{
  "best_metric": 0.6931376457214355,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.11242270938729623,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005621135469364812,
      "grad_norm": 0.4462641477584839,
      "learning_rate": 1e-05,
      "loss": 0.8695,
      "step": 1
    },
    {
      "epoch": 0.0005621135469364812,
      "eval_loss": 0.9304347634315491,
      "eval_runtime": 152.8782,
      "eval_samples_per_second": 19.604,
      "eval_steps_per_second": 4.906,
      "step": 1
    },
    {
      "epoch": 0.0011242270938729624,
      "grad_norm": 0.4966641962528229,
      "learning_rate": 2e-05,
      "loss": 0.8821,
      "step": 2
    },
    {
      "epoch": 0.0016863406408094434,
      "grad_norm": 0.4642832577228546,
      "learning_rate": 3e-05,
      "loss": 0.8318,
      "step": 3
    },
    {
      "epoch": 0.0022484541877459247,
      "grad_norm": 0.4215812683105469,
      "learning_rate": 4e-05,
      "loss": 0.9229,
      "step": 4
    },
    {
      "epoch": 0.002810567734682406,
      "grad_norm": 0.3394550085067749,
      "learning_rate": 5e-05,
      "loss": 0.8387,
      "step": 5
    },
    {
      "epoch": 0.003372681281618887,
      "grad_norm": 0.3142542839050293,
      "learning_rate": 6e-05,
      "loss": 0.8377,
      "step": 6
    },
    {
      "epoch": 0.0039347948285553686,
      "grad_norm": 0.31795454025268555,
      "learning_rate": 7e-05,
      "loss": 0.7851,
      "step": 7
    },
    {
      "epoch": 0.004496908375491849,
      "grad_norm": 0.3021998107433319,
      "learning_rate": 8e-05,
      "loss": 0.6981,
      "step": 8
    },
    {
      "epoch": 0.00505902192242833,
      "grad_norm": 0.34148478507995605,
      "learning_rate": 9e-05,
      "loss": 0.8783,
      "step": 9
    },
    {
      "epoch": 0.005621135469364812,
      "grad_norm": 0.28774145245552063,
      "learning_rate": 0.0001,
      "loss": 0.749,
      "step": 10
    },
    {
      "epoch": 0.006183249016301293,
      "grad_norm": 0.2732573449611664,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.8135,
      "step": 11
    },
    {
      "epoch": 0.006745362563237774,
      "grad_norm": 0.2660185694694519,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.8121,
      "step": 12
    },
    {
      "epoch": 0.007307476110174255,
      "grad_norm": 0.24798351526260376,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.7186,
      "step": 13
    },
    {
      "epoch": 0.007869589657110737,
      "grad_norm": 0.23619535565376282,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.6955,
      "step": 14
    },
    {
      "epoch": 0.008431703204047217,
      "grad_norm": 0.2606937885284424,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.8111,
      "step": 15
    },
    {
      "epoch": 0.008993816750983699,
      "grad_norm": 0.23904958367347717,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.7415,
      "step": 16
    },
    {
      "epoch": 0.00955593029792018,
      "grad_norm": 0.224972665309906,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.7289,
      "step": 17
    },
    {
      "epoch": 0.01011804384485666,
      "grad_norm": 0.2341756969690323,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.7664,
      "step": 18
    },
    {
      "epoch": 0.010680157391793142,
      "grad_norm": 0.23427802324295044,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.777,
      "step": 19
    },
    {
      "epoch": 0.011242270938729624,
      "grad_norm": 0.23395201563835144,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.6645,
      "step": 20
    },
    {
      "epoch": 0.011804384485666104,
      "grad_norm": 0.22882209718227386,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.7765,
      "step": 21
    },
    {
      "epoch": 0.012366498032602586,
      "grad_norm": 0.24740347266197205,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.8041,
      "step": 22
    },
    {
      "epoch": 0.012928611579539067,
      "grad_norm": 0.23894909024238586,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.7296,
      "step": 23
    },
    {
      "epoch": 0.013490725126475547,
      "grad_norm": 0.2319473773241043,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.6918,
      "step": 24
    },
    {
      "epoch": 0.014052838673412029,
      "grad_norm": 0.24976247549057007,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.7509,
      "step": 25
    },
    {
      "epoch": 0.01461495222034851,
      "grad_norm": 0.25387611985206604,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.7479,
      "step": 26
    },
    {
      "epoch": 0.01517706576728499,
      "grad_norm": 0.25057706236839294,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.8992,
      "step": 27
    },
    {
      "epoch": 0.015739179314221474,
      "grad_norm": 0.24653461575508118,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.8189,
      "step": 28
    },
    {
      "epoch": 0.016301292861157952,
      "grad_norm": 0.23226606845855713,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.6996,
      "step": 29
    },
    {
      "epoch": 0.016863406408094434,
      "grad_norm": 0.24168235063552856,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.7524,
      "step": 30
    },
    {
      "epoch": 0.017425519955030916,
      "grad_norm": 0.24114258587360382,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.6848,
      "step": 31
    },
    {
      "epoch": 0.017987633501967398,
      "grad_norm": 0.2529737949371338,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.7956,
      "step": 32
    },
    {
      "epoch": 0.01854974704890388,
      "grad_norm": 0.2458229809999466,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.7187,
      "step": 33
    },
    {
      "epoch": 0.01911186059584036,
      "grad_norm": 0.24641719460487366,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.727,
      "step": 34
    },
    {
      "epoch": 0.01967397414277684,
      "grad_norm": 0.2536425292491913,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.7149,
      "step": 35
    },
    {
      "epoch": 0.02023608768971332,
