{
  "best_metric": 0.18108560144901276,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 1.0117845117845117,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006734006734006734,
      "grad_norm": 6.161822319030762,
      "learning_rate": 1e-05,
      "loss": 2.8675,
      "step": 1
    },
    {
      "epoch": 0.006734006734006734,
      "eval_loss": 4.463713645935059,
      "eval_runtime": 18.6145,
      "eval_samples_per_second": 13.43,
      "eval_steps_per_second": 3.384,
      "step": 1
    },
    {
      "epoch": 0.013468013468013467,
      "grad_norm": 5.41481876373291,
      "learning_rate": 2e-05,
      "loss": 2.8226,
      "step": 2
    },
    {
      "epoch": 0.020202020202020204,
      "grad_norm": 6.805539131164551,
      "learning_rate": 3e-05,
      "loss": 3.0642,
      "step": 3
    },
    {
      "epoch": 0.026936026936026935,
      "grad_norm": 8.14186954498291,
      "learning_rate": 4e-05,
      "loss": 3.6152,
      "step": 4
    },
    {
      "epoch": 0.03367003367003367,
      "grad_norm": 7.278221130371094,
      "learning_rate": 5e-05,
      "loss": 2.9121,
      "step": 5
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 10.494874000549316,
      "learning_rate": 6e-05,
      "loss": 3.014,
      "step": 6
    },
    {
      "epoch": 0.04713804713804714,
      "grad_norm": 9.578802108764648,
      "learning_rate": 7e-05,
      "loss": 2.203,
      "step": 7
    },
    {
      "epoch": 0.05387205387205387,
      "grad_norm": 8.834941864013672,
      "learning_rate": 8e-05,
      "loss": 1.2678,
      "step": 8
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 5.328277587890625,
      "learning_rate": 9e-05,
      "loss": 0.569,
      "step": 9
    },
    {
      "epoch": 0.06734006734006734,
      "grad_norm": 5.531549453735352,
      "learning_rate": 0.0001,
      "loss": 1.0076,
      "step": 10
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 8.928789138793945,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.8953,
      "step": 11
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 4.855547904968262,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.4578,
      "step": 12
    },
    {
      "epoch": 0.08754208754208755,
      "grad_norm": 11.603761672973633,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.3924,
      "step": 13
    },
    {
      "epoch": 0.09427609427609428,
      "grad_norm": 32.66161346435547,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.7657,
      "step": 14
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 44.362709045410156,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.3351,
      "step": 15
    },
    {
      "epoch": 0.10774410774410774,
      "grad_norm": 14.521812438964844,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.1321,
      "step": 16
    },
    {
      "epoch": 0.11447811447811448,
      "grad_norm": 9.498165130615234,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.3866,
      "step": 17
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 20.581798553466797,
      "learning_rate": 9.956320346634876e-05,
      "loss": 2.1088,
      "step": 18
    },
    {
      "epoch": 0.12794612794612795,
      "grad_norm": 20.961137771606445,
      "learning_rate": 9.944739353007344e-05,
      "loss": 2.4268,
      "step": 19
    },
    {
      "epoch": 0.13468013468013468,
      "grad_norm": 13.910545349121094,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.4516,
      "step": 20
    },
    {
      "epoch": 0.1414141414141414,
      "grad_norm": 6.430734157562256,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.6906,
      "step": 21
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 13.838027954101562,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.0004,
      "step": 22
    },
    {
      "epoch": 0.15488215488215487,
      "grad_norm": 15.384847640991211,
      "learning_rate": 9.884934153917997e-05,
      "loss": 2.68,
      "step": 23
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 7.194993019104004,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.5325,
      "step": 24
    },
    {
      "epoch": 0.16835016835016836,
      "grad_norm": 7.786040306091309,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.0705,
      "step": 25
    },
    {
      "epoch": 0.1750841750841751,
      "grad_norm": 18.196880340576172,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.6112,
      "step": 26
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 30.845064163208008,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.5114,
      "step": 27
    },
    {
      "epoch": 0.18855218855218855,
      "grad_norm": 16.398073196411133,
      "learning_rate": 9.780178907671789e-05,
      "loss": 2.3194,
      "step": 28
    },
    {
      "epoch": 0.19528619528619529,
      "grad_norm": 17.725175857543945,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.0657,
      "step": 29
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 14.462620735168457,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.7129,
