{
  "best_metric": 0.3401404023170471,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.14380729822038468,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007190364911019234,
      "grad_norm": 0.6023048758506775,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.8203,
      "step": 1
    },
    {
      "epoch": 0.0007190364911019234,
      "eval_loss": 1.5364902019500732,
      "eval_runtime": 58.5395,
      "eval_samples_per_second": 40.007,
      "eval_steps_per_second": 20.004,
      "step": 1
    },
    {
      "epoch": 0.0014380729822038468,
      "grad_norm": 0.6873555183410645,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.9046,
      "step": 2
    },
    {
      "epoch": 0.0021571094733057704,
      "grad_norm": 0.742555558681488,
      "learning_rate": 1e-05,
      "loss": 1.709,
      "step": 3
    },
    {
      "epoch": 0.0028761459644076936,
      "grad_norm": 0.8109886050224304,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 2.233,
      "step": 4
    },
    {
      "epoch": 0.003595182455509617,
      "grad_norm": 0.6829097867012024,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.7143,
      "step": 5
    },
    {
      "epoch": 0.004314218946611541,
      "grad_norm": 0.7394075393676758,
      "learning_rate": 2e-05,
      "loss": 1.7139,
      "step": 6
    },
    {
      "epoch": 0.005033255437713464,
      "grad_norm": 0.8270502090454102,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 1.8787,
      "step": 7
    },
    {
      "epoch": 0.005752291928815387,
      "grad_norm": 0.6169760823249817,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 1.6642,
      "step": 8
    },
    {
      "epoch": 0.006471328419917311,
      "grad_norm": 0.6499037742614746,
      "learning_rate": 3e-05,
      "loss": 1.6552,
      "step": 9
    },
    {
      "epoch": 0.007190364911019234,
      "grad_norm": 0.6464849710464478,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.7106,
      "step": 10
    },
    {
      "epoch": 0.007909401402121157,
      "grad_norm": 0.5525938272476196,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 1.6372,
      "step": 11
    },
    {
      "epoch": 0.008628437893223082,
      "grad_norm": 0.44765809178352356,
      "learning_rate": 4e-05,
      "loss": 1.4306,
      "step": 12
    },
    {
      "epoch": 0.009347474384325004,
      "grad_norm": 0.4276944696903229,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 1.3624,
      "step": 13
    },
    {
      "epoch": 0.010066510875426928,
      "grad_norm": 0.4440835416316986,
      "learning_rate": 4.666666666666667e-05,
      "loss": 1.428,
      "step": 14
    },
    {
      "epoch": 0.010785547366528852,
      "grad_norm": 0.4091176986694336,
      "learning_rate": 5e-05,
      "loss": 1.3089,
      "step": 15
    },
    {
      "epoch": 0.011504583857630774,
      "grad_norm": 0.38626205921173096,
      "learning_rate": 5.333333333333333e-05,
      "loss": 1.2807,
      "step": 16
    },
    {
      "epoch": 0.012223620348732698,
      "grad_norm": 0.38527804613113403,
      "learning_rate": 5.666666666666667e-05,
      "loss": 1.334,
      "step": 17
    },
    {
      "epoch": 0.012942656839834622,
      "grad_norm": 0.3838706910610199,
      "learning_rate": 6e-05,
      "loss": 1.3725,
      "step": 18
    },
    {
      "epoch": 0.013661693330936545,
      "grad_norm": 0.3551206886768341,
      "learning_rate": 6.333333333333333e-05,
      "loss": 1.3084,
      "step": 19
    },
    {
      "epoch": 0.014380729822038469,
      "grad_norm": 0.35459205508232117,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.3165,
      "step": 20
    },
    {
      "epoch": 0.015099766313140393,
      "grad_norm": 0.3400305509567261,
      "learning_rate": 7e-05,
      "loss": 1.2457,
      "step": 21
    },
    {
      "epoch": 0.015818802804242315,
      "grad_norm": 0.3397105038166046,
      "learning_rate": 7.333333333333333e-05,
      "loss": 1.2202,
      "step": 22
    },
    {
      "epoch": 0.016537839295344237,
      "grad_norm": 0.35030993819236755,
      "learning_rate": 7.666666666666667e-05,
      "loss": 1.234,
      "step": 23
    },
    {
      "epoch": 0.017256875786446163,
      "grad_norm": 0.33557063341140747,
      "learning_rate": 8e-05,
      "loss": 1.1808,
      "step": 24
    },
    {
      "epoch": 0.017975912277548085,
      "grad_norm": 0.30998116731643677,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.1153,
      "step": 25
