{
  "best_metric": 1.4881032705307007,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.0161033837235049,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.051691861752451e-05,
      "grad_norm": 15.694011688232422,
      "learning_rate": 1e-05,
      "loss": 2.23,
      "step": 1
    },
    {
      "epoch": 8.051691861752451e-05,
      "eval_loss": 3.512342929840088,
      "eval_runtime": 1553.9839,
      "eval_samples_per_second": 13.461,
      "eval_steps_per_second": 3.366,
      "step": 1
    },
    {
      "epoch": 0.00016103383723504902,
      "grad_norm": 17.33702850341797,
      "learning_rate": 2e-05,
      "loss": 2.5065,
      "step": 2
    },
    {
      "epoch": 0.00024155075585257353,
      "grad_norm": 17.64397621154785,
      "learning_rate": 3e-05,
      "loss": 2.5815,
      "step": 3
    },
    {
      "epoch": 0.00032206767447009804,
      "grad_norm": 11.568385124206543,
      "learning_rate": 4e-05,
      "loss": 2.2006,
      "step": 4
    },
    {
      "epoch": 0.0004025845930876225,
      "grad_norm": 5.545162677764893,
      "learning_rate": 5e-05,
      "loss": 2.1846,
      "step": 5
    },
    {
      "epoch": 0.00048310151170514705,
      "grad_norm": 4.827724456787109,
      "learning_rate": 6e-05,
      "loss": 1.9824,
      "step": 6
    },
    {
      "epoch": 0.0005636184303226716,
      "grad_norm": 2.6311419010162354,
      "learning_rate": 7e-05,
      "loss": 2.0108,
      "step": 7
    },
    {
      "epoch": 0.0006441353489401961,
      "grad_norm": 2.659532308578491,
      "learning_rate": 8e-05,
      "loss": 2.0057,
      "step": 8
    },
    {
      "epoch": 0.0007246522675577206,
      "grad_norm": 1.7492154836654663,
      "learning_rate": 9e-05,
      "loss": 2.048,
      "step": 9
    },
    {
      "epoch": 0.000805169186175245,
      "grad_norm": 1.2077504396438599,
      "learning_rate": 0.0001,
      "loss": 1.8373,
      "step": 10
    },
    {
      "epoch": 0.0008856861047927696,
      "grad_norm": 1.0642375946044922,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.8222,
      "step": 11
    },
    {
      "epoch": 0.0009662030234102941,
      "grad_norm": 1.2671899795532227,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.8701,
      "step": 12
    },
    {
      "epoch": 0.0010467199420278186,
      "grad_norm": 0.8027169108390808,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.7772,
      "step": 13
    },
    {
      "epoch": 0.0011272368606453432,
      "grad_norm": 1.0432685613632202,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.72,
      "step": 14
    },
    {
      "epoch": 0.0012077537792628676,
      "grad_norm": 0.6952840685844421,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.6682,
      "step": 15
    },
    {
      "epoch": 0.0012882706978803921,
      "grad_norm": 0.939834475517273,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.7082,
      "step": 16
    },
    {
      "epoch": 0.0013687876164979165,
      "grad_norm": 0.5965157747268677,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.4408,
      "step": 17
    },
    {
      "epoch": 0.001449304535115441,
      "grad_norm": 0.8464444875717163,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.5831,
      "step": 18
    },
    {
      "epoch": 0.0015298214537329657,
      "grad_norm": 0.6520291566848755,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.598,
      "step": 19
    },
    {
      "epoch": 0.00161033837235049,
      "grad_norm": 0.6852399110794067,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.6095,
      "step": 20
    },
    {
      "epoch": 0.0016908552909680147,
      "grad_norm": 1.1227819919586182,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.692,
      "step": 21
    },
    {
      "epoch": 0.0017713722095855393,
      "grad_norm": 0.6330742835998535,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.4861,
      "step": 22
    },
    {
      "epoch": 0.0018518891282030636,
      "grad_norm": 0.6982694268226624,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.5463,
      "step": 23
    },
    {
      "epoch": 0.0019324060468205882,
      "grad_norm": 0.7267745137214661,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.5918,
      "step": 24
    },
    {
      "epoch": 0.0020129229654381126,
      "grad_norm": 0.8092511296272278,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.5714,
      "step": 25
    },
    {
      "epoch": 0.002093439884055637,
      "grad_norm": 0.6692335605621338,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.5636,
      "step": 26
    },
    {
      "epoch": 0.0021739568026731618,
      "grad_norm": 0.6988323330879211,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.5656,
      "step": 27
    },
    {
      "epoch": 0.0022544737212906864,
      "grad_norm": 0.6920161247253418,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.5276,
      "step": 28
