{
  "best_metric": 1.5433133840560913,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.13855213023900242,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006927606511950121,
      "grad_norm": 2.047163486480713,
      "learning_rate": 1e-05,
      "loss": 1.4826,
      "step": 1
    },
    {
      "epoch": 0.0006927606511950121,
      "eval_loss": 2.2855608463287354,
      "eval_runtime": 182.7267,
      "eval_samples_per_second": 13.304,
      "eval_steps_per_second": 3.327,
      "step": 1
    },
    {
      "epoch": 0.0013855213023900243,
      "grad_norm": 2.08404278755188,
      "learning_rate": 2e-05,
      "loss": 1.9256,
      "step": 2
    },
    {
      "epoch": 0.0020782819535850364,
      "grad_norm": 1.8669313192367554,
      "learning_rate": 3e-05,
      "loss": 1.9484,
      "step": 3
    },
    {
      "epoch": 0.0027710426047800486,
      "grad_norm": 1.5075883865356445,
      "learning_rate": 4e-05,
      "loss": 2.0096,
      "step": 4
    },
    {
      "epoch": 0.0034638032559750607,
      "grad_norm": 0.9478077292442322,
      "learning_rate": 5e-05,
      "loss": 1.8187,
      "step": 5
    },
    {
      "epoch": 0.004156563907170073,
      "grad_norm": 1.1804261207580566,
      "learning_rate": 6e-05,
      "loss": 1.9365,
      "step": 6
    },
    {
      "epoch": 0.0048493245583650845,
      "grad_norm": 1.2288304567337036,
      "learning_rate": 7e-05,
      "loss": 1.7757,
      "step": 7
    },
    {
      "epoch": 0.005542085209560097,
      "grad_norm": 1.3752599954605103,
      "learning_rate": 8e-05,
      "loss": 1.8373,
      "step": 8
    },
    {
      "epoch": 0.006234845860755109,
      "grad_norm": 0.9812780022621155,
      "learning_rate": 9e-05,
      "loss": 1.6162,
      "step": 9
    },
    {
      "epoch": 0.006927606511950121,
      "grad_norm": 0.7303366661071777,
      "learning_rate": 0.0001,
      "loss": 1.7239,
      "step": 10
    },
    {
      "epoch": 0.007620367163145133,
      "grad_norm": 0.5897315740585327,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.4914,
      "step": 11
    },
    {
      "epoch": 0.008313127814340146,
      "grad_norm": 0.6309636235237122,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.5897,
      "step": 12
    },
    {
      "epoch": 0.009005888465535157,
      "grad_norm": 0.6942201256752014,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.704,
      "step": 13
    },
    {
      "epoch": 0.009698649116730169,
      "grad_norm": 0.7105118036270142,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.6951,
      "step": 14
    },
    {
      "epoch": 0.010391409767925183,
      "grad_norm": 0.7029067873954773,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.6272,
      "step": 15
    },
    {
      "epoch": 0.011084170419120194,
      "grad_norm": 0.7534646987915039,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.6326,
      "step": 16
    },
    {
      "epoch": 0.011776931070315206,
      "grad_norm": 0.7150416374206543,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.6515,
      "step": 17
    },
    {
      "epoch": 0.012469691721510218,
      "grad_norm": 0.8204565644264221,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.6801,
      "step": 18
    },
    {
      "epoch": 0.013162452372705231,
      "grad_norm": 0.7861640453338623,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.7708,
      "step": 19
    },
    {
      "epoch": 0.013855213023900243,
      "grad_norm": 0.711506187915802,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.594,
      "step": 20
    },
    {
      "epoch": 0.014547973675095255,
      "grad_norm": 0.7247769832611084,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.5334,
      "step": 21
    },
    {
      "epoch": 0.015240734326290266,
      "grad_norm": 0.7230167984962463,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.6162,
      "step": 22
    },
    {
      "epoch": 0.01593349497748528,
      "grad_norm": 0.8036465048789978,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.7543,
      "step": 23
    },
    {
      "epoch": 0.01662625562868029,
      "grad_norm": 0.8362630605697632,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.7448,
      "step": 24
    },
    {
      "epoch": 0.017319016279875303,
      "grad_norm": 0.8258106112480164,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.6961,
      "step": 25
    },
    {
      "epoch": 0.018011776931070315,
      "grad_norm": 0.851980984210968,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.77,
      "step": 26
    },
    {
      "epoch": 0.018704537582265326,
      "grad_norm": 0.840356707572937,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.6796,
      "step": 27
    },
    {
      "epoch": 0.019397298233460338,
      "grad_norm": 0.8998118042945862,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.6497,
      "step": 28
