{
  "best_metric": 0.07994554191827774,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.3484848484848486,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006734006734006734,
      "grad_norm": 6.121026039123535,
      "learning_rate": 1e-05,
      "loss": 2.8675,
      "step": 1
    },
    {
      "epoch": 0.006734006734006734,
      "eval_loss": 4.463713645935059,
      "eval_runtime": 18.7561,
      "eval_samples_per_second": 13.329,
      "eval_steps_per_second": 3.359,
      "step": 1
    },
    {
      "epoch": 0.013468013468013467,
      "grad_norm": 5.401608943939209,
      "learning_rate": 2e-05,
      "loss": 2.8226,
      "step": 2
    },
    {
      "epoch": 0.020202020202020204,
      "grad_norm": 6.750210285186768,
      "learning_rate": 3e-05,
      "loss": 3.0636,
      "step": 3
    },
    {
      "epoch": 0.026936026936026935,
      "grad_norm": 8.059123992919922,
      "learning_rate": 4e-05,
      "loss": 3.6148,
      "step": 4
    },
    {
      "epoch": 0.03367003367003367,
      "grad_norm": 7.225228309631348,
      "learning_rate": 5e-05,
      "loss": 2.9129,
      "step": 5
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 10.421002388000488,
      "learning_rate": 6e-05,
      "loss": 3.012,
      "step": 6
    },
    {
      "epoch": 0.04713804713804714,
      "grad_norm": 9.47394847869873,
      "learning_rate": 7e-05,
      "loss": 2.1905,
      "step": 7
    },
    {
      "epoch": 0.05387205387205387,
      "grad_norm": 8.703824996948242,
      "learning_rate": 8e-05,
      "loss": 1.266,
      "step": 8
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 5.181202411651611,
      "learning_rate": 9e-05,
      "loss": 0.572,
      "step": 9
    },
    {
      "epoch": 0.06734006734006734,
      "grad_norm": 5.445838451385498,
      "learning_rate": 0.0001,
      "loss": 1.0015,
      "step": 10
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 8.712956428527832,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.8769,
      "step": 11
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 4.731899261474609,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.4426,
      "step": 12
    },
    {
      "epoch": 0.08754208754208755,
      "grad_norm": 11.56647777557373,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.378,
      "step": 13
    },
    {
      "epoch": 0.09427609427609428,
      "grad_norm": 34.63393020629883,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.83,
      "step": 14
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 45.28231430053711,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.4133,
      "step": 15
    },
    {
      "epoch": 0.10774410774410774,
      "grad_norm": 14.745728492736816,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.1377,
      "step": 16
    },
    {
      "epoch": 0.11447811447811448,
      "grad_norm": 8.851201057434082,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.3687,
      "step": 17
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 19.857824325561523,
      "learning_rate": 9.956320346634876e-05,
      "loss": 2.1217,
      "step": 18
    },
    {
      "epoch": 0.12794612794612795,
      "grad_norm": 20.709373474121094,
      "learning_rate": 9.944739353007344e-05,
      "loss": 2.4086,
      "step": 19
    },
    {
      "epoch": 0.13468013468013468,
      "grad_norm": 14.202071189880371,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.4594,
      "step": 20
    },
    {
      "epoch": 0.1414141414141414,
      "grad_norm": 6.514452934265137,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.7042,
      "step": 21
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 13.507194519042969,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.9844,
      "step": 22
    },
    {
      "epoch": 0.15488215488215487,
      "grad_norm": 15.926103591918945,
      "learning_rate": 9.884934153917997e-05,
      "loss": 2.6745,
      "step": 23
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 6.509042739868164,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.515,
      "step": 24
    },
    {
      "epoch": 0.16835016835016836,
      "grad_norm": 7.085171222686768,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.0526,
      "step": 25
    },
    {
      "epoch": 0.1750841750841751,
      "grad_norm": 18.25786590576172,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.5697,
      "step": 26
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 26.057647705078125,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.6904,
      "step": 27
    },
    {
      "epoch": 0.18855218855218855,
      "grad_norm": 17.099252700805664,
      "learning_rate": 9.780178907671789e-05,
      "loss": 2.2878,
      "step": 28
    },
    {
      "epoch": 0.19528619528619529,
      "grad_norm": 16.112071990966797,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8625,
      "step": 29
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 12.023772239685059,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.6545,
      "step": 30
    },
    {
      "epoch": 0.20875420875420875,
      "grad_norm": 11.859292984008789,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.9407,
      "step": 31
    },
    {
      "epoch": 0.21548821548821548,
      "grad_norm": 7.53825569152832,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.1836,
      "step": 32
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 6.366017818450928,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.6869,
      "step": 33
    },
    {