    },
    {
      "epoch": 0.0023349906399082105,
      "grad_norm": 0.7586509585380554,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.4832,
      "step": 29
    },
    {
      "epoch": 0.002415507558525735,
      "grad_norm": 0.75624680519104,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.7347,
      "step": 30
    },
    {
      "epoch": 0.0024960244771432597,
      "grad_norm": 0.8674934506416321,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.469,
      "step": 31
    },
    {
      "epoch": 0.0025765413957607843,
      "grad_norm": 0.9146162271499634,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.3929,
      "step": 32
    },
    {
      "epoch": 0.002657058314378309,
      "grad_norm": 0.8667139410972595,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.6595,
      "step": 33
    },
    {
      "epoch": 0.002737575232995833,
      "grad_norm": 0.9289156198501587,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.468,
      "step": 34
    },
    {
      "epoch": 0.0028180921516133576,
      "grad_norm": 0.8652037978172302,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.6761,
      "step": 35
    },
    {
      "epoch": 0.002898609070230882,
      "grad_norm": 0.7662935853004456,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.4846,
      "step": 36
    },
    {
      "epoch": 0.002979125988848407,
      "grad_norm": 0.829105019569397,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.5524,
      "step": 37
    },
    {
      "epoch": 0.0030596429074659314,
      "grad_norm": 0.7352724075317383,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.3437,
      "step": 38
    },
    {
      "epoch": 0.003140159826083456,
      "grad_norm": 1.0383816957473755,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.5991,
      "step": 39
    },
    {
      "epoch": 0.00322067674470098,
      "grad_norm": 0.7830373644828796,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.5001,
      "step": 40
    },
    {
      "epoch": 0.0033011936633185047,
      "grad_norm": 1.0262047052383423,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.6893,
      "step": 41
    },
    {
      "epoch": 0.0033817105819360293,
      "grad_norm": 0.9097186326980591,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.5568,
      "step": 42
    },
    {
      "epoch": 0.003462227500553554,
      "grad_norm": 0.940087616443634,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.6516,
      "step": 43
    },
    {
      "epoch": 0.0035427444191710785,
      "grad_norm": 1.0287165641784668,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.8198,
      "step": 44
    },
    {
      "epoch": 0.0036232613377886027,
      "grad_norm": 1.0288898944854736,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.7021,
      "step": 45
    },
    {
      "epoch": 0.0037037782564061273,
      "grad_norm": 0.8909144401550293,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.284,
      "step": 46
    },
    {
      "epoch": 0.003784295175023652,
      "grad_norm": 1.2093318700790405,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.7116,
      "step": 47
    },
    {
      "epoch": 0.0038648120936411764,
      "grad_norm": 1.316892385482788,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.7716,
      "step": 48
    },
    {
      "epoch": 0.003945329012258701,
      "grad_norm": 1.7544459104537964,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.8157,
      "step": 49
    },
    {
      "epoch": 0.004025845930876225,
      "grad_norm": 1.5375967025756836,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.9209,
      "step": 50
    },
    {
      "epoch": 0.004025845930876225,
      "eval_loss": 1.635573148727417,
      "eval_runtime": 1564.134,
      "eval_samples_per_second": 13.374,
      "eval_steps_per_second": 3.344,
      "step": 50
    },
    {
      "epoch": 0.00410636284949375,
      "grad_norm": 0.8445530533790588,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.3096,
      "step": 51
    },
    {
      "epoch": 0.004186879768111274,
      "grad_norm": 0.7997322082519531,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.6707,
      "step": 52
    },
    {
      "epoch": 0.0042673966867287985,
      "grad_norm": 0.706866443157196,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.4309,
      "step": 53
    },
    {
      "epoch": 0.0043479136053463235,
      "grad_norm": 0.4168620705604553,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.4875,
      "step": 54
    },
    {
      "epoch": 0.004428430523963848,
      "grad_norm": 0.4258555769920349,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.4082,
      "step": 55
    },
    {
      "epoch": 0.004508947442581373,
      "grad_norm": 0.5967984199523926,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.4149,
      "step": 56
    },
    {
      "epoch": 0.004589464361198897,