      "step": 30
    },
    {
      "epoch": 0.20875420875420875,
      "grad_norm": 14.625421524047852,
      "learning_rate": 9.701596950580806e-05,
      "loss": 2.1476,
      "step": 31
    },
    {
      "epoch": 0.21548821548821548,
      "grad_norm": 8.385483741760254,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.3099,
      "step": 32
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 7.231852054595947,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.789,
      "step": 33
    },
    {
      "epoch": 0.22895622895622897,
      "grad_norm": 4.259565353393555,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.5128,
      "step": 34
    },
    {
      "epoch": 0.2356902356902357,
      "grad_norm": 10.803373336791992,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.7361,
      "step": 35
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 35.85740661621094,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.536,
      "step": 36
    },
    {
      "epoch": 0.24915824915824916,
      "grad_norm": 37.33977508544922,
      "learning_rate": 9.509956150664796e-05,
      "loss": 3.7534,
      "step": 37
    },
    {
      "epoch": 0.2558922558922559,
      "grad_norm": 19.735960006713867,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.2538,
      "step": 38
    },
    {
      "epoch": 0.26262626262626265,
      "grad_norm": 21.216079711914062,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.7994,
      "step": 39
    },
    {
      "epoch": 0.26936026936026936,
      "grad_norm": 23.052797317504883,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.6919,
      "step": 40
    },
    {
      "epoch": 0.2760942760942761,
      "grad_norm": 18.24834632873535,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.3287,
      "step": 41
    },
    {
      "epoch": 0.2828282828282828,
      "grad_norm": 15.68345832824707,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.7946,
      "step": 42
    },
    {
      "epoch": 0.2895622895622896,
      "grad_norm": 14.876367568969727,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.8821,
      "step": 43
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 6.82881498336792,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.4505,
      "step": 44
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 2.584322452545166,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.0999,
      "step": 45
    },
    {
      "epoch": 0.30976430976430974,
      "grad_norm": 0.8666490912437439,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.0333,
      "step": 46
    },
    {
      "epoch": 0.3164983164983165,
      "grad_norm": 0.6170616745948792,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.0107,
      "step": 47
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 5.7754292488098145,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.2646,
      "step": 48
    },
    {
      "epoch": 0.32996632996632996,
      "grad_norm": 5.182677268981934,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.326,
      "step": 49
    },
    {
      "epoch": 0.3367003367003367,
      "grad_norm": 2.9576914310455322,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.2479,
      "step": 50
    },
    {
      "epoch": 0.3367003367003367,
      "eval_loss": 0.8739397525787354,
      "eval_runtime": 18.9744,
      "eval_samples_per_second": 13.176,
      "eval_steps_per_second": 3.32,
      "step": 50
    },
    {
      "epoch": 0.3434343434343434,
      "grad_norm": 5.953899383544922,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.3218,
      "step": 51
    },
    {
      "epoch": 0.3501683501683502,
      "grad_norm": 4.58974027633667,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.3787,
      "step": 52
    },
    {
      "epoch": 0.3569023569023569,
      "grad_norm": 18.686017990112305,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.6737,
      "step": 53
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 17.43784523010254,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.4888,
      "step": 54
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 5.394166469573975,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.1968,
      "step": 55
    },
    {
      "epoch": 0.3771043771043771,
      "grad_norm": 2.398655652999878,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.0239,
      "step": 56
    },
    {
      "epoch": 0.3838383838383838,
      "grad_norm": 10.176691055297852,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.9358,
      "step": 57
    },
    {
      "epoch": 0.39057239057239057,
      "grad_norm": 23.327444076538086,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.3804,
      "step": 58
    },
    {
      "epoch": 0.39730639730639733,
      "grad_norm": 3.338932991027832,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.1873,
      "step": 59
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 1.1189355850219727,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.0452,