      "grad_norm": 0.2676127552986145,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.8486,
      "step": 36
    },
    {
      "epoch": 0.020798201236649803,
      "grad_norm": 0.2531084418296814,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.7364,
      "step": 37
    },
    {
      "epoch": 0.021360314783586284,
      "grad_norm": 0.2523763179779053,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.7262,
      "step": 38
    },
    {
      "epoch": 0.021922428330522766,
      "grad_norm": 0.2602189779281616,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.7425,
      "step": 39
    },
    {
      "epoch": 0.022484541877459248,
      "grad_norm": 0.262887179851532,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.7743,
      "step": 40
    },
    {
      "epoch": 0.02304665542439573,
      "grad_norm": 0.27744829654693604,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.744,
      "step": 41
    },
    {
      "epoch": 0.023608768971332208,
      "grad_norm": 0.28950393199920654,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.7458,
      "step": 42
    },
    {
      "epoch": 0.02417088251826869,
      "grad_norm": 0.29417434334754944,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.6386,
      "step": 43
    },
    {
      "epoch": 0.02473299606520517,
      "grad_norm": 0.3165974020957947,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.7344,
      "step": 44
    },
    {
      "epoch": 0.025295109612141653,
      "grad_norm": 0.3100324869155884,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.6518,
      "step": 45
    },
    {
      "epoch": 0.025857223159078135,
      "grad_norm": 0.31941431760787964,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.6657,
      "step": 46
    },
    {
      "epoch": 0.026419336706014616,
      "grad_norm": 0.3361773192882538,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.8227,
      "step": 47
    },
    {
      "epoch": 0.026981450252951095,
      "grad_norm": 0.4094504117965698,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8563,
      "step": 48
    },
    {
      "epoch": 0.027543563799887576,
      "grad_norm": 0.4309692680835724,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.848,
      "step": 49
    },
    {
      "epoch": 0.028105677346824058,
      "grad_norm": 0.5381000638008118,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.9305,
      "step": 50
    },
    {
      "epoch": 0.028105677346824058,
      "eval_loss": 0.7394219040870667,
      "eval_runtime": 153.5501,
      "eval_samples_per_second": 19.518,
      "eval_steps_per_second": 4.884,
      "step": 50
    },
    {
      "epoch": 0.02866779089376054,
      "grad_norm": 0.3238924443721771,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.7456,
      "step": 51
    },
    {
      "epoch": 0.02922990444069702,
      "grad_norm": 0.33645787835121155,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.868,
      "step": 52
    },
    {
      "epoch": 0.029792017987633503,
      "grad_norm": 0.2600613236427307,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.7027,
      "step": 53
    },
    {
      "epoch": 0.03035413153456998,
      "grad_norm": 0.22714689373970032,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.7382,
      "step": 54
    },
    {
      "epoch": 0.030916245081506463,
      "grad_norm": 0.22327734529972076,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.7457,
      "step": 55
    },
    {
      "epoch": 0.03147835862844295,
      "grad_norm": 0.20763379335403442,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.6401,
      "step": 56
    },
    {
      "epoch": 0.03204047217537943,
      "grad_norm": 0.21818415820598602,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.7375,
      "step": 57
    },
    {
      "epoch": 0.032602585722315905,
      "grad_norm": 0.22508615255355835,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.6904,
      "step": 58
    },
    {
      "epoch": 0.03316469926925239,
      "grad_norm": 0.21768085658550262,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.6676,
      "step": 59
    },
    {
      "epoch": 0.03372681281618887,
      "grad_norm": 0.2046968787908554,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.6939,
      "step": 60
    },
    {
      "epoch": 0.034288926363125354,
      "grad_norm": 0.206581711769104,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.7102,
      "step": 61
    },
    {
      "epoch": 0.03485103991006183,
      "grad_norm": 0.2068776935338974,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.7275,
      "step": 62
    },
    {
      "epoch": 0.03541315345699832,
      "grad_norm": 0.19978730380535126,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.6208,
      "step": 63
    },
    {
      "epoch": 0.035975267003934795,
      "grad_norm": 0.2066263109445572,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.6757,
      "step": 64
    },
    {
      "epoch": 0.03653738055087127,
      "grad_norm": 0.20205795764923096,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.7198,
      "step": 65
    },
    {
      "epoch": 0.03709949409780776,
      "grad_norm": 0.21334125101566315,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.7575,
      "step": 66
    },
    {
      "epoch": 0.03766160764474424,
      "grad_norm": 0.21765801310539246,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.736,
      "step": 67
    },
    {
      "epoch": 0.03822372119168072,
      "grad_norm": 0.21035075187683105,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.7355,
      "step": 68
    },
    {
      "epoch": 0.0387858347386172,
      "grad_norm": 0.2173381745815277,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.726,
      "step": 69
    },
    {
      "epoch": 0.03934794828555368,
      "grad_norm": 0.20702363550662994,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.7282,
      "step": 70
    },
    {
      "epoch": 0.039910061832490164,
      "grad_norm": 0.2116130143404007,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.7629,
      "step": 71
    },
    {
      "epoch": 0.04047217