    },
    {
      "epoch": 0.018694948768650008,
      "grad_norm": 0.307394802570343,
      "learning_rate": 8.666666666666667e-05,
      "loss": 1.0866,
      "step": 26
    },
    {
      "epoch": 0.019413985259751933,
      "grad_norm": 0.3161311447620392,
      "learning_rate": 9e-05,
      "loss": 1.0822,
      "step": 27
    },
    {
      "epoch": 0.020133021750853856,
      "grad_norm": 0.3012605607509613,
      "learning_rate": 9.333333333333334e-05,
      "loss": 1.0352,
      "step": 28
    },
    {
      "epoch": 0.020852058241955778,
      "grad_norm": 0.3080648183822632,
      "learning_rate": 9.666666666666667e-05,
      "loss": 0.9947,
      "step": 29
    },
    {
      "epoch": 0.021571094733057704,
      "grad_norm": 0.30388250946998596,
      "learning_rate": 0.0001,
      "loss": 0.991,
      "step": 30
    },
    {
      "epoch": 0.022290131224159626,
      "grad_norm": 0.3022182881832123,
      "learning_rate": 9.999146252290264e-05,
      "loss": 0.9371,
      "step": 31
    },
    {
      "epoch": 0.02300916771526155,
      "grad_norm": 0.280342698097229,
      "learning_rate": 9.996585300715116e-05,
      "loss": 0.9211,
      "step": 32
    },
    {
      "epoch": 0.023728204206363474,
      "grad_norm": 0.30300894379615784,
      "learning_rate": 9.99231801983717e-05,
      "loss": 0.8932,
      "step": 33
    },
    {
      "epoch": 0.024447240697465396,
      "grad_norm": 0.27925336360931396,
      "learning_rate": 9.986345866928941e-05,
      "loss": 0.8711,
      "step": 34
    },
    {
      "epoch": 0.02516627718856732,
      "grad_norm": 0.2760774493217468,
      "learning_rate": 9.978670881475172e-05,
      "loss": 0.839,
      "step": 35
    },
    {
      "epoch": 0.025885313679669245,
      "grad_norm": 0.28717532753944397,
      "learning_rate": 9.96929568447637e-05,
      "loss": 0.8329,
      "step": 36
    },
    {
      "epoch": 0.026604350170771167,
      "grad_norm": 0.24982668459415436,
      "learning_rate": 9.958223477553714e-05,
      "loss": 0.7724,
      "step": 37
    },
    {
      "epoch": 0.02732338666187309,
      "grad_norm": 0.26853281259536743,
      "learning_rate": 9.94545804185573e-05,
      "loss": 0.7699,
      "step": 38
    },
    {
      "epoch": 0.028042423152975015,
      "grad_norm": 0.27748724818229675,
      "learning_rate": 9.931003736767013e-05,
      "loss": 0.7257,
      "step": 39
    },
    {
      "epoch": 0.028761459644076937,
      "grad_norm": 0.2774640917778015,
      "learning_rate": 9.91486549841951e-05,
      "loss": 0.7207,
      "step": 40
    },
    {
      "epoch": 0.02948049613517886,
      "grad_norm": 0.3005022704601288,
      "learning_rate": 9.89704883800683e-05,
      "loss": 0.6897,
      "step": 41
    },
    {
      "epoch": 0.030199532626280785,
      "grad_norm": 0.27618181705474854,
      "learning_rate": 9.877559839902184e-05,
      "loss": 0.6481,
      "step": 42
    },
    {
      "epoch": 0.030918569117382708,
      "grad_norm": 0.2797397971153259,
      "learning_rate": 9.85640515958057e-05,
      "loss": 0.6316,
      "step": 43
    },
    {
      "epoch": 0.03163760560848463,
      "grad_norm": 0.29535141587257385,
      "learning_rate": 9.833592021345937e-05,
      "loss": 0.6072,
      "step": 44
    },
    {
      "epoch": 0.03235664209958655,
      "grad_norm": 0.2769714295864105,
      "learning_rate": 9.809128215864097e-05,
      "loss": 0.5522,
      "step": 45
    },
    {
      "epoch": 0.033075678590688475,
      "grad_norm": 0.2524624466896057,
      "learning_rate": 9.783022097502204e-05,
      "loss": 0.5423,
      "step": 46
    },
    {
      "epoch": 0.033794715081790404,
      "grad_norm": 0.2533889412879944,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.5077,
      "step": 47
    },
    {
      "epoch": 0.034513751572892326,
      "grad_norm": 0.2663760483264923,
      "learning_rate": 9.725919140804099e-05,
      "loss": 0.4958,
      "step": 48
    },
    {
      "epoch": 0.03523278806399425,
      "grad_norm": 0.2982303500175476,
      "learning_rate": 9.694941803075283e-05,
      "loss": 0.48,
      "step": 49
    },
    {
      "epoch": 0.03595182455509617,
      "grad_norm": 0.3360510468482971,
      "learning_rate": 9.662361147021779e-05,
      "loss": 0.4886,
      "step": 50
    },
    {
      "epoch": 0.03595182455509617,
      "eval_loss": 0.543006181716919,
      "eval_runtime": 58.3426,
      "eval_samples_per_second": 40.142,