    },
    {
      "epoch": 0.02009005888465535,
      "grad_norm": 1.4215574264526367,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.9171,
      "step": 29
    },
    {
      "epoch": 0.020782819535850365,
      "grad_norm": 0.9744236469268799,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.7032,
      "step": 30
    },
    {
      "epoch": 0.021475580187045377,
      "grad_norm": 1.0084221363067627,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.7642,
      "step": 31
    },
    {
      "epoch": 0.02216834083824039,
      "grad_norm": 1.1500318050384521,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.8561,
      "step": 32
    },
    {
      "epoch": 0.0228611014894354,
      "grad_norm": 1.0929768085479736,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.7688,
      "step": 33
    },
    {
      "epoch": 0.023553862140630412,
      "grad_norm": 1.1748161315917969,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.7483,
      "step": 34
    },
    {
      "epoch": 0.024246622791825424,
      "grad_norm": 1.3313413858413696,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.7579,
      "step": 35
    },
    {
      "epoch": 0.024939383443020435,
      "grad_norm": 1.4813777208328247,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.0638,
      "step": 36
    },
    {
      "epoch": 0.025632144094215447,
      "grad_norm": 1.3699488639831543,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.6141,
      "step": 37
    },
    {
      "epoch": 0.026324904745410462,
      "grad_norm": 1.5125676393508911,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.7951,
      "step": 38
    },
    {
      "epoch": 0.027017665396605474,
      "grad_norm": 1.53731107711792,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.7671,
      "step": 39
    },
    {
      "epoch": 0.027710426047800486,
      "grad_norm": 1.7640604972839355,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.8081,
      "step": 40
    },
    {
      "epoch": 0.028403186698995497,
      "grad_norm": 1.6514116525650024,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.4547,
      "step": 41
    },
    {
      "epoch": 0.02909594735019051,
      "grad_norm": 2.2603237628936768,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.0858,
      "step": 42
    },
    {
      "epoch": 0.02978870800138552,
      "grad_norm": 2.523048162460327,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.9191,
      "step": 43
    },
    {
      "epoch": 0.030481468652580532,
      "grad_norm": 2.417120933532715,
      "learning_rate": 9.230476262104677e-05,
      "loss": 2.0561,
      "step": 44
    },
    {
      "epoch": 0.031174229303775544,
      "grad_norm": 2.2785043716430664,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.8882,
      "step": 45
    },
    {
      "epoch": 0.03186698995497056,
      "grad_norm": 2.2046115398406982,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.5272,
      "step": 46
    },
    {
      "epoch": 0.03255975060616557,
      "grad_norm": 2.597402572631836,
      "learning_rate": 9.093124073433463e-05,
      "loss": 2.0753,
      "step": 47
    },
    {
      "epoch": 0.03325251125736058,
      "grad_norm": 2.7070717811584473,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.6519,
      "step": 48
    },
    {
      "epoch": 0.03394527190855559,
      "grad_norm": 2.9477412700653076,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.4324,
      "step": 49
    },
    {
      "epoch": 0.034638032559750606,
      "grad_norm": 4.567273139953613,
      "learning_rate": 8.945702546981969e-05,
      "loss": 2.0015,
      "step": 50
    },
    {
      "epoch": 0.034638032559750606,
      "eval_loss": 1.8632498979568481,
      "eval_runtime": 184.5768,
      "eval_samples_per_second": 13.171,
      "eval_steps_per_second": 3.294,
      "step": 50
    },
    {
      "epoch": 0.03533079321094562,
      "grad_norm": 1.2950654029846191,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.5298,
      "step": 51
    },
    {
      "epoch": 0.03602355386214063,
      "grad_norm": 1.2909640073776245,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.6083,
      "step": 52
    },
    {
      "epoch": 0.036716314513335645,
      "grad_norm": 0.9368382692337036,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.7538,
      "step": 53
    },
    {
      "epoch": 0.03740907516453065,
      "grad_norm": 0.7290942668914795,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.6392,
      "step": 54
    },
    {
      "epoch": 0.03810183581572567,
      "grad_norm": 0.6426312327384949,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.7225,
      "step": 55
    },
    {
      "epoch": 0.038794596466920676,
      "grad_norm": 0.5837317705154419,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.6282,
      "step": 56
    },
    {