      "step": 60
    },
    {
      "epoch": 0.4107744107744108,
      "grad_norm": 12.247446060180664,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.6126,
      "step": 61
    },
    {
      "epoch": 0.4175084175084175,
      "grad_norm": 12.965231895446777,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.0026,
      "step": 62
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 6.692859649658203,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.4579,
      "step": 63
    },
    {
      "epoch": 0.43097643097643096,
      "grad_norm": 15.951886177062988,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.783,
      "step": 64
    },
    {
      "epoch": 0.4377104377104377,
      "grad_norm": 15.763463973999023,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.6878,
      "step": 65
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 10.72807788848877,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.8085,
      "step": 66
    },
    {
      "epoch": 0.4511784511784512,
      "grad_norm": 9.895514488220215,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.5594,
      "step": 67
    },
    {
      "epoch": 0.45791245791245794,
      "grad_norm": 12.06293773651123,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.6084,
      "step": 68
    },
    {
      "epoch": 0.46464646464646464,
      "grad_norm": 6.301954746246338,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.4009,
      "step": 69
    },
    {
      "epoch": 0.4713804713804714,
      "grad_norm": 5.985467433929443,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.3007,
      "step": 70
    },
    {
      "epoch": 0.4781144781144781,
      "grad_norm": 2.0199482440948486,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.0968,
      "step": 71
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 6.879729747772217,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.2841,
      "step": 72
    },
    {
      "epoch": 0.49158249158249157,
      "grad_norm": 20.6297664642334,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.4522,
      "step": 73
    },
    {
      "epoch": 0.4983164983164983,
      "grad_norm": 24.402189254760742,
      "learning_rate": 7.452117519152542e-05,
      "loss": 2.8895,
      "step": 74
    },
    {
      "epoch": 0.5050505050505051,
      "grad_norm": 7.097860813140869,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.8646,
      "step": 75
    },
    {
      "epoch": 0.5117845117845118,
      "grad_norm": 5.300270080566406,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.6358,
      "step": 76
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 9.244047164916992,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.763,
      "step": 77
    },
    {
      "epoch": 0.5252525252525253,
      "grad_norm": 10.318648338317871,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.9043,
      "step": 78
    },
    {
      "epoch": 0.531986531986532,
      "grad_norm": 11.570682525634766,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.888,
      "step": 79
    },
    {
      "epoch": 0.5387205387205387,
      "grad_norm": 25.91558265686035,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.6085,
      "step": 80
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 10.623796463012695,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.4522,
      "step": 81
    },
    {
      "epoch": 0.5521885521885522,
      "grad_norm": 5.795869827270508,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.1864,
      "step": 82
    },
    {
      "epoch": 0.5589225589225589,
      "grad_norm": 2.326096296310425,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.0638,
      "step": 83
    },
    {
      "epoch": 0.5656565656565656,
      "grad_norm": 3.944319486618042,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.2879,
      "step": 84
    },
    {
      "epoch": 0.5723905723905723,
      "grad_norm": 3.199124336242676,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.2697,
      "step": 85
    },
    {
      "epoch": 0.5791245791245792,
      "grad_norm": 1.5741173028945923,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.1497,
      "step": 86
    },
    {
      "epoch": 0.5858585858585859,
      "grad_norm": 2.585702419281006,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.1227,
      "step": 87
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 4.927533149719238,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.2904,
      "step": 88
    },
    {
      "epoch": 0.5993265993265994,
      "grad_norm": 26.6557674407959,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.7588,
      "step": 89
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 10.253666877746582,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.323,
      "step": 90
    },
    {
      "epoch": 0.6127946127946128,
      "grad_norm": 1.437423586845398,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.0291,
      "step": 91
    },