      "eval_steps_per_second": 20.071,
      "step": 50
    },
    {
      "epoch": 0.03667086104619809,
      "grad_norm": 0.4645315706729889,
      "learning_rate": 9.628188298907782e-05,
      "loss": 0.5215,
      "step": 51
    },
    {
      "epoch": 0.037389897537300015,
      "grad_norm": 0.4897192120552063,
      "learning_rate": 9.592434928729616e-05,
      "loss": 0.5516,
      "step": 52
    },
    {
      "epoch": 0.038108934028401945,
      "grad_norm": 0.8688023686408997,
      "learning_rate": 9.555113246230442e-05,
      "loss": 0.502,
      "step": 53
    },
    {
      "epoch": 0.03882797051950387,
      "grad_norm": 0.7859905362129211,
      "learning_rate": 9.516235996730645e-05,
      "loss": 0.5325,
      "step": 54
    },
    {
      "epoch": 0.03954700701060579,
      "grad_norm": 0.7686246633529663,
      "learning_rate": 9.475816456775313e-05,
      "loss": 0.6318,
      "step": 55
    },
    {
      "epoch": 0.04026604350170771,
      "grad_norm": 0.47948557138442993,
      "learning_rate": 9.43386842960031e-05,
      "loss": 0.6223,
      "step": 56
    },
    {
      "epoch": 0.040985079992809634,
      "grad_norm": 0.5028918385505676,
      "learning_rate": 9.39040624041849e-05,
      "loss": 0.548,
      "step": 57
    },
    {
      "epoch": 0.041704116483911556,
      "grad_norm": 0.530976414680481,
      "learning_rate": 9.345444731527642e-05,
      "loss": 0.5258,
      "step": 58
    },
    {
      "epoch": 0.042423152975013485,
      "grad_norm": 0.5062253475189209,
      "learning_rate": 9.298999257241863e-05,
      "loss": 0.5511,
      "step": 59
    },
    {
      "epoch": 0.04314218946611541,
      "grad_norm": 0.4118981659412384,
      "learning_rate": 9.251085678648072e-05,
      "loss": 0.5256,
      "step": 60
    },
    {
      "epoch": 0.04386122595721733,
      "grad_norm": 0.4127258360385895,
      "learning_rate": 9.201720358189464e-05,
      "loss": 0.461,
      "step": 61
    },
    {
      "epoch": 0.04458026244831925,
      "grad_norm": 0.6444300413131714,
      "learning_rate": 9.150920154077754e-05,
      "loss": 0.4467,
      "step": 62
    },
    {
      "epoch": 0.045299298939421175,
      "grad_norm": 0.5414140820503235,
      "learning_rate": 9.098702414536107e-05,
      "loss": 0.4442,
      "step": 63
    },
    {
      "epoch": 0.0460183354305231,
      "grad_norm": 0.27357229590415955,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.3968,
      "step": 64
    },
    {
      "epoch": 0.04673737192162502,
      "grad_norm": 0.25929877161979675,
      "learning_rate": 8.9900861364012e-05,
      "loss": 0.4143,
      "step": 65
    },
    {
      "epoch": 0.04745640841272695,
      "grad_norm": 0.27426910400390625,
      "learning_rate": 8.933724690167417e-05,
      "loss": 0.4045,
      "step": 66
    },
    {
      "epoch": 0.04817544490382887,
      "grad_norm": 0.32933494448661804,
      "learning_rate": 8.876019880555649e-05,
      "loss": 0.3966,
      "step": 67
    },
    {
      "epoch": 0.04889448139493079,
      "grad_norm": 0.2937968373298645,
      "learning_rate": 8.816991413705516e-05,
      "loss": 0.3956,
      "step": 68
    },
    {
      "epoch": 0.049613517886032715,
      "grad_norm": 0.3488810658454895,
      "learning_rate": 8.756659447784368e-05,
      "loss": 0.3861,
      "step": 69
    },
    {
      "epoch": 0.05033255437713464,
      "grad_norm": 0.23227158188819885,
      "learning_rate": 8.695044586103296e-05,
      "loss": 0.3739,
      "step": 70
    },
    {
      "epoch": 0.05105159086823656,
      "grad_norm": 0.21385645866394043,
      "learning_rate": 8.632167870081121e-05,
      "loss": 0.3851,
      "step": 71
    },
    {
      "epoch": 0.05177062735933849,
      "grad_norm": 0.27515462040901184,
      "learning_rate": 8.568050772058762e-05,
      "loss": 0.378,
      "step": 72
    },
    {
      "epoch": 0.05248966385044041,
      "grad_norm": 0.280422180891037,
      "learning_rate": 8.502715187966455e-05,
      "loss": 0.3699,
      "step": 73
    },
    {
      "epoch": 0.053208700341542334,
      "grad_norm": 0.25346243381500244,
      "learning_rate": 8.436183429846313e-05,
      "loss": 0.3905,
      "step": 74
    },
    {
      "epoch": 0.053927736832644256,
      "grad_norm": 0.26597610116004944,
      "learning_rate": 8.368478218232787e-05,
      "loss": 0.4217,
      "step": 75
    },
    {
      "epoch": 0.05464677332374618,
      "grad_norm": 0.23165351152420044,