      "epoch": 0.03948735711811569,
      "grad_norm": 0.5810585618019104,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.5666,
      "step": 57
    },
    {
      "epoch": 0.0401801177693107,
      "grad_norm": 0.5959537625312805,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.5718,
      "step": 58
    },
    {
      "epoch": 0.040872878420505715,
      "grad_norm": 0.6295363306999207,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.5756,
      "step": 59
    },
    {
      "epoch": 0.04156563907170073,
      "grad_norm": 0.6176732182502747,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.5888,
      "step": 60
    },
    {
      "epoch": 0.04225839972289574,
      "grad_norm": 0.5834788084030151,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.5,
      "step": 61
    },
    {
      "epoch": 0.042951160374090754,
      "grad_norm": 0.6111202239990234,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.4321,
      "step": 62
    },
    {
      "epoch": 0.04364392102528576,
      "grad_norm": 0.6033303737640381,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.4581,
      "step": 63
    },
    {
      "epoch": 0.04433668167648078,
      "grad_norm": 0.6345365643501282,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.4483,
      "step": 64
    },
    {
      "epoch": 0.045029442327675785,
      "grad_norm": 0.6359748244285583,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.5392,
      "step": 65
    },
    {
      "epoch": 0.0457222029788708,
      "grad_norm": 0.63890540599823,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.5423,
      "step": 66
    },
    {
      "epoch": 0.046414963630065816,
      "grad_norm": 0.6280885934829712,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.5097,
      "step": 67
    },
    {
      "epoch": 0.047107724281260824,
      "grad_norm": 0.6749413013458252,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.53,
      "step": 68
    },
    {
      "epoch": 0.04780048493245584,
      "grad_norm": 0.672849714756012,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.6531,
      "step": 69
    },
    {
      "epoch": 0.04849324558365085,
      "grad_norm": 0.655882716178894,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.4457,
      "step": 70
    },
    {
      "epoch": 0.04918600623484586,
      "grad_norm": 0.7098842859268188,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.5776,
      "step": 71
    },
    {
      "epoch": 0.04987876688604087,
      "grad_norm": 0.7302150726318359,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.6309,
      "step": 72
    },
    {
      "epoch": 0.050571527537235886,
      "grad_norm": 0.7837209105491638,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.6634,
      "step": 73
    },
    {
      "epoch": 0.051264288188430894,
      "grad_norm": 0.7368186712265015,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.5211,
      "step": 74
    },
    {
      "epoch": 0.05195704883962591,
      "grad_norm": 0.7818071246147156,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.4992,
      "step": 75
    },
    {
      "epoch": 0.052649809490820924,
      "grad_norm": 0.7995255589485168,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.6081,
      "step": 76
    },
    {
      "epoch": 0.05334257014201593,
      "grad_norm": 0.8555031418800354,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.5777,
      "step": 77
    },
    {
      "epoch": 0.05403533079321095,
      "grad_norm": 0.8953914046287537,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.6073,
      "step": 78
    },
    {
      "epoch": 0.054728091444405956,
      "grad_norm": 0.9667080640792847,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.7662,
      "step": 79
    },
    {
      "epoch": 0.05542085209560097,
      "grad_norm": 0.9754164814949036,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.7188,
      "step": 80
    },
    {
      "epoch": 0.05611361274679598,
      "grad_norm": 1.0194123983383179,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.6131,
      "step": 81
    },
    {
      "epoch": 0.056806373397990995,
      "grad_norm": 1.0185964107513428,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.6057,
      "step": 82
    },
    {
      "epoch": 0.057499134049186,
      "grad_norm": 1.0227956771850586,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.7111,
      "step": 83
    },
    {
      "epoch": 0.05819189470038102,
      "grad_norm": 1.1718602180480957,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.6701,
      "step": 84
    },
    {
      "epoch": 0.05888465535157603,
      "grad_norm": 1.2311724424362183,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.7365,
      "step": 85
    },
    {
      "epoch": 0.05957741600277104,
      "grad_norm": 1.255084753036499,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.7453,