    {
      "epoch": 0.6195286195286195,
      "grad_norm": 4.365328311920166,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.2537,
      "step": 92
    },
    {
      "epoch": 0.6262626262626263,
      "grad_norm": 10.765714645385742,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.4309,
      "step": 93
    },
    {
      "epoch": 0.632996632996633,
      "grad_norm": 2.2685635089874268,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.0595,
      "step": 94
    },
    {
      "epoch": 0.6397306397306397,
      "grad_norm": 1.6070325374603271,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.1181,
      "step": 95
    },
    {
      "epoch": 0.6464646464646465,
      "grad_norm": 6.679049491882324,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.5612,
      "step": 96
    },
    {
      "epoch": 0.6531986531986532,
      "grad_norm": 9.408721923828125,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.6143,
      "step": 97
    },
    {
      "epoch": 0.6599326599326599,
      "grad_norm": 3.8771674633026123,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.2848,
      "step": 98
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 5.795817852020264,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.348,
      "step": 99
    },
    {
      "epoch": 0.6734006734006734,
      "grad_norm": 12.45134449005127,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.8546,
      "step": 100
    },
    {
      "epoch": 0.6734006734006734,
      "eval_loss": 0.5177435874938965,
      "eval_runtime": 18.9859,
      "eval_samples_per_second": 13.168,
      "eval_steps_per_second": 3.318,
      "step": 100
    },
    {
      "epoch": 0.6801346801346801,
      "grad_norm": 10.82240104675293,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.0345,
      "step": 101
    },
    {
      "epoch": 0.6868686868686869,
      "grad_norm": 7.96519660949707,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.7131,
      "step": 102
    },
    {
      "epoch": 0.6936026936026936,
      "grad_norm": 8.444652557373047,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.6352,
      "step": 103
    },
    {
      "epoch": 0.7003367003367004,
      "grad_norm": 7.348634243011475,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.45,
      "step": 104
    },
    {
      "epoch": 0.7070707070707071,
      "grad_norm": 6.703751087188721,
      "learning_rate": 5e-05,
      "loss": 0.4372,
      "step": 105
    },
    {
      "epoch": 0.7138047138047138,
      "grad_norm": 17.601346969604492,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.9375,
      "step": 106
    },
    {
      "epoch": 0.7205387205387206,
      "grad_norm": 6.026136875152588,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.345,
      "step": 107
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 4.048173904418945,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.241,
      "step": 108
    },
    {
      "epoch": 0.734006734006734,
      "grad_norm": 4.903576374053955,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.1662,
      "step": 109
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 5.705333709716797,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.1814,
      "step": 110
    },
    {
      "epoch": 0.7474747474747475,
      "grad_norm": 19.19615364074707,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.0645,
      "step": 111
    },
    {
      "epoch": 0.7542087542087542,
      "grad_norm": 4.758594512939453,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.224,
      "step": 112
    },
    {
      "epoch": 0.7609427609427609,
      "grad_norm": 3.704911470413208,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.1361,
      "step": 113
    },
    {
      "epoch": 0.7676767676767676,
      "grad_norm": 4.751764297485352,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.2406,
      "step": 114
    },
    {
      "epoch": 0.7744107744107744,
      "grad_norm": 10.151143074035645,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.6081,
      "step": 115
    },
    {
      "epoch": 0.7811447811447811,
      "grad_norm": 3.3288161754608154,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.0963,
      "step": 116
    },
    {
      "epoch": 0.7878787878787878,
      "grad_norm": 4.25910758972168,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.6281,
      "step": 117
    },
    {
      "epoch": 0.7946127946127947,
      "grad_norm": 6.9847211837768555,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.9259,
      "step": 118
    },
    {
      "epoch": 0.8013468013468014,
      "grad_norm": 4.942013740539551,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.5668,
      "step": 119
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 6.882447719573975,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.4911,
      "step": 120
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 8.792299270629883,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.1962,
      "step": 121