      "learning_rate": 8.299622674393614e-05,
      "loss": 0.4055,
      "step": 76
    },
    {
      "epoch": 0.0553658098148481,
      "grad_norm": 0.23990345001220703,
      "learning_rate": 8.229640312433937e-05,
      "loss": 0.4223,
      "step": 77
    },
    {
      "epoch": 0.05608484630595003,
      "grad_norm": 0.19223831593990326,
      "learning_rate": 8.158555031266254e-05,
      "loss": 0.3819,
      "step": 78
    },
    {
      "epoch": 0.05680388279705195,
      "grad_norm": 0.17479577660560608,
      "learning_rate": 8.086391106448965e-05,
      "loss": 0.3974,
      "step": 79
    },
    {
      "epoch": 0.057522919288153875,
      "grad_norm": 0.20406880974769592,
      "learning_rate": 8.013173181896283e-05,
      "loss": 0.4011,
      "step": 80
    },
    {
      "epoch": 0.0582419557792558,
      "grad_norm": 0.2144848257303238,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.4025,
      "step": 81
    },
    {
      "epoch": 0.05896099227035772,
      "grad_norm": 0.2034243494272232,
      "learning_rate": 7.863675700402526e-05,
      "loss": 0.4417,
      "step": 82
    },
    {
      "epoch": 0.05968002876145964,
      "grad_norm": 0.20847761631011963,
      "learning_rate": 7.787447196714427e-05,
      "loss": 0.4451,
      "step": 83
    },
    {
      "epoch": 0.06039906525256157,
      "grad_norm": 0.15953093767166138,
      "learning_rate": 7.710266782362247e-05,
      "loss": 0.4236,
      "step": 84
    },
    {
      "epoch": 0.06111810174366349,
      "grad_norm": 0.178719624876976,
      "learning_rate": 7.63216081438678e-05,
      "loss": 0.4178,
      "step": 85
    },
    {
      "epoch": 0.061837138234765415,
      "grad_norm": 0.1618184745311737,
      "learning_rate": 7.553155965904535e-05,
      "loss": 0.3903,
      "step": 86
    },
    {
      "epoch": 0.06255617472586734,
      "grad_norm": 0.18507510423660278,
      "learning_rate": 7.473279216998895e-05,
      "loss": 0.3658,
      "step": 87
    },
    {
      "epoch": 0.06327521121696926,
      "grad_norm": 0.16280052065849304,
      "learning_rate": 7.392557845506432e-05,
      "loss": 0.3835,
      "step": 88
    },
    {
      "epoch": 0.06399424770807119,
      "grad_norm": 0.18812771141529083,
      "learning_rate": 7.311019417701566e-05,
      "loss": 0.3639,
      "step": 89
    },
    {
      "epoch": 0.0647132841991731,
      "grad_norm": 0.20103318989276886,
      "learning_rate": 7.228691778882693e-05,
      "loss": 0.3782,
      "step": 90
    },
    {
      "epoch": 0.06543232069027503,
      "grad_norm": 0.1834009438753128,
      "learning_rate": 7.145603043863045e-05,
      "loss": 0.3744,
      "step": 91
    },
    {
      "epoch": 0.06615135718137695,
      "grad_norm": 0.20019042491912842,
      "learning_rate": 7.061781587369519e-05,
      "loss": 0.3403,
      "step": 92
    },
    {
      "epoch": 0.06687039367247888,
      "grad_norm": 0.21144333481788635,
      "learning_rate": 6.977256034352712e-05,
      "loss": 0.3926,
      "step": 93
    },
    {
      "epoch": 0.06758943016358081,
      "grad_norm": 0.18462230265140533,
      "learning_rate": 6.892055250211552e-05,
      "loss": 0.3744,
      "step": 94
    },
    {
      "epoch": 0.06830846665468272,
      "grad_norm": 0.1614454835653305,
      "learning_rate": 6.806208330935766e-05,
      "loss": 0.3242,
      "step": 95
    },
    {
      "epoch": 0.06902750314578465,
      "grad_norm": 0.1568639725446701,
      "learning_rate": 6.719744593169641e-05,
      "loss": 0.3231,
      "step": 96
    },
    {
      "epoch": 0.06974653963688657,
      "grad_norm": 0.17419424653053284,
      "learning_rate": 6.632693564200416e-05,
      "loss": 0.3012,
      "step": 97
    },
    {
      "epoch": 0.0704655761279885,
      "grad_norm": 0.19043923914432526,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.2923,
      "step": 98
    },
    {
      "epoch": 0.07118461261909041,
      "grad_norm": 0.21909672021865845,
      "learning_rate": 6.456948734446624e-05,
      "loss": 0.3132,
      "step": 99
    },
    {
      "epoch": 0.07190364911019234,
      "grad_norm": 0.25625696778297424,
      "learning_rate": 6.368314950360415e-05,
      "loss": 0.3616,
      "step": 100
    },
    {
      "epoch": 0.07190364911019234,
      "eval_loss": 0.38074085116386414,
      "eval_runtime": 58.3498,
      "eval_samples_per_second": 40.137,
      "eval_steps_per_second": 20.069,
      "step": 100
    },
    {
      "epoch": 0.07262268560129427,