      "step": 86
    },
    {
      "epoch": 0.06027017665396606,
      "grad_norm": 1.4649220705032349,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.7197,
      "step": 87
    },
    {
      "epoch": 0.060962937305161065,
      "grad_norm": 1.3487746715545654,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.687,
      "step": 88
    },
    {
      "epoch": 0.06165569795635608,
      "grad_norm": 1.438979148864746,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.7361,
      "step": 89
    },
    {
      "epoch": 0.06234845860755109,
      "grad_norm": 1.5143617391586304,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.7665,
      "step": 90
    },
    {
      "epoch": 0.0630412192587461,
      "grad_norm": 1.5927358865737915,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.8169,
      "step": 91
    },
    {
      "epoch": 0.06373397990994112,
      "grad_norm": 1.537095069885254,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.4944,
      "step": 92
    },
    {
      "epoch": 0.06442674056113613,
      "grad_norm": 1.8598449230194092,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.5148,
      "step": 93
    },
    {
      "epoch": 0.06511950121233114,
      "grad_norm": 2.0445775985717773,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.701,
      "step": 94
    },
    {
      "epoch": 0.06581226186352615,
      "grad_norm": 2.032562732696533,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.6913,
      "step": 95
    },
    {
      "epoch": 0.06650502251472117,
      "grad_norm": 2.152479648590088,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.8405,
      "step": 96
    },
    {
      "epoch": 0.06719778316591618,
      "grad_norm": 2.379943370819092,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.6487,
      "step": 97
    },
    {
      "epoch": 0.06789054381711118,
      "grad_norm": 2.6310393810272217,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.8972,
      "step": 98
    },
    {
      "epoch": 0.0685833044683062,
      "grad_norm": 2.870434522628784,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.8055,
      "step": 99
    },
    {
      "epoch": 0.06927606511950121,
      "grad_norm": 4.0857086181640625,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.7904,
      "step": 100
    },
    {
      "epoch": 0.06927606511950121,
      "eval_loss": 1.6982988119125366,
      "eval_runtime": 184.5442,
      "eval_samples_per_second": 13.173,
      "eval_steps_per_second": 3.295,
      "step": 100
    },
    {
      "epoch": 0.06996882577069623,
      "grad_norm": 0.808838963508606,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.2906,
      "step": 101
    },
    {
      "epoch": 0.07066158642189124,
      "grad_norm": 0.8714607954025269,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.5006,
      "step": 102
    },
    {
      "epoch": 0.07135434707308624,
      "grad_norm": 0.7841171026229858,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.5611,
      "step": 103
    },
    {
      "epoch": 0.07204710772428126,
      "grad_norm": 0.6819593906402588,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.6411,
      "step": 104
    },
    {
      "epoch": 0.07273986837547627,
      "grad_norm": 0.5991967916488647,
      "learning_rate": 5e-05,
      "loss": 1.5971,
      "step": 105
    },
    {
      "epoch": 0.07343262902667129,
      "grad_norm": 0.6412804126739502,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.622,
      "step": 106
    },
    {
      "epoch": 0.07412538967786629,
      "grad_norm": 0.5765404105186462,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.6142,
      "step": 107
    },
    {
      "epoch": 0.0748181503290613,
      "grad_norm": 0.6134495139122009,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.6143,
      "step": 108
    },
    {
      "epoch": 0.07551091098025632,
      "grad_norm": 0.5833260416984558,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.4422,
      "step": 109
    },
    {
      "epoch": 0.07620367163145134,
      "grad_norm": 0.6028990745544434,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.4908,
      "step": 110
    },
    {
      "epoch": 0.07689643228264635,
      "grad_norm": 0.6026722192764282,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.5221,
      "step": 111
    },
    {
      "epoch": 0.07758919293384135,
      "grad_norm": 0.5972195267677307,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.4751,
      "step": 112
    },
    {
      "epoch": 0.07828195358503637,
      "grad_norm": 0.5974715948104858,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.5023,
      "step": 113
    },
    {
      "epoch": 0.07897471423623138,
      "grad_norm": 0.6070694923400879,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.4872,
      "step": 114
    },
    {
      "epoch": 0.0796674748874264,