      "grad_norm": 0.5998218655586243,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.5081,
      "step": 57
    },
    {
      "epoch": 0.004669981279816421,
      "grad_norm": 0.49025171995162964,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.4152,
      "step": 58
    },
    {
      "epoch": 0.004750498198433946,
      "grad_norm": 0.44819146394729614,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.3845,
      "step": 59
    },
    {
      "epoch": 0.00483101511705147,
      "grad_norm": 0.5317243933677673,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.4941,
      "step": 60
    },
    {
      "epoch": 0.004911532035668995,
      "grad_norm": 0.5236647129058838,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.3369,
      "step": 61
    },
    {
      "epoch": 0.004992048954286519,
      "grad_norm": 0.44179674983024597,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.393,
      "step": 62
    },
    {
      "epoch": 0.0050725658729040436,
      "grad_norm": 0.5650262236595154,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.41,
      "step": 63
    },
    {
      "epoch": 0.005153082791521569,
      "grad_norm": 0.5390046834945679,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.4469,
      "step": 64
    },
    {
      "epoch": 0.005233599710139093,
      "grad_norm": 0.5149980783462524,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.4273,
      "step": 65
    },
    {
      "epoch": 0.005314116628756618,
      "grad_norm": 0.4648854732513428,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.3731,
      "step": 66
    },
    {
      "epoch": 0.005394633547374142,
      "grad_norm": 0.4596269130706787,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.4532,
      "step": 67
    },
    {
      "epoch": 0.005475150465991666,
      "grad_norm": 0.5018298625946045,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.4546,
      "step": 68
    },
    {
      "epoch": 0.005555667384609191,
      "grad_norm": 0.495149165391922,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.355,
      "step": 69
    },
    {
      "epoch": 0.005636184303226715,
      "grad_norm": 0.5004109740257263,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.266,
      "step": 70
    },
    {
      "epoch": 0.00571670122184424,
      "grad_norm": 0.5031141042709351,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.5312,
      "step": 71
    },
    {
      "epoch": 0.005797218140461764,
      "grad_norm": 0.5997195243835449,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.46,
      "step": 72
    },
    {
      "epoch": 0.0058777350590792895,
      "grad_norm": 0.5207065343856812,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.4882,
      "step": 73
    },
    {
      "epoch": 0.005958251977696814,
      "grad_norm": 0.5105201601982117,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.3682,
      "step": 74
    },
    {
      "epoch": 0.006038768896314338,
      "grad_norm": 0.5663651823997498,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.4381,
      "step": 75
    },
    {
      "epoch": 0.006119285814931863,
      "grad_norm": 0.5280080437660217,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.3723,
      "step": 76
    },
    {
      "epoch": 0.006199802733549387,
      "grad_norm": 0.6614448428153992,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.4818,
      "step": 77
    },
    {
      "epoch": 0.006280319652166912,
      "grad_norm": 0.5965041518211365,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.3351,
      "step": 78
    },
    {
      "epoch": 0.006360836570784436,
      "grad_norm": 0.6547884941101074,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.4995,
      "step": 79
    },
    {
      "epoch": 0.00644135348940196,
      "grad_norm": 0.6421893239021301,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.5583,
      "step": 80
    },
    {
      "epoch": 0.006521870408019485,
      "grad_norm": 0.666612446308136,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.5512,
      "step": 81
    },
    {
      "epoch": 0.0066023873266370095,
      "grad_norm": 0.7277308702468872,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.388,
      "step": 82
    },
    {
      "epoch": 0.0066829042452545345,
      "grad_norm": 0.6979571580886841,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.5284,
      "step": 83
    },
    {
      "epoch": 0.006763421163872059,
      "grad_norm": 0.6597092747688293,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.4454,
      "step": 84
    },
    {
      "epoch": 0.006843938082489583,
      "grad_norm": 0.6322495341300964,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.6041,
      "step": 85
    },
    {
      "epoch": 0.006924455001107108,
      "grad_norm": 0.6709463596343994,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.4301,
      "step": 86
    },
    {