      "grad_norm": 0.33766958117485046,
      "learning_rate": 6.279213887972179e-05,
      "loss": 0.307,
      "step": 101
    },
    {
      "epoch": 0.07334172209239619,
      "grad_norm": 0.34318283200263977,
      "learning_rate": 6.189675975213094e-05,
      "loss": 0.4072,
      "step": 102
    },
    {
      "epoch": 0.07406075858349812,
      "grad_norm": 0.32589223980903625,
      "learning_rate": 6.099731789198344e-05,
      "loss": 0.4191,
      "step": 103
    },
    {
      "epoch": 0.07477979507460003,
      "grad_norm": 0.4203377664089203,
      "learning_rate": 6.009412045785051e-05,
      "loss": 0.3067,
      "step": 104
    },
    {
      "epoch": 0.07549883156570196,
      "grad_norm": 0.2928689122200012,
      "learning_rate": 5.918747589082853e-05,
      "loss": 0.4129,
      "step": 105
    },
    {
      "epoch": 0.07621786805680389,
      "grad_norm": 0.36445778608322144,
      "learning_rate": 5.82776938092065e-05,
      "loss": 0.4685,
      "step": 106
    },
    {
      "epoch": 0.0769369045479058,
      "grad_norm": 0.30332398414611816,
      "learning_rate": 5.736508490273188e-05,
      "loss": 0.447,
      "step": 107
    },
    {
      "epoch": 0.07765594103900773,
      "grad_norm": 0.345113605260849,
      "learning_rate": 5.644996082651017e-05,
      "loss": 0.437,
      "step": 108
    },
    {
      "epoch": 0.07837497753010965,
      "grad_norm": 0.48073431849479675,
      "learning_rate": 5.553263409457504e-05,
      "loss": 0.5559,
      "step": 109
    },
    {
      "epoch": 0.07909401402121158,
      "grad_norm": 0.36484697461128235,
      "learning_rate": 5.4613417973165106e-05,
      "loss": 0.3887,
      "step": 110
    },
    {
      "epoch": 0.0798130505123135,
      "grad_norm": 0.36127138137817383,
      "learning_rate": 5.3692626373743706e-05,
      "loss": 0.3855,
      "step": 111
    },
    {
      "epoch": 0.08053208700341542,
      "grad_norm": 0.4991846978664398,
      "learning_rate": 5.27705737457985e-05,
      "loss": 0.4507,
      "step": 112
    },
    {
      "epoch": 0.08125112349451735,
      "grad_norm": 0.3157109320163727,
      "learning_rate": 5.184757496945726e-05,
      "loss": 0.3359,
      "step": 113
    },
    {
      "epoch": 0.08197015998561927,
      "grad_norm": 0.27371692657470703,
      "learning_rate": 5.092394524795649e-05,
      "loss": 0.3133,
      "step": 114
    },
    {
      "epoch": 0.0826891964767212,
      "grad_norm": 0.2584126889705658,
      "learning_rate": 5e-05,
      "loss": 0.3422,
      "step": 115
    },
    {
      "epoch": 0.08340823296782311,
      "grad_norm": 0.25695544481277466,
      "learning_rate": 4.907605475204352e-05,
      "loss": 0.3427,
      "step": 116
    },
    {
      "epoch": 0.08412726945892504,
      "grad_norm": 0.2519172430038452,
      "learning_rate": 4.8152425030542766e-05,
      "loss": 0.3448,
      "step": 117
    },
    {
      "epoch": 0.08484630595002697,
      "grad_norm": 0.2275260090827942,
      "learning_rate": 4.72294262542015e-05,
      "loss": 0.3182,
      "step": 118
    },
    {
      "epoch": 0.08556534244112889,
      "grad_norm": 0.207272008061409,
      "learning_rate": 4.6307373626256306e-05,
      "loss": 0.3349,
      "step": 119
    },
    {
      "epoch": 0.08628437893223082,
      "grad_norm": 0.2518884241580963,
      "learning_rate": 4.5386582026834906e-05,
      "loss": 0.3105,
      "step": 120
    },
    {
      "epoch": 0.08700341542333273,
      "grad_norm": 0.24043984711170197,
      "learning_rate": 4.446736590542497e-05,
      "loss": 0.3513,
      "step": 121
    },
    {
      "epoch": 0.08772245191443466,
      "grad_norm": 0.2303398847579956,
      "learning_rate": 4.3550039173489845e-05,
      "loss": 0.3194,
      "step": 122
    },
    {
      "epoch": 0.08844148840553658,
      "grad_norm": 0.2184295505285263,
      "learning_rate": 4.2634915097268115e-05,
      "loss": 0.325,
      "step": 123
    },
    {
      "epoch": 0.0891605248966385,
      "grad_norm": 0.23223859071731567,
      "learning_rate": 4.1722306190793495e-05,
      "loss": 0.3429,
      "step": 124
    },
    {
      "epoch": 0.08987956138774043,
      "grad_norm": 0.20050419867038727,
      "learning_rate": 4.0812524109171476e-05,
      "loss": 0.3547,
      "step": 125
    },
    {
      "epoch": 0.09059859787884235,
      "grad_norm": 0.17888019979000092,
      "learning_rate": 3.99058795421495e-05,
      "loss": 0.3294,
      "step": 126