      "epoch": 0.22895622895622897,
      "grad_norm": 4.454495906829834,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.4733,
      "step": 34
    },
    {
      "epoch": 0.2356902356902357,
      "grad_norm": 10.728924751281738,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.5969,
      "step": 35
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 51.227439880371094,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.5813,
      "step": 36
    },
    {
      "epoch": 0.24915824915824916,
      "grad_norm": 33.850791931152344,
      "learning_rate": 9.509956150664796e-05,
      "loss": 3.8551,
      "step": 37
    },
    {
      "epoch": 0.2558922558922559,
      "grad_norm": 25.391429901123047,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.2337,
      "step": 38
    },
    {
      "epoch": 0.26262626262626265,
      "grad_norm": 20.936763763427734,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.7138,
      "step": 39
    },
    {
      "epoch": 0.26936026936026936,
      "grad_norm": 27.38364028930664,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.7087,
      "step": 40
    },
    {
      "epoch": 0.2760942760942761,
      "grad_norm": 18.151782989501953,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.9714,
      "step": 41
    },
    {
      "epoch": 0.2828282828282828,
      "grad_norm": 16.08642578125,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.799,
      "step": 42
    },
    {
      "epoch": 0.2895622895622896,
      "grad_norm": 12.910481452941895,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.9214,
      "step": 43
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 6.000406265258789,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.3767,
      "step": 44
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 2.063612699508667,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.0837,
      "step": 45
    },
    {
      "epoch": 0.30976430976430974,
      "grad_norm": 0.5385233163833618,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.02,
      "step": 46
    },
    {
      "epoch": 0.3164983164983165,
      "grad_norm": 0.5535562038421631,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.0081,
      "step": 47
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 3.3844351768493652,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.1975,
      "step": 48
    },
    {
      "epoch": 0.32996632996632996,
      "grad_norm": 3.400275707244873,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.2479,
      "step": 49
    },
    {
      "epoch": 0.3367003367003367,
      "grad_norm": 2.0123932361602783,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.1787,
      "step": 50
    },
    {
      "epoch": 0.3367003367003367,
      "eval_loss": 0.8339872360229492,
      "eval_runtime": 19.0793,
      "eval_samples_per_second": 13.103,
      "eval_steps_per_second": 3.302,
      "step": 50
    },
    {
      "epoch": 0.3434343434343434,
      "grad_norm": 4.244322299957275,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.2517,
      "step": 51
    },
    {
      "epoch": 0.3501683501683502,
      "grad_norm": 3.9279189109802246,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.3568,
      "step": 52
    },
    {
      "epoch": 0.3569023569023569,
      "grad_norm": 17.319961547851562,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.5707,
      "step": 53
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 17.113658905029297,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.9504,
      "step": 54
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 2.1276981830596924,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.0218,
      "step": 55
    },
    {
      "epoch": 0.3771043771043771,
      "grad_norm": 0.29551687836647034,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.0026,
      "step": 56
    },
    {
      "epoch": 0.3838383838383838,
      "grad_norm": 9.554738998413086,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.957,
      "step": 57
    },
    {
      "epoch": 0.39057239057239057,
      "grad_norm": 9.033601760864258,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.6361,
      "step": 58
    },
    {
      "epoch": 0.39730639730639733,
      "grad_norm": 2.822766065597534,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.1721,
      "step": 59
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 0.896061360836029,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.0536,
      "step": 60
    },
    {
      "epoch": 0.4107744107744108,
      "grad_norm": 28.111530303955078,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.9259,
      "step": 61
    },
    {
      "epoch": 0.4175084175084175,
      "grad_norm": 10.919363975524902,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.0929,
      "step": 62
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 7.4378981590271,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.5817,
      "step": 63
    },
    {
      "epoch": 0.43097643097643096,
      "grad_norm": 17.82065773010254,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.9908,
      "step": 64
    },
    {
      "epoch": 0.4377104377104377,
      "grad_norm": 12.175094604492188,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.7306,
      "step": 65
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 11.517578125,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.9027,
      "step": 66
    },
    {
      "epoch": 0.4511784511784512,
      "grad_norm": 11.20206069946289,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8769,