      "epoch": 0.007004971919724632,
      "grad_norm": 0.9026774764060974,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.3447,
      "step": 87
    },
    {
      "epoch": 0.007085488838342157,
      "grad_norm": 0.8283661007881165,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.6074,
      "step": 88
    },
    {
      "epoch": 0.007166005756959681,
      "grad_norm": 0.6361680030822754,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.4813,
      "step": 89
    },
    {
      "epoch": 0.007246522675577205,
      "grad_norm": 0.7173851728439331,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.4084,
      "step": 90
    },
    {
      "epoch": 0.00732703959419473,
      "grad_norm": 0.7785750031471252,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.3313,
      "step": 91
    },
    {
      "epoch": 0.0074075565128122545,
      "grad_norm": 0.8564140200614929,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.4273,
      "step": 92
    },
    {
      "epoch": 0.0074880734314297795,
      "grad_norm": 0.9119535684585571,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.5423,
      "step": 93
    },
    {
      "epoch": 0.007568590350047304,
      "grad_norm": 0.8943213224411011,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.4068,
      "step": 94
    },
    {
      "epoch": 0.007649107268664828,
      "grad_norm": 0.9337512254714966,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.4746,
      "step": 95
    },
    {
      "epoch": 0.007729624187282353,
      "grad_norm": 1.1742053031921387,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.8425,
      "step": 96
    },
    {
      "epoch": 0.007810141105899877,
      "grad_norm": 1.1696361303329468,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.7462,
      "step": 97
    },
    {
      "epoch": 0.007890658024517402,
      "grad_norm": 1.1739925146102905,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.6647,
      "step": 98
    },
    {
      "epoch": 0.007971174943134927,
      "grad_norm": 1.2244256734848022,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.7935,
      "step": 99
    },
    {
      "epoch": 0.00805169186175245,
      "grad_norm": 1.8664811849594116,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 2.3502,
      "step": 100
    },
    {
      "epoch": 0.00805169186175245,
      "eval_loss": 1.5458824634552002,
      "eval_runtime": 1563.1648,
      "eval_samples_per_second": 13.382,
      "eval_steps_per_second": 3.346,
      "step": 100
    },
    {
      "epoch": 0.008132208780369975,
      "grad_norm": 0.42842939496040344,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.3317,
      "step": 101
    },
    {
      "epoch": 0.0082127256989875,
      "grad_norm": 0.5643890500068665,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.4563,
      "step": 102
    },
    {
      "epoch": 0.008293242617605024,
      "grad_norm": 0.4634335935115814,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.3654,
      "step": 103
    },
    {
      "epoch": 0.008373759536222549,
      "grad_norm": 0.44454672932624817,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.3543,
      "step": 104
    },
    {
      "epoch": 0.008454276454840074,
      "grad_norm": 0.44821494817733765,
      "learning_rate": 5e-05,
      "loss": 1.2992,
      "step": 105
    },
    {
      "epoch": 0.008534793373457597,
      "grad_norm": 0.43948835134506226,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.2973,
      "step": 106
    },
    {
      "epoch": 0.008615310292075122,
      "grad_norm": 0.37838828563690186,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.4294,
      "step": 107
    },
    {
      "epoch": 0.008695827210692647,
      "grad_norm": 0.4603414237499237,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.451,
      "step": 108
    },
    {
      "epoch": 0.008776344129310172,
      "grad_norm": 0.4389083981513977,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.2915,
      "step": 109
    },
    {
      "epoch": 0.008856861047927695,
      "grad_norm": 0.41231870651245117,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.4153,
      "step": 110
    },
    {
      "epoch": 0.00893737796654522,
      "grad_norm": 0.4334801733493805,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.4621,
      "step": 111
    },
    {
      "epoch": 0.009017894885162745,
      "grad_norm": 0.44022494554519653,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.5572,
      "step": 112
    },
    {
      "epoch": 0.009098411803780269,
      "grad_norm": 0.45386338233947754,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.465,
      "step": 113
    },
    {
      "epoch": 0.009178928722397794,
      "grad_norm": 0.41959309577941895,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.4254,
      "step": 114
    },
    {
      "epoch": 0.009259445641015319,