    },
    {
      "epoch": 0.09131763436994428,
      "grad_norm": 0.21177802979946136,
      "learning_rate": 3.9002682108016585e-05,
      "loss": 0.3581,
      "step": 127
    },
    {
      "epoch": 0.0920366708610462,
      "grad_norm": 0.21987402439117432,
      "learning_rate": 3.8103240247869075e-05,
      "loss": 0.3762,
      "step": 128
    },
    {
      "epoch": 0.09275570735214812,
      "grad_norm": 0.20270776748657227,
      "learning_rate": 3.720786112027822e-05,
      "loss": 0.3337,
      "step": 129
    },
    {
      "epoch": 0.09347474384325004,
      "grad_norm": 0.19828373193740845,
      "learning_rate": 3.631685049639586e-05,
      "loss": 0.3515,
      "step": 130
    },
    {
      "epoch": 0.09419378033435197,
      "grad_norm": 0.20338848233222961,
      "learning_rate": 3.543051265553377e-05,
      "loss": 0.3462,
      "step": 131
    },
    {
      "epoch": 0.0949128168254539,
      "grad_norm": 0.2387722134590149,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.393,
      "step": 132
    },
    {
      "epoch": 0.09563185331655581,
      "grad_norm": 0.1974070519208908,
      "learning_rate": 3.367306435799584e-05,
      "loss": 0.3852,
      "step": 133
    },
    {
      "epoch": 0.09635088980765774,
      "grad_norm": 0.15162739157676697,
      "learning_rate": 3.2802554068303596e-05,
      "loss": 0.3544,
      "step": 134
    },
    {
      "epoch": 0.09706992629875966,
      "grad_norm": 0.18993422389030457,
      "learning_rate": 3.1937916690642356e-05,
      "loss": 0.3877,
      "step": 135
    },
    {
      "epoch": 0.09778896278986159,
      "grad_norm": 0.2038678079843521,
      "learning_rate": 3.107944749788449e-05,
      "loss": 0.3657,
      "step": 136
    },
    {
      "epoch": 0.09850799928096352,
      "grad_norm": 0.18316876888275146,
      "learning_rate": 3.0227439656472877e-05,
      "loss": 0.3442,
      "step": 137
    },
    {
      "epoch": 0.09922703577206543,
      "grad_norm": 0.18696491420269012,
      "learning_rate": 2.9382184126304834e-05,
      "loss": 0.3674,
      "step": 138
    },
    {
      "epoch": 0.09994607226316736,
      "grad_norm": 0.15872074663639069,
      "learning_rate": 2.8543969561369556e-05,
      "loss": 0.3374,
      "step": 139
    },
    {
      "epoch": 0.10066510875426928,
      "grad_norm": 0.1745549738407135,
      "learning_rate": 2.771308221117309e-05,
      "loss": 0.3503,
      "step": 140
    },
    {
      "epoch": 0.1013841452453712,
      "grad_norm": 0.20435255765914917,
      "learning_rate": 2.688980582298435e-05,
      "loss": 0.3567,
      "step": 141
    },
    {
      "epoch": 0.10210318173647312,
      "grad_norm": 0.18533742427825928,
      "learning_rate": 2.607442154493568e-05,
      "loss": 0.3254,
      "step": 142
    },
    {
      "epoch": 0.10282221822757505,
      "grad_norm": 0.15743325650691986,
      "learning_rate": 2.5267207830011068e-05,
      "loss": 0.3218,
      "step": 143
    },
    {
      "epoch": 0.10354125471867698,
      "grad_norm": 0.15209344029426575,
      "learning_rate": 2.446844034095466e-05,
      "loss": 0.316,
      "step": 144
    },
    {
      "epoch": 0.1042602912097789,
      "grad_norm": 0.16973493993282318,
      "learning_rate": 2.3678391856132204e-05,
      "loss": 0.2995,
      "step": 145
    },
    {
      "epoch": 0.10497932770088082,
      "grad_norm": 0.17065779864788055,
      "learning_rate": 2.2897332176377528e-05,
      "loss": 0.2766,
      "step": 146
    },
    {
      "epoch": 0.10569836419198274,
      "grad_norm": 0.20378005504608154,
      "learning_rate": 2.2125528032855724e-05,
      "loss": 0.3278,
      "step": 147
    },
    {
      "epoch": 0.10641740068308467,
      "grad_norm": 0.17352186143398285,
      "learning_rate": 2.136324299597474e-05,
      "loss": 0.2776,
      "step": 148
    },
    {
      "epoch": 0.1071364371741866,
      "grad_norm": 0.19107244908809662,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.316,
      "step": 149
    },
    {
      "epoch": 0.10785547366528851,
      "grad_norm": 0.2604922950267792,
      "learning_rate": 1.9868268181037185e-05,
      "loss": 0.3095,
      "step": 150
    },
    {
      "epoch": 0.10785547366528851,
      "eval_loss": 0.34555259346961975,
      "eval_runtime": 58.8178,
      "eval_samples_per_second": 39.818,
      "eval_steps_per_second": 19.909,
      "step": 150
    },
    {
      "epoch": 0.10857451015639044,
      "grad_norm": 0.2277640551328659,