      "step": 67
    },
    {
      "epoch": 0.45791245791245794,
      "grad_norm": 8.96699047088623,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.6167,
      "step": 68
    },
    {
      "epoch": 0.46464646464646464,
      "grad_norm": 5.195659637451172,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.4302,
      "step": 69
    },
    {
      "epoch": 0.4713804713804714,
      "grad_norm": 4.217161178588867,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.294,
      "step": 70
    },
    {
      "epoch": 0.4781144781144781,
      "grad_norm": 2.0732929706573486,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.1291,
      "step": 71
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 9.605835914611816,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.4103,
      "step": 72
    },
    {
      "epoch": 0.49158249158249157,
      "grad_norm": 13.96337604522705,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.0666,
      "step": 73
    },
    {
      "epoch": 0.4983164983164983,
      "grad_norm": 32.71107482910156,
      "learning_rate": 7.452117519152542e-05,
      "loss": 2.6826,
      "step": 74
    },
    {
      "epoch": 0.5050505050505051,
      "grad_norm": 9.413982391357422,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.1954,
      "step": 75
    },
    {
      "epoch": 0.5117845117845118,
      "grad_norm": 6.991236209869385,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.8157,
      "step": 76
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 14.62874984741211,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.4164,
      "step": 77
    },
    {
      "epoch": 0.5252525252525253,
      "grad_norm": 13.252262115478516,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.2324,
      "step": 78
    },
    {
      "epoch": 0.531986531986532,
      "grad_norm": 8.076154708862305,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.9044,
      "step": 79
    },
    {
      "epoch": 0.5387205387205387,
      "grad_norm": 20.27266502380371,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.5883,
      "step": 80
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 9.704740524291992,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7538,
      "step": 81
    },
    {
      "epoch": 0.5521885521885522,
      "grad_norm": 7.8740057945251465,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.318,
      "step": 82
    },
    {
      "epoch": 0.5589225589225589,
      "grad_norm": 3.428229808807373,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.1222,
      "step": 83
    },
    {
      "epoch": 0.5656565656565656,
      "grad_norm": 3.7295846939086914,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.3864,
      "step": 84
    },
    {
      "epoch": 0.5723905723905723,
      "grad_norm": 4.210822582244873,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.4438,
      "step": 85
    },
    {
      "epoch": 0.5791245791245792,
      "grad_norm": 2.802032232284546,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.2611,
      "step": 86
    },
    {
      "epoch": 0.5858585858585859,
      "grad_norm": 2.6524429321289062,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.1232,
      "step": 87
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 4.63939905166626,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.3219,
      "step": 88
    },
    {
      "epoch": 0.5993265993265994,
      "grad_norm": 12.697944641113281,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.9179,
      "step": 89
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 7.046720027923584,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.5563,
      "step": 90
    },
    {
      "epoch": 0.6127946127946128,
      "grad_norm": 3.9998939037323,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.2472,
      "step": 91
    },
    {
      "epoch": 0.6195286195286195,
      "grad_norm": 4.337342262268066,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.5139,
      "step": 92
    },
    {
      "epoch": 0.6262626262626263,
      "grad_norm": 5.748466968536377,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.6184,
      "step": 93
    },
    {
      "epoch": 0.632996632996633,
      "grad_norm": 2.739331007003784,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.1089,
      "step": 94
    },
    {
      "epoch": 0.6397306397306397,
      "grad_norm": 1.7327274084091187,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.1593,
      "step": 95
    },
    {
      "epoch": 0.6464646464646465,
      "grad_norm": 4.314657211303711,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.3038,
      "step": 96
    },
    {
      "epoch": 0.6531986531986532,
      "grad_norm": 6.426628112792969,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.6352,
      "step": 97
    },
    {
      "epoch": 0.6599326599326599,
      "grad_norm": 3.179295778274536,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.3076,
      "step": 98
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 2.7440943717956543,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.311,
      "step": 99
    },
    {
      "epoch": 0.6734006734006734,
      "grad_norm": 7.669990062713623,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.7346,
      "step": 100
    },
    {
      "epoch": 0.6734006734006734,
      "eval_loss": 0.41200679540634155,
      "eval_runtime": 19.0809,
      "eval_samples_per_second": 13.102,
      "eval_steps_per_second": 3.302,
      "step": 100
    },
    {
      "epoch": 0.6801346801346801,
