      "step": 1360
    },
    {
      "epoch": 0.14885704910860767,
      "grad_norm": 1.7703958749771118,
      "learning_rate": 0.00019883771309134627,
      "loss": 0.6973,
      "step": 1361
    },
    {
      "epoch": 0.14896642239965,
      "grad_norm": 1.5369101762771606,
      "learning_rate": 0.00019883596934600862,
      "loss": 0.7437,
      "step": 1362
    },
    {
      "epoch": 0.14907579569069232,
      "grad_norm": 1.0070579051971436,
      "learning_rate": 0.00019883422430126354,
      "loss": 0.7783,
      "step": 1363
    },
    {
      "epoch": 0.14918516898173467,
      "grad_norm": 2.0147452354431152,
      "learning_rate": 0.000198832477957134,
      "loss": 0.6302,
      "step": 1364
    },
    {
      "epoch": 0.149294542272777,
      "grad_norm": 1.3789225816726685,
      "learning_rate": 0.00019883073031364289,
      "loss": 0.7851,
      "step": 1365
    },
    {
      "epoch": 0.14940391556381932,
      "grad_norm": 1.3498444557189941,
      "learning_rate": 0.00019882898137081324,
      "loss": 1.0645,
      "step": 1366
    },
    {
      "epoch": 0.14951328885486165,
      "grad_norm": 1.3234645128250122,
      "learning_rate": 0.00019882723112866807,
      "loss": 0.6351,
      "step": 1367
    },
    {
      "epoch": 0.14962266214590397,
      "grad_norm": 1.5828369855880737,
      "learning_rate": 0.0001988254795872303,
      "loss": 1.0627,
      "step": 1368
    },
    {
      "epoch": 0.1497320354369463,
      "grad_norm": 1.729599952697754,
      "learning_rate": 0.00019882372674652303,
      "loss": 0.9174,
      "step": 1369
    },
    {
      "epoch": 0.14984140872798862,
      "grad_norm": 1.4323097467422485,
      "learning_rate": 0.0001988219726065693,
      "loss": 0.8694,
      "step": 1370
    },
    {
      "epoch": 0.14995078201903095,
      "grad_norm": 1.3311268091201782,
      "learning_rate": 0.0001988202171673921,
      "loss": 0.8819,
      "step": 1371
    },
    {
      "epoch": 0.15006015531007327,
      "grad_norm": 1.691634178161621,
      "learning_rate": 0.00019881846042901462,
      "loss": 0.9333,
      "step": 1372
    },
    {
      "epoch": 0.1501695286011156,
      "grad_norm": 1.2400075197219849,
      "learning_rate": 0.0001988167023914599,
      "loss": 0.8887,
      "step": 1373
    },
    {
      "epoch": 0.15027890189215792,
      "grad_norm": 1.1478346586227417,
      "learning_rate": 0.000198814943054751,
      "loss": 0.9972,
      "step": 1374
    },
    {
      "epoch": 0.15038827518320028,
      "grad_norm": 1.105053424835205,
      "learning_rate": 0.00019881318241891116,
      "loss": 0.8586,
      "step": 1375
    },
    {
      "epoch": 0.1504976484742426,
      "grad_norm": 1.6296879053115845,
      "learning_rate": 0.00019881142048396345,
      "loss": 1.1815,
      "step": 1376
    },
    {
      "epoch": 0.15060702176528493,
      "grad_norm": 1.3772250413894653,
      "learning_rate": 0.00019880965724993103,
      "loss": 1.1228,
      "step": 1377
    },
    {
      "epoch": 0.15071639505632725,
      "grad_norm": 1.5180319547653198,
      "learning_rate": 0.00019880789271683715,
      "loss": 0.8623,
      "step": 1378
    },
    {
      "epoch": 0.15082576834736958,
      "grad_norm": 1.5298681259155273,
      "learning_rate": 0.00019880612688470494,
      "loss": 0.5956,
      "step": 1379
    },
    {
      "epoch": 0.1509351416384119,
      "grad_norm": 1.423857569694519,
      "learning_rate": 0.00019880435975355764,
      "loss": 0.9896,
      "step": 1380
    },
    {
      "epoch": 0.15104451492945423,
      "grad_norm": 1.3312628269195557,
      "learning_rate": 0.00019880259132341852,
      "loss": 0.6942,
      "step": 1381
    },
    {
      "epoch": 0.15115388822049655,