      "grad_norm": 0.615339994430542,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.5426,
      "step": 115
    },
    {
      "epoch": 0.0803602355386214,
      "grad_norm": 0.5781705975532532,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.3618,
      "step": 116
    },
    {
      "epoch": 0.08105299618981641,
      "grad_norm": 0.6544880867004395,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.5149,
      "step": 117
    },
    {
      "epoch": 0.08174575684101143,
      "grad_norm": 0.657573938369751,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.5114,
      "step": 118
    },
    {
      "epoch": 0.08243851749220645,
      "grad_norm": 0.6392859220504761,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.5861,
      "step": 119
    },
    {
      "epoch": 0.08313127814340146,
      "grad_norm": 0.6606055498123169,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.5429,
      "step": 120
    },
    {
      "epoch": 0.08382403879459646,
      "grad_norm": 0.7363746166229248,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.7137,
      "step": 121
    },
    {
      "epoch": 0.08451679944579148,
      "grad_norm": 0.685859203338623,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.5803,
      "step": 122
    },
    {
      "epoch": 0.08520956009698649,
      "grad_norm": 0.745258629322052,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.5613,
      "step": 123
    },
    {
      "epoch": 0.08590232074818151,
      "grad_norm": 0.7659652233123779,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.6056,
      "step": 124
    },
    {
      "epoch": 0.08659508139937652,
      "grad_norm": 0.7633351683616638,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.7241,
      "step": 125
    },
    {
      "epoch": 0.08728784205057152,
      "grad_norm": 0.7845526337623596,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.4687,
      "step": 126
    },
    {
      "epoch": 0.08798060270176654,
      "grad_norm": 0.819581925868988,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.6291,
      "step": 127
    },
    {
      "epoch": 0.08867336335296155,
      "grad_norm": 0.8217785954475403,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.5233,
      "step": 128
    },
    {
      "epoch": 0.08936612400415657,
      "grad_norm": 0.8633366823196411,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.5922,
      "step": 129
    },
    {
      "epoch": 0.09005888465535157,
      "grad_norm": 0.8733365535736084,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.6332,
      "step": 130
    },
    {
      "epoch": 0.09075164530654659,
      "grad_norm": 0.9523481726646423,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.5584,
      "step": 131
    },
    {
      "epoch": 0.0914444059577416,
      "grad_norm": 1.0276700258255005,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.4192,
      "step": 132
    },
    {
      "epoch": 0.09213716660893662,
      "grad_norm": 1.0592403411865234,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.8051,
      "step": 133
    },
    {
      "epoch": 0.09282992726013163,
      "grad_norm": 1.0674453973770142,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.5308,
      "step": 134
    },
    {
      "epoch": 0.09352268791132663,
      "grad_norm": 1.1967990398406982,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.6214,
      "step": 135
    },
    {
      "epoch": 0.09421544856252165,
      "grad_norm": 1.3590198755264282,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.8485,
      "step": 136
    },
    {
      "epoch": 0.09490820921371666,
      "grad_norm": 1.393479585647583,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.5188,
      "step": 137
    },
    {
      "epoch": 0.09560096986491168,
      "grad_norm": 1.4235612154006958,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.579,
      "step": 138
    },
    {
      "epoch": 0.09629373051610668,
      "grad_norm": 1.5139780044555664,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.5479,
      "step": 139
    },
    {
      "epoch": 0.0969864911673017,
      "grad_norm": 1.5156546831130981,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.6592,
      "step": 140
    },
    {
      "epoch": 0.09767925181849671,
      "grad_norm": 1.5736416578292847,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.7471,
      "step": 141
    },
    {
      "epoch": 0.09837201246969172,
      "grad_norm": 1.863377332687378,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.6134,
      "step": 142
    },
    {
      "epoch": 0.09906477312088674,
      "grad_norm": 2.1274333000183105,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.8196,
      "step": 143
    },
    {
      "epoch": 0.09975753377208174,
      "grad_norm": 1.9414417743682861,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.7024,
      "step": 144