      "grad_norm": 8.629302978515625,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.7252,
      "step": 101
    },
    {
      "epoch": 0.6868686868686869,
      "grad_norm": 9.565890312194824,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.66,
      "step": 102
    },
    {
      "epoch": 0.6936026936026936,
      "grad_norm": 9.665349006652832,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.6068,
      "step": 103
    },
    {
      "epoch": 0.7003367003367004,
      "grad_norm": 5.815318584442139,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.38,
      "step": 104
    },
    {
      "epoch": 0.7070707070707071,
      "grad_norm": 8.690848350524902,
      "learning_rate": 5e-05,
      "loss": 0.274,
      "step": 105
    },
    {
      "epoch": 0.7138047138047138,
      "grad_norm": 8.568137168884277,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.3357,
      "step": 106
    },
    {
      "epoch": 0.7205387205387206,
      "grad_norm": 5.144561767578125,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.138,
      "step": 107
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 8.123993873596191,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.1827,
      "step": 108
    },
    {
      "epoch": 0.734006734006734,
      "grad_norm": 3.8712053298950195,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.1489,
      "step": 109
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 3.3853085041046143,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.1053,
      "step": 110
    },
    {
      "epoch": 0.7474747474747475,
      "grad_norm": 14.193425178527832,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.2038,
      "step": 111
    },
    {
      "epoch": 0.7542087542087542,
      "grad_norm": 5.1542863845825195,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.3054,
      "step": 112
    },
    {
      "epoch": 0.7609427609427609,
      "grad_norm": 4.273439884185791,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.2325,
      "step": 113
    },
    {
      "epoch": 0.7676767676767676,
      "grad_norm": 3.6603095531463623,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.2397,
      "step": 114
    },
    {
      "epoch": 0.7744107744107744,
      "grad_norm": 6.249441623687744,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.4568,
      "step": 115
    },
    {
      "epoch": 0.7811447811447811,
      "grad_norm": 4.61054801940918,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.1693,
      "step": 116
    },
    {
      "epoch": 0.7878787878787878,
      "grad_norm": 4.619693756103516,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.5565,
      "step": 117
    },
    {
      "epoch": 0.7946127946127947,
      "grad_norm": 7.368781089782715,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.7525,
      "step": 118
    },
    {
      "epoch": 0.8013468013468014,
      "grad_norm": 3.864196538925171,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.3568,
      "step": 119
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 4.652040958404541,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.2723,
      "step": 120
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 2.7281908988952637,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.0842,
      "step": 121
    },
    {
      "epoch": 0.8215488215488216,
      "grad_norm": 0.9157584309577942,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.033,
      "step": 122
    },
    {
      "epoch": 0.8282828282828283,
      "grad_norm": 0.9845476746559143,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.0304,
      "step": 123
    },
    {
      "epoch": 0.835016835016835,
      "grad_norm": 1.3026992082595825,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0562,
      "step": 124
    },
    {
      "epoch": 0.8417508417508418,
      "grad_norm": 5.472594261169434,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.1806,
      "step": 125
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 3.1418073177337646,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.1032,
      "step": 126
    },
    {
      "epoch": 0.8552188552188552,
      "grad_norm": 17.40517234802246,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.6696,
      "step": 127
    },
    {
      "epoch": 0.8619528619528619,
      "grad_norm": 12.50394344329834,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.7633,
      "step": 128
    },
    {
      "epoch": 0.8686868686868687,
      "grad_norm": 10.156083106994629,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.4443,
      "step": 129
    },
    {
      "epoch": 0.8754208754208754,
      "grad_norm": 3.4469010829925537,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.1296,
      "step": 130
    },
    {
      "epoch": 0.8821548821548821,
      "grad_norm": 14.18774127960205,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.1235,
      "step": 131
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 15.086287498474121,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.5188,
      "step": 132
    },
    {
      "epoch": 0.8956228956228957,
      "grad_norm": 3.5302555561065674,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.2315,
      "step": 133
    },
    {
      "epoch": 0.9023569023569024,
      "grad_norm": 5.8531012535095215,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.2845,
      "step": 134
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 5.840641975402832,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.2867,