      "grad_norm": 1.1663191318511963,
      "learning_rate": 0.00019880082159431074,
      "loss": 0.9578,
      "step": 1382
    },
    {
      "epoch": 0.15126326151153888,
      "grad_norm": 1.145989179611206,
      "learning_rate": 0.00019879905056625766,
      "loss": 0.7223,
      "step": 1383
    },
    {
      "epoch": 0.1513726348025812,
      "grad_norm": 0.8383100032806396,
      "learning_rate": 0.00019879727823928249,
      "loss": 0.963,
      "step": 1384
    },
    {
      "epoch": 0.15148200809362353,
      "grad_norm": 1.585050106048584,
      "learning_rate": 0.00019879550461340858,
      "loss": 0.5838,
      "step": 1385
    },
    {
      "epoch": 0.15159138138466585,
      "grad_norm": 1.1837832927703857,
      "learning_rate": 0.00019879372968865925,
      "loss": 1.0345,
      "step": 1386
    },
    {
      "epoch": 0.1517007546757082,
      "grad_norm": 1.171630620956421,
      "learning_rate": 0.00019879195346505778,
      "loss": 0.8856,
      "step": 1387
    },
    {
      "epoch": 0.15181012796675053,
      "grad_norm": 1.2677950859069824,
      "learning_rate": 0.0001987901759426276,
      "loss": 1.1283,
      "step": 1388
    },
    {
      "epoch": 0.15191950125779285,
      "grad_norm": 0.9968597888946533,
      "learning_rate": 0.000198788397121392,
      "loss": 0.6675,
      "step": 1389
    },
    {
      "epoch": 0.15202887454883518,
      "grad_norm": 1.2447069883346558,
      "learning_rate": 0.00019878661700137445,
      "loss": 1.079,
      "step": 1390
    },
    {
      "epoch": 0.1521382478398775,
      "grad_norm": 1.5468206405639648,
      "learning_rate": 0.0001987848355825983,
      "loss": 0.7963,
      "step": 1391
    },
    {
      "epoch": 0.15224762113091983,
      "grad_norm": 1.3707401752471924,
      "learning_rate": 0.00019878305286508697,
      "loss": 0.5818,
      "step": 1392
    },
    {
      "epoch": 0.15235699442196216,
      "grad_norm": 1.3503425121307373,
      "learning_rate": 0.00019878126884886389,
      "loss": 0.8322,
      "step": 1393
    },
    {
      "epoch": 0.15246636771300448,
      "grad_norm": 2.1415793895721436,
      "learning_rate": 0.00019877948353395257,
      "loss": 0.7691,
      "step": 1394
    },
    {
      "epoch": 0.1525757410040468,
      "grad_norm": 1.3835546970367432,
      "learning_rate": 0.00019877769692037641,
      "loss": 0.955,
      "step": 1395
    },
    {
      "epoch": 0.15268511429508913,
      "grad_norm": 1.197978138923645,
      "learning_rate": 0.00019877590900815894,
      "loss": 0.84,
      "step": 1396
    },
    {
      "epoch": 0.15279448758613146,
      "grad_norm": 1.2404671907424927,
      "learning_rate": 0.00019877411979732368,
      "loss": 0.7603,
      "step": 1397
    },
    {
      "epoch": 0.15290386087717378,
      "grad_norm": 1.1336536407470703,
      "learning_rate": 0.0001987723292878941,
      "loss": 0.8828,
      "step": 1398
    },
    {
      "epoch": 0.15301323416821613,
      "grad_norm": 1.4907398223876953,
      "learning_rate": 0.00019877053747989379,
      "loss": 0.8101,
      "step": 1399
    },
    {
      "epoch": 0.15312260745925846,
      "grad_norm": 1.4589446783065796,
      "learning_rate": 0.00019876874437334627,
      "loss": 0.5207,
      "step": 1400
    },
    {
      "epoch": 0.15312260745925846,
      "eval_loss": 0.8338207006454468,
      "eval_runtime": 40.9401,
      "eval_samples_per_second": 17.977,
      "eval_steps_per_second": 4.494,
      "step": 1400
    }
  ],
  "logging_steps": 1,
  "max_steps": 27429,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 5
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1461719506917786e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}