      "learning_rate": 1.9136088935510362e-05,
      "loss": 0.2502,
      "step": 151
    },
    {
      "epoch": 0.10929354664749236,
      "grad_norm": 0.2793837785720825,
      "learning_rate": 1.8414449687337464e-05,
      "loss": 0.2861,
      "step": 152
    },
    {
      "epoch": 0.11001258313859429,
      "grad_norm": 0.44137507677078247,
      "learning_rate": 1.7703596875660645e-05,
      "loss": 0.405,
      "step": 153
    },
    {
      "epoch": 0.1107316196296962,
      "grad_norm": 0.2606457769870758,
      "learning_rate": 1.700377325606388e-05,
      "loss": 0.2649,
      "step": 154
    },
    {
      "epoch": 0.11145065612079813,
      "grad_norm": 0.33907219767570496,
      "learning_rate": 1.631521781767214e-05,
      "loss": 0.403,
      "step": 155
    },
    {
      "epoch": 0.11216969261190006,
      "grad_norm": 0.28054168820381165,
      "learning_rate": 1.5638165701536868e-05,
      "loss": 0.3893,
      "step": 156
    },
    {
      "epoch": 0.11288872910300198,
      "grad_norm": 0.31116437911987305,
      "learning_rate": 1.4972848120335453e-05,
      "loss": 0.4007,
      "step": 157
    },
    {
      "epoch": 0.1136077655941039,
      "grad_norm": 0.28493228554725647,
      "learning_rate": 1.4319492279412388e-05,
      "loss": 0.3631,
      "step": 158
    },
    {
      "epoch": 0.11432680208520582,
      "grad_norm": 0.3235074281692505,
      "learning_rate": 1.3678321299188801e-05,
      "loss": 0.3939,
      "step": 159
    },
    {
      "epoch": 0.11504583857630775,
      "grad_norm": 0.30169492959976196,
      "learning_rate": 1.3049554138967051e-05,
      "loss": 0.329,
      "step": 160
    },
    {
      "epoch": 0.11576487506740966,
      "grad_norm": 0.9609299302101135,
      "learning_rate": 1.2433405522156332e-05,
      "loss": 0.5237,
      "step": 161
    },
    {
      "epoch": 0.1164839115585116,
      "grad_norm": 0.24112538993358612,
      "learning_rate": 1.183008586294485e-05,
      "loss": 0.3021,
      "step": 162
    },
    {
      "epoch": 0.11720294804961352,
      "grad_norm": 0.24137409031391144,
      "learning_rate": 1.1239801194443506e-05,
      "loss": 0.2978,
      "step": 163
    },
    {
      "epoch": 0.11792198454071544,
      "grad_norm": 0.28550300002098083,
      "learning_rate": 1.066275309832584e-05,
      "loss": 0.3217,
      "step": 164
    },
    {
      "epoch": 0.11864102103181737,
      "grad_norm": 0.29699841141700745,
      "learning_rate": 1.0099138635988026e-05,
      "loss": 0.2758,
      "step": 165
    },
    {
      "epoch": 0.11936005752291928,
      "grad_norm": 0.27138757705688477,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.2664,
      "step": 166
    },
    {
      "epoch": 0.12007909401402121,
      "grad_norm": 0.2857905626296997,
      "learning_rate": 9.012975854638949e-06,
      "loss": 0.3008,
      "step": 167
    },
    {
      "epoch": 0.12079813050512314,
      "grad_norm": 0.21144956350326538,
      "learning_rate": 8.490798459222476e-06,
      "loss": 0.2829,
      "step": 168
    },
    {
      "epoch": 0.12151716699622506,
      "grad_norm": 0.22459468245506287,
      "learning_rate": 7.982796418105371e-06,
      "loss": 0.2816,
      "step": 169
    },
    {
      "epoch": 0.12223620348732699,
      "grad_norm": 0.19300833344459534,
      "learning_rate": 7.489143213519301e-06,
      "loss": 0.3023,
      "step": 170
    },
    {
      "epoch": 0.1229552399784289,
      "grad_norm": 0.2020920366048813,
      "learning_rate": 7.010007427581378e-06,
      "loss": 0.319,
      "step": 171
    },
    {
      "epoch": 0.12367427646953083,
      "grad_norm": 0.20110531151294708,
      "learning_rate": 6.5455526847235825e-06,
      "loss": 0.32,
      "step": 172
    },
    {
      "epoch": 0.12439331296063275,
      "grad_norm": 0.17036013305187225,
      "learning_rate": 6.0959375958151045e-06,
      "loss": 0.3051,
      "step": 173
    },
    {
      "epoch": 0.1251123494517347,
      "grad_norm": 0.17303591966629028,
      "learning_rate": 5.6613157039969055e-06,
      "loss": 0.3138,
      "step": 174
    },
    {
      "epoch": 0.1258313859428366,
      "grad_norm": 0.19305406510829926,
      "learning_rate": 5.241835432246889e-06,
      "loss": 0.3315,
      "step": 175
    },
    {
      "epoch": 0.12655042243393852,
      "grad_norm": 0.19402852654457092,
      "learning_rate": 4.837640032693558e-06,
      "loss": 0.3325,
      "step": 176
    },
    {