      "grad_norm": 0.5270527005195618,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.4127,
      "step": 115
    },
    {
      "epoch": 0.009339962559632842,
      "grad_norm": 0.4227737784385681,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.2715,
      "step": 116
    },
    {
      "epoch": 0.009420479478250367,
      "grad_norm": 0.45509597659111023,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.5044,
      "step": 117
    },
    {
      "epoch": 0.009500996396867892,
      "grad_norm": 0.5056562423706055,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.3814,
      "step": 118
    },
    {
      "epoch": 0.009581513315485417,
      "grad_norm": 0.46866923570632935,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.3934,
      "step": 119
    },
    {
      "epoch": 0.00966203023410294,
      "grad_norm": 0.4556780159473419,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.388,
      "step": 120
    },
    {
      "epoch": 0.009742547152720465,
      "grad_norm": 0.5601311326026917,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.3276,
      "step": 121
    },
    {
      "epoch": 0.00982306407133799,
      "grad_norm": 0.5342466831207275,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.3697,
      "step": 122
    },
    {
      "epoch": 0.009903580989955514,
      "grad_norm": 0.49002259969711304,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.3699,
      "step": 123
    },
    {
      "epoch": 0.009984097908573039,
      "grad_norm": 0.5552515387535095,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.5532,
      "step": 124
    },
    {
      "epoch": 0.010064614827190564,
      "grad_norm": 0.4900350868701935,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.3606,
      "step": 125
    },
    {
      "epoch": 0.010145131745808087,
      "grad_norm": 0.5334219932556152,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.2242,
      "step": 126
    },
    {
      "epoch": 0.010225648664425612,
      "grad_norm": 0.629417359828949,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.4833,
      "step": 127
    },
    {
      "epoch": 0.010306165583043137,
      "grad_norm": 0.5269851684570312,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.3561,
      "step": 128
    },
    {
      "epoch": 0.010386682501660662,
      "grad_norm": 0.739433228969574,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.426,
      "step": 129
    },
    {
      "epoch": 0.010467199420278185,
      "grad_norm": 0.7249503135681152,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.4334,
      "step": 130
    },
    {
      "epoch": 0.01054771633889571,
      "grad_norm": 0.6687948107719421,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.5072,
      "step": 131
    },
    {
      "epoch": 0.010628233257513236,
      "grad_norm": 0.6781296133995056,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.6441,
      "step": 132
    },
    {
      "epoch": 0.010708750176130759,
      "grad_norm": 0.6829041838645935,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.408,
      "step": 133
    },
    {
      "epoch": 0.010789267094748284,
      "grad_norm": 0.5669664144515991,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.4808,
      "step": 134
    },
    {
      "epoch": 0.010869784013365809,
      "grad_norm": 0.6487475633621216,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.5326,
      "step": 135
    },
    {
      "epoch": 0.010950300931983332,
      "grad_norm": 0.6838583946228027,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.4965,
      "step": 136
    },
    {
      "epoch": 0.011030817850600857,
      "grad_norm": 0.7144851088523865,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.4568,
      "step": 137
    },
    {
      "epoch": 0.011111334769218382,
      "grad_norm": 0.6923321485519409,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.393,
      "step": 138
    },
    {
      "epoch": 0.011191851687835907,
      "grad_norm": 0.8496538996696472,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.6645,
      "step": 139
    },
    {
      "epoch": 0.01127236860645343,
      "grad_norm": 0.5879185199737549,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.3587,
      "step": 140
    },
    {
      "epoch": 0.011352885525070956,
      "grad_norm": 0.7312722206115723,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.3843,
      "step": 141
    },
    {
      "epoch": 0.01143340244368848,
      "grad_norm": 0.9298387169837952,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.7808,
      "step": 142
    },
    {
      "epoch": 0.011513919362306004,
      "grad_norm": 0.9687211513519287,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.5339,
      "step": 143
    },
    {
      "epoch": 0.011594436280923529,
      "grad_norm": 0.8629782199859619,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.4944,
      "step": 144
    },
    {