    },
    {
      "epoch": 0.10045029442327676,
      "grad_norm": 2.2269279956817627,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.7322,
      "step": 145
    },
    {
      "epoch": 0.10114305507447177,
      "grad_norm": 2.3395190238952637,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.749,
      "step": 146
    },
    {
      "epoch": 0.10183581572566679,
      "grad_norm": 2.3803727626800537,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.6153,
      "step": 147
    },
    {
      "epoch": 0.10252857637686179,
      "grad_norm": 2.970226287841797,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 2.0335,
      "step": 148
    },
    {
      "epoch": 0.1032213370280568,
      "grad_norm": 3.3703672885894775,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.8923,
      "step": 149
    },
    {
      "epoch": 0.10391409767925182,
      "grad_norm": 4.29112434387207,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.552,
      "step": 150
    },
    {
      "epoch": 0.10391409767925182,
      "eval_loss": 1.5660514831542969,
      "eval_runtime": 184.5174,
      "eval_samples_per_second": 13.175,
      "eval_steps_per_second": 3.295,
      "step": 150
    },
    {
      "epoch": 0.10460685833044683,
      "grad_norm": 0.4656112790107727,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.0941,
      "step": 151
    },
    {
      "epoch": 0.10529961898164185,
      "grad_norm": 0.5755825042724609,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.5797,
      "step": 152
    },
    {
      "epoch": 0.10599237963283685,
      "grad_norm": 0.6040727496147156,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.5418,
      "step": 153
    },
    {
      "epoch": 0.10668514028403187,
      "grad_norm": 0.6039297580718994,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.5792,
      "step": 154
    },
    {
      "epoch": 0.10737790093522688,
      "grad_norm": 0.5903182029724121,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.5083,
      "step": 155
    },
    {
      "epoch": 0.1080706615864219,
      "grad_norm": 0.5798469185829163,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.5602,
      "step": 156
    },
    {
      "epoch": 0.1087634222376169,
      "grad_norm": 0.5550411939620972,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.4344,
      "step": 157
    },
    {
      "epoch": 0.10945618288881191,
      "grad_norm": 0.5716089606285095,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.5428,
      "step": 158
    },
    {
      "epoch": 0.11014894354000693,
      "grad_norm": 0.5546737313270569,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.4759,
      "step": 159
    },
    {
      "epoch": 0.11084170419120194,
      "grad_norm": 0.5612758994102478,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.3933,
      "step": 160
    },
    {
      "epoch": 0.11153446484239696,
      "grad_norm": 0.5763513445854187,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.5106,
      "step": 161
    },
    {
      "epoch": 0.11222722549359196,
      "grad_norm": 0.5759108066558838,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.396,
      "step": 162
    },
    {
      "epoch": 0.11291998614478697,
      "grad_norm": 0.6222297549247742,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.4479,
      "step": 163
    },
    {
      "epoch": 0.11361274679598199,
      "grad_norm": 0.5856943130493164,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.4318,
      "step": 164
    },
    {
      "epoch": 0.114305507447177,
      "grad_norm": 0.591346025466919,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.4285,
      "step": 165
    },
    {
      "epoch": 0.114998268098372,
      "grad_norm": 0.5905902981758118,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.4163,
      "step": 166
    },
    {
      "epoch": 0.11569102874956702,
      "grad_norm": 0.6204029321670532,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.4313,
      "step": 167
    },
    {
      "epoch": 0.11638378940076204,
      "grad_norm": 0.641972005367279,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.5093,
      "step": 168
    },
    {
      "epoch": 0.11707655005195705,
      "grad_norm": 0.6664228439331055,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.4805,
      "step": 169
    },
    {
      "epoch": 0.11776931070315207,
      "grad_norm": 0.6841524839401245,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.592,
      "step": 170
    },
    {
      "epoch": 0.11846207135434707,
      "grad_norm": 0.6664283275604248,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.4791,
      "step": 171
    },
    {
      "epoch": 0.11915483200554208,
      "grad_norm": 0.7538617849349976,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.5943,
      "step": 172
    },
    {
      "epoch": 0.1198475926567371,