      "epoch": 0.12726945892504044,
      "grad_norm": 0.19571861624717712,
      "learning_rate": 4.448867537695578e-06,
      "loss": 0.3536,
      "step": 177
    },
    {
      "epoch": 0.12798849541614238,
      "grad_norm": 0.17924807965755463,
      "learning_rate": 4.075650712703849e-06,
      "loss": 0.3514,
      "step": 178
    },
    {
      "epoch": 0.1287075319072443,
      "grad_norm": 0.1848725527524948,
      "learning_rate": 3.71811701092219e-06,
      "loss": 0.3485,
      "step": 179
    },
    {
      "epoch": 0.1294265683983462,
      "grad_norm": 0.1518690586090088,
      "learning_rate": 3.376388529782215e-06,
      "loss": 0.3308,
      "step": 180
    },
    {
      "epoch": 0.13014560488944815,
      "grad_norm": 0.19320723414421082,
      "learning_rate": 3.0505819692471792e-06,
      "loss": 0.3754,
      "step": 181
    },
    {
      "epoch": 0.13086464138055007,
      "grad_norm": 0.15887463092803955,
      "learning_rate": 2.7408085919590264e-06,
      "loss": 0.3554,
      "step": 182
    },
    {
      "epoch": 0.13158367787165198,
      "grad_norm": 0.19461137056350708,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.3837,
      "step": 183
    },
    {
      "epoch": 0.1323027143627539,
      "grad_norm": 0.20374387502670288,
      "learning_rate": 2.1697790249779636e-06,
      "loss": 0.3782,
      "step": 184
    },
    {
      "epoch": 0.13302175085385584,
      "grad_norm": 0.17451471090316772,
      "learning_rate": 1.908717841359048e-06,
      "loss": 0.3439,
      "step": 185
    },
    {
      "epoch": 0.13374078734495776,
      "grad_norm": 0.18102188408374786,
      "learning_rate": 1.6640797865406288e-06,
      "loss": 0.3599,
      "step": 186
    },
    {
      "epoch": 0.13445982383605967,
      "grad_norm": 0.19148917496204376,
      "learning_rate": 1.4359484041943038e-06,
      "loss": 0.3331,
      "step": 187
    },
    {
      "epoch": 0.13517886032716162,
      "grad_norm": 0.21265220642089844,
      "learning_rate": 1.2244016009781701e-06,
      "loss": 0.3481,
      "step": 188
    },
    {
      "epoch": 0.13589789681826353,
      "grad_norm": 0.21602880954742432,
      "learning_rate": 1.0295116199317057e-06,
      "loss": 0.3241,
      "step": 189
    },
    {
      "epoch": 0.13661693330936545,
      "grad_norm": 0.2161773294210434,
      "learning_rate": 8.513450158049108e-07,
      "loss": 0.3491,
      "step": 190
    },
    {
      "epoch": 0.13733596980046736,
      "grad_norm": 0.2377278059720993,
      "learning_rate": 6.899626323298713e-07,
      "loss": 0.3494,
      "step": 191
    },
    {
      "epoch": 0.1380550062915693,
      "grad_norm": 0.20273280143737793,
      "learning_rate": 5.454195814427021e-07,
      "loss": 0.3559,
      "step": 192
    },
    {
      "epoch": 0.13877404278267122,
      "grad_norm": 0.26119890809059143,
      "learning_rate": 4.177652244628627e-07,
      "loss": 0.3343,
      "step": 193
    },
    {
      "epoch": 0.13949307927377314,
      "grad_norm": 0.24087214469909668,
      "learning_rate": 3.0704315523631953e-07,
      "loss": 0.3304,
      "step": 194
    },
    {
      "epoch": 0.14021211576487508,
      "grad_norm": 0.23309563100337982,
      "learning_rate": 2.1329118524827662e-07,
      "loss": 0.3333,
      "step": 195
    },
    {
      "epoch": 0.140931152255977,
      "grad_norm": 0.20350925624370575,
      "learning_rate": 1.3654133071059893e-07,
      "loss": 0.2935,
      "step": 196
    },
    {
      "epoch": 0.1416501887470789,
      "grad_norm": 0.22840029001235962,
      "learning_rate": 7.681980162830282e-08,
      "loss": 0.299,
      "step": 197
    },
    {
      "epoch": 0.14236922523818082,
      "grad_norm": 0.24860765039920807,
      "learning_rate": 3.4146992848854695e-08,
      "loss": 0.2984,
      "step": 198
    },
    {
      "epoch": 0.14308826172928277,
      "grad_norm": 0.28271716833114624,
      "learning_rate": 8.537477097364522e-09,
      "loss": 0.2937,
      "step": 199
    },
    {
      "epoch": 0.14380729822038468,
      "grad_norm": 0.37126749753952026,
      "learning_rate": 0.0,
      "loss": 0.2713,
      "step": 200
    },
    {
      "epoch": 0.14380729822038468,
      "eval_loss": 0.3401404023170471,
      "eval_runtime": 58.8186,
      "eval_samples_per_second": 39.817,
      "eval_steps_per_second": 19.909,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6229883634057216.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}