      "epoch": 0.011674953199541054,
      "grad_norm": 0.8845195770263672,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.4167,
      "step": 145
    },
    {
      "epoch": 0.011755470118158579,
      "grad_norm": 0.8540925979614258,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.4933,
      "step": 146
    },
    {
      "epoch": 0.011835987036776102,
      "grad_norm": 0.9973525404930115,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.5346,
      "step": 147
    },
    {
      "epoch": 0.011916503955393627,
      "grad_norm": 1.0560837984085083,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.496,
      "step": 148
    },
    {
      "epoch": 0.011997020874011152,
      "grad_norm": 0.9571331143379211,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.4229,
      "step": 149
    },
    {
      "epoch": 0.012077537792628676,
      "grad_norm": 1.4350992441177368,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.7281,
      "step": 150
    },
    {
      "epoch": 0.012077537792628676,
      "eval_loss": 1.4881032705307007,
      "eval_runtime": 1565.186,
      "eval_samples_per_second": 13.365,
      "eval_steps_per_second": 3.341,
      "step": 150
    },
    {
      "epoch": 0.0121580547112462,
      "grad_norm": 0.26667049527168274,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.2019,
      "step": 151
    },
    {
      "epoch": 0.012238571629863726,
      "grad_norm": 0.39429017901420593,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.3906,
      "step": 152
    },
    {
      "epoch": 0.012319088548481249,
      "grad_norm": 0.346015989780426,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.4222,
      "step": 153
    },
    {
      "epoch": 0.012399605467098774,
      "grad_norm": 0.32731351256370544,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.3621,
      "step": 154
    },
    {
      "epoch": 0.012480122385716299,
      "grad_norm": 0.33853569626808167,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.4196,
      "step": 155
    },
    {
      "epoch": 0.012560639304333824,
      "grad_norm": 0.33642446994781494,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.3536,
      "step": 156
    },
    {
      "epoch": 0.012641156222951347,
      "grad_norm": 0.37169885635375977,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.4761,
      "step": 157
    },
    {
      "epoch": 0.012721673141568872,
      "grad_norm": 0.451521098613739,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.3824,
      "step": 158
    },
    {
      "epoch": 0.012802190060186397,
      "grad_norm": 0.37195083498954773,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.2683,
      "step": 159
    },
    {
      "epoch": 0.01288270697880392,
      "grad_norm": 0.39328181743621826,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.2856,
      "step": 160
    },
    {
      "epoch": 0.012963223897421446,
      "grad_norm": 0.34638622403144836,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.2844,
      "step": 161
    },
    {
      "epoch": 0.01304374081603897,
      "grad_norm": 0.41183391213417053,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.3941,
      "step": 162
    },
    {
      "epoch": 0.013124257734656494,
      "grad_norm": 0.41171473264694214,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.3354,
      "step": 163
    },
    {
      "epoch": 0.013204774653274019,
      "grad_norm": 0.4064787030220032,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.4138,
      "step": 164
    },
    {
      "epoch": 0.013285291571891544,
      "grad_norm": 0.4661749601364136,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.3705,
      "step": 165
    },
    {
      "epoch": 0.013365808490509069,
      "grad_norm": 0.4481525123119354,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.4985,
      "step": 166
    },
    {
      "epoch": 0.013446325409126592,
      "grad_norm": 0.4615930914878845,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.3835,
      "step": 167
    },
    {
      "epoch": 0.013526842327744117,
      "grad_norm": 0.4717801809310913,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.4163,
      "step": 168
    },
    {
      "epoch": 0.013607359246361642,
      "grad_norm": 0.5136454105377197,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.4726,
      "step": 169
    },
    {
      "epoch": 0.013687876164979166,
      "grad_norm": 0.4442136585712433,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.3468,
      "step": 170
    },
    {
      "epoch": 0.01376839308359669,
      "grad_norm": 0.46402686834335327,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.2927,
      "step": 171
    },
    {
      "epoch": 0.013848910002214216,
      "grad_norm": 0.43890780210494995,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.4446,
      "step": 172
    },
    {
      "epoch": 0.013929426920831739,