      "grad_norm": 0.7325513362884521,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.5066,
      "step": 173
    },
    {
      "epoch": 0.12054035330793211,
      "grad_norm": 0.7289254069328308,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.5446,
      "step": 174
    },
    {
      "epoch": 0.12123311395912713,
      "grad_norm": 0.7824656963348389,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.5452,
      "step": 175
    },
    {
      "epoch": 0.12192587461032213,
      "grad_norm": 0.8466042280197144,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.6697,
      "step": 176
    },
    {
      "epoch": 0.12261863526151714,
      "grad_norm": 0.8427552580833435,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.6268,
      "step": 177
    },
    {
      "epoch": 0.12331139591271216,
      "grad_norm": 0.8988440036773682,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.5465,
      "step": 178
    },
    {
      "epoch": 0.12400415656390718,
      "grad_norm": 1.0656927824020386,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.5494,
      "step": 179
    },
    {
      "epoch": 0.12469691721510218,
      "grad_norm": 0.9276512861251831,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.4964,
      "step": 180
    },
    {
      "epoch": 0.1253896778662972,
      "grad_norm": 0.9992802739143372,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.6587,
      "step": 181
    },
    {
      "epoch": 0.1260824385174922,
      "grad_norm": 1.0021182298660278,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.5739,
      "step": 182
    },
    {
      "epoch": 0.1267751991686872,
      "grad_norm": 1.0378376245498657,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.5981,
      "step": 183
    },
    {
      "epoch": 0.12746795981988224,
      "grad_norm": 1.2840222120285034,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.8746,
      "step": 184
    },
    {
      "epoch": 0.12816072047107724,
      "grad_norm": 1.211229681968689,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.7252,
      "step": 185
    },
    {
      "epoch": 0.12885348112227227,
      "grad_norm": 1.2241302728652954,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.7186,
      "step": 186
    },
    {
      "epoch": 0.12954624177346727,
      "grad_norm": 1.329634428024292,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.7648,
      "step": 187
    },
    {
      "epoch": 0.13023900242466227,
      "grad_norm": 1.457235336303711,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.7809,
      "step": 188
    },
    {
      "epoch": 0.1309317630758573,
      "grad_norm": 1.6213152408599854,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.7624,
      "step": 189
    },
    {
      "epoch": 0.1316245237270523,
      "grad_norm": 1.6628527641296387,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.9083,
      "step": 190
    },
    {
      "epoch": 0.1323172843782473,
      "grad_norm": 1.6546683311462402,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.7032,
      "step": 191
    },
    {
      "epoch": 0.13301004502944233,
      "grad_norm": 1.7574177980422974,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.4686,
      "step": 192
    },
    {
      "epoch": 0.13370280568063733,
      "grad_norm": 1.917037010192871,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 1.7451,
      "step": 193
    },
    {
      "epoch": 0.13439556633183236,
      "grad_norm": 1.9023606777191162,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.6578,
      "step": 194
    },
    {
      "epoch": 0.13508832698302736,
      "grad_norm": 2.2865285873413086,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.6675,
      "step": 195
    },
    {
      "epoch": 0.13578108763422236,
      "grad_norm": 2.199190139770508,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.81,
      "step": 196
    },
    {
      "epoch": 0.1364738482854174,
      "grad_norm": 2.3805201053619385,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.6742,
      "step": 197
    },
    {
      "epoch": 0.1371666089366124,
      "grad_norm": 3.1633899211883545,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.8714,
      "step": 198
    },
    {
      "epoch": 0.13785936958780742,
      "grad_norm": 2.6520771980285645,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.8664,
      "step": 199
    },
    {
      "epoch": 0.13855213023900242,
      "grad_norm": 3.554774761199951,
      "learning_rate": 0.0,
      "loss": 1.8842,
      "step": 200
    },
    {
      "epoch": 0.13855213023900242,
      "eval_loss": 1.5433133840560913,
      "eval_runtime": 184.549,
      "eval_samples_per_second": 13.173,
      "eval_steps_per_second": 3.295,
      "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": 3.017027157491712e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}