    },
    {
      "epoch": 0.8215488215488216,
      "grad_norm": 4.350340366363525,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.1922,
      "step": 122
    },
    {
      "epoch": 0.8282828282828283,
      "grad_norm": 5.087093353271484,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.1348,
      "step": 123
    },
    {
      "epoch": 0.835016835016835,
      "grad_norm": 2.8573567867279053,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0975,
      "step": 124
    },
    {
      "epoch": 0.8417508417508418,
      "grad_norm": 5.1946492195129395,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.1017,
      "step": 125
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 8.632237434387207,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.3959,
      "step": 126
    },
    {
      "epoch": 0.8552188552188552,
      "grad_norm": 11.74206829071045,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.134,
      "step": 127
    },
    {
      "epoch": 0.8619528619528619,
      "grad_norm": 20.08863067626953,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.2316,
      "step": 128
    },
    {
      "epoch": 0.8686868686868687,
      "grad_norm": 20.174644470214844,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.4492,
      "step": 129
    },
    {
      "epoch": 0.8754208754208754,
      "grad_norm": 4.945806503295898,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.1764,
      "step": 130
    },
    {
      "epoch": 0.8821548821548821,
      "grad_norm": 12.166462898254395,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.5486,
      "step": 131
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 7.911715030670166,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.222,
      "step": 132
    },
    {
      "epoch": 0.8956228956228957,
      "grad_norm": 0.9088268876075745,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.0581,
      "step": 133
    },
    {
      "epoch": 0.9023569023569024,
      "grad_norm": 2.8902766704559326,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.1729,
      "step": 134
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 4.079202175140381,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.2658,
      "step": 135
    },
    {
      "epoch": 0.9158249158249159,
      "grad_norm": 2.5197372436523438,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.1391,
      "step": 136
    },
    {
      "epoch": 0.9225589225589226,
      "grad_norm": 5.427261829376221,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.2419,
      "step": 137
    },
    {
      "epoch": 0.9292929292929293,
      "grad_norm": 14.229353904724121,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.5891,
      "step": 138
    },
    {
      "epoch": 0.936026936026936,
      "grad_norm": 5.965293884277344,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.3071,
      "step": 139
    },
    {
      "epoch": 0.9427609427609428,
      "grad_norm": 5.0351033210754395,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.5023,
      "step": 140
    },
    {
      "epoch": 0.9494949494949495,
      "grad_norm": 6.387707710266113,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.558,
      "step": 141
    },
    {
      "epoch": 0.9562289562289562,
      "grad_norm": 2.2307064533233643,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.2544,
      "step": 142
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 3.933332920074463,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.2604,
      "step": 143
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 3.44079327583313,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.1672,
      "step": 144
    },
    {
      "epoch": 0.9764309764309764,
      "grad_norm": 2.185455799102783,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.1181,
      "step": 145
    },
    {
      "epoch": 0.9831649831649831,
      "grad_norm": 2.50177264213562,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.0992,
      "step": 146
    },
    {
      "epoch": 0.98989898989899,
      "grad_norm": 1.1756283044815063,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.0627,
      "step": 147
    },
    {
      "epoch": 0.9966329966329966,
      "grad_norm": 6.326255798339844,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.5571,
      "step": 148
    },
    {
      "epoch": 1.005050505050505,
      "grad_norm": 2.855851888656616,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.1974,
      "step": 149
    },
    {
      "epoch": 1.0117845117845117,
      "grad_norm": 4.803467750549316,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.0497,
      "step": 150
    },
    {
      "epoch": 1.0117845117845117,
      "eval_loss": 0.18108560144901276,
      "eval_runtime": 18.9819,
      "eval_samples_per_second": 13.17,
      "eval_steps_per_second": 3.319,
      "step": 150
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.262770368118784e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}