      "grad_norm": 0.45133015513420105,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.4763,
      "step": 173
    },
    {
      "epoch": 0.014009943839449264,
      "grad_norm": 0.5477501749992371,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.4132,
      "step": 174
    },
    {
      "epoch": 0.014090460758066789,
      "grad_norm": 0.5438304543495178,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.3898,
      "step": 175
    },
    {
      "epoch": 0.014170977676684314,
      "grad_norm": 0.4997485280036926,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.4163,
      "step": 176
    },
    {
      "epoch": 0.014251494595301837,
      "grad_norm": 0.5147976279258728,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.5556,
      "step": 177
    },
    {
      "epoch": 0.014332011513919362,
      "grad_norm": 0.5399206876754761,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.3201,
      "step": 178
    },
    {
      "epoch": 0.014412528432536887,
      "grad_norm": 0.7199476361274719,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.565,
      "step": 179
    },
    {
      "epoch": 0.01449304535115441,
      "grad_norm": 0.6314929127693176,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.3938,
      "step": 180
    },
    {
      "epoch": 0.014573562269771936,
      "grad_norm": 0.6556135416030884,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.5652,
      "step": 181
    },
    {
      "epoch": 0.01465407918838946,
      "grad_norm": 0.59678715467453,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.315,
      "step": 182
    },
    {
      "epoch": 0.014734596107006984,
      "grad_norm": 0.5509481430053711,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.4197,
      "step": 183
    },
    {
      "epoch": 0.014815113025624509,
      "grad_norm": 0.6057325601577759,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.4712,
      "step": 184
    },
    {
      "epoch": 0.014895629944242034,
      "grad_norm": 0.6615339517593384,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.4587,
      "step": 185
    },
    {
      "epoch": 0.014976146862859559,
      "grad_norm": 0.6603967547416687,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.1763,
      "step": 186
    },
    {
      "epoch": 0.015056663781477082,
      "grad_norm": 0.7309848666191101,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.4143,
      "step": 187
    },
    {
      "epoch": 0.015137180700094607,
      "grad_norm": 0.690373420715332,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.3348,
      "step": 188
    },
    {
      "epoch": 0.015217697618712132,
      "grad_norm": 0.7621862292289734,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.5015,
      "step": 189
    },
    {
      "epoch": 0.015298214537329656,
      "grad_norm": 0.7496787309646606,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.3518,
      "step": 190
    },
    {
      "epoch": 0.01537873145594718,
      "grad_norm": 0.8436548113822937,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.6093,
      "step": 191
    },
    {
      "epoch": 0.015459248374564706,
      "grad_norm": 0.8552038073539734,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.4763,
      "step": 192
    },
    {
      "epoch": 0.01553976529318223,
      "grad_norm": 0.9818535447120667,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 1.5643,
      "step": 193
    },
    {
      "epoch": 0.015620282211799754,
      "grad_norm": 1.0228612422943115,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.672,
      "step": 194
    },
    {
      "epoch": 0.01570079913041728,
      "grad_norm": 0.9128052592277527,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.4994,
      "step": 195
    },
    {
      "epoch": 0.015781316049034804,
      "grad_norm": 0.8675194382667542,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.3002,
      "step": 196
    },
    {
      "epoch": 0.01586183296765233,
      "grad_norm": 1.1194286346435547,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.6567,
      "step": 197
    },
    {
      "epoch": 0.015942349886269854,
      "grad_norm": 1.0962642431259155,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.7238,
      "step": 198
    },
    {
      "epoch": 0.016022866804887376,
      "grad_norm": 1.275984287261963,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.6813,
      "step": 199
    },
    {
      "epoch": 0.0161033837235049,
      "grad_norm": 1.448941707611084,
      "learning_rate": 0.0,
      "loss": 1.8146,
      "step": 200
    },
    {
      "epoch": 0.0161033837235049,
      "eval_loss": 1.4893519878387451,
      "eval_runtime": 1563.6447,
      "eval_samples_per_second": 13.378,
      "eval_steps_per_second": 3.345,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.7847343411822592e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}