      "step": 135
    },
    {
      "epoch": 0.9158249158249159,
      "grad_norm": 1.5300294160842896,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.1229,
      "step": 136
    },
    {
      "epoch": 0.9225589225589226,
      "grad_norm": 10.018693923950195,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.3112,
      "step": 137
    },
    {
      "epoch": 0.9292929292929293,
      "grad_norm": 9.715715408325195,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.2506,
      "step": 138
    },
    {
      "epoch": 0.936026936026936,
      "grad_norm": 4.553313732147217,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.3357,
      "step": 139
    },
    {
      "epoch": 0.9427609427609428,
      "grad_norm": 10.136809349060059,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.9882,
      "step": 140
    },
    {
      "epoch": 0.9494949494949495,
      "grad_norm": 6.176605701446533,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.3524,
      "step": 141
    },
    {
      "epoch": 0.9562289562289562,
      "grad_norm": 2.6813530921936035,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.3056,
      "step": 142
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 5.840284824371338,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.3219,
      "step": 143
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 3.654775381088257,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.2013,
      "step": 144
    },
    {
      "epoch": 0.9764309764309764,
      "grad_norm": 2.143498659133911,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.1308,
      "step": 145
    },
    {
      "epoch": 0.9831649831649831,
      "grad_norm": 2.276360034942627,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.0875,
      "step": 146
    },
    {
      "epoch": 0.98989898989899,
      "grad_norm": 1.5602620840072632,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.0661,
      "step": 147
    },
    {
      "epoch": 0.9966329966329966,
      "grad_norm": 7.182041645050049,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.622,
      "step": 148
    },
    {
      "epoch": 1.005050505050505,
      "grad_norm": 1.9773716926574707,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.0677,
      "step": 149
    },
    {
      "epoch": 1.0117845117845117,
      "grad_norm": 1.700388789176941,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.0282,
      "step": 150
    },
    {
      "epoch": 1.0117845117845117,
      "eval_loss": 0.1453329175710678,
      "eval_runtime": 19.0916,
      "eval_samples_per_second": 13.095,
      "eval_steps_per_second": 3.3,
      "step": 150
    },
    {
      "epoch": 1.0185185185185186,
      "grad_norm": 8.89376163482666,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.3086,
      "step": 151
    },
    {
      "epoch": 1.0252525252525253,
      "grad_norm": 36.16452407836914,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.2191,
      "step": 152
    },
    {
      "epoch": 1.031986531986532,
      "grad_norm": 0.9914328455924988,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.0166,
      "step": 153
    },
    {
      "epoch": 1.0387205387205387,
      "grad_norm": 2.0962395668029785,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.0806,
      "step": 154
    },
    {
      "epoch": 1.0454545454545454,
      "grad_norm": 0.9336819648742676,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.0069,
      "step": 155
    },
    {
      "epoch": 1.0521885521885521,
      "grad_norm": 0.17883454263210297,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.0026,
      "step": 156
    },
    {
      "epoch": 1.0589225589225588,
      "grad_norm": 0.15024049580097198,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.0018,
      "step": 157
    },
    {
      "epoch": 1.0656565656565657,
      "grad_norm": 0.14298710227012634,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.0016,
      "step": 158
    },
    {
      "epoch": 1.0723905723905724,
      "grad_norm": 0.3942915201187134,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.0051,
      "step": 159
    },
    {
      "epoch": 1.0791245791245792,
      "grad_norm": 0.2913673520088196,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.0038,
      "step": 160
    },
    {
      "epoch": 1.0858585858585859,
      "grad_norm": 0.18271450698375702,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.0027,
      "step": 161
    },
    {
      "epoch": 1.0925925925925926,
      "grad_norm": 4.659060478210449,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.2889,
      "step": 162
    },
    {
      "epoch": 1.0993265993265993,
      "grad_norm": 5.062216758728027,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.2755,
      "step": 163
    },
    {
      "epoch": 1.106060606060606,
      "grad_norm": 2.2467360496520996,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.0563,
      "step": 164
    },
    {
      "epoch": 1.112794612794613,
      "grad_norm": 0.3059391975402832,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.0065,
      "step": 165
    },
    {
      "epoch": 1.1195286195286196,
      "grad_norm": 0.240287184715271,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.0057,
      "step": 166
    },
    {
      "epoch": 1.1262626262626263,
      "grad_norm": 0.7112791538238525,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.0118,
      "step": 167
    },
    {
      "epoch": 1.132996632996633,
      "grad_norm": 0.6974908113479614,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.0296,
      "step": 168
    },
    {
      "epoch": 1.1397306397306397,
      "grad_norm": 1.118945837020874,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.1291,
      "step": 169
    },
    {
      "epoch": 1.1464646464646464,
      "grad_norm": 0.6697227954864502,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.0774,
      "step": 170
    },
    {
      "epoch": 1.1531986531986531,
      "grad_norm": 0.7580008506774902,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.0558,
      "step": 171
    },
    {
      "epoch": 1.15993265993266,
      "grad_norm": 3.865731716156006,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.1478,
      "step": 172
    },
    {
      "epoch": 1.1666666666666667,
      "grad_norm": 4.478240013122559,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.3446,
      "step": 173
    },
    {
      "epoch": 1.1734006734006734,
      "grad_norm": 3.7954843044281006,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.2452,
      "step": 174
    },
    {
      "epoch": 1.1801346801346801,
      "grad_norm": 9.61264419555664,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.4171,
      "step": 175
    },
    {
      "epoch": 1.1868686868686869,
      "grad_norm": 7.028502464294434,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.2597,
      "step": 176
    },
    {
      "epoch": 1.1936026936026936,
      "grad_norm": 1.9548472166061401,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.276,
      "step": 177
    },
    {
      "epoch": 1.2003367003367003,
      "grad_norm": 6.922970294952393,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.61,
      "step": 178
    },
    {
      "epoch": 1.2070707070707072,
      "grad_norm": 2.1758780479431152,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.25,
      "step": 179
    },
    {
      "epoch": 1.2138047138047139,
      "grad_norm": 1.1072797775268555,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.136,
      "step": 180
    },
    {
      "epoch": 1.2205387205387206,
      "grad_norm": 1.035145878791809,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0507,
      "step": 181
    },
    {
      "epoch": 1.2272727272727273,
      "grad_norm": 0.6913142204284668,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.055,
      "step": 182
    },
    {
      "epoch": 1.234006734006734,
      "grad_norm": 1.4909873008728027,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.0784,
      "step": 183
    },
    {
      "epoch": 1.2407407407407407,
      "grad_norm": 0.8771810531616211,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.0505,
      "step": 184
    },
    {
      "epoch": 1.2474747474747474,
      "grad_norm": 3.344261407852173,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.2536,
      "step": 185
    },
    {
      "epoch": 1.2542087542087543,
      "grad_norm": 2.5295791625976562,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.183,
      "step": 186
    },
    {
      "epoch": 1.2609427609427608,
      "grad_norm": 0.41250237822532654,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.0138,
      "step": 187
    },
    {
      "epoch": 1.2676767676767677,
      "grad_norm": 2.387815237045288,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.0541,
      "step": 188
    },
    {
      "epoch": 1.2744107744107744,
      "grad_norm": 1.1531003713607788,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.0203,
      "step": 189
    },
    {
      "epoch": 1.2811447811447811,
      "grad_norm": 0.22131957113742828,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.0066,
      "step": 190
    },
    {
      "epoch": 1.2878787878787878,
      "grad_norm": 0.3680664598941803,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.0094,
      "step": 191
    },
    {
      "epoch": 1.2946127946127945,
      "grad_norm": 0.016052616760134697,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.0004,
      "step": 192
    },
    {
      "epoch": 1.3013468013468015,
      "grad_norm": 0.0171983540058136,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.0004,
      "step": 193
    },
    {
      "epoch": 1.308080808080808,
      "grad_norm": 0.016519540920853615,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.0004,
      "step": 194
    },
    {
      "epoch": 1.3148148148148149,
      "grad_norm": 0.016674496233463287,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.0004,
      "step": 195
    },
    {
      "epoch": 1.3215488215488216,
      "grad_norm": 0.06452403962612152,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.0017,
      "step": 196
    },
    {
      "epoch": 1.3282828282828283,
      "grad_norm": 0.21854397654533386,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.0047,
      "step": 197
    },
    {
      "epoch": 1.335016835016835,
      "grad_norm": 1.0600335597991943,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.0165,
      "step": 198
    },
    {
      "epoch": 1.3417508417508417,
      "grad_norm": 0.8936813473701477,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.0159,
      "step": 199
    },
    {
      "epoch": 1.3484848484848486,
      "grad_norm": 0.14329122006893158,
      "learning_rate": 0.0,
      "loss": 0.0045,
      "step": 200
    },
    {
      "epoch": 1.3484848484848486,
      "eval_loss": 0.07994554191827774,
      "eval_runtime": 19.1148,
      "eval_samples_per_second": 13.079,
      "eval_steps_per_second": 3.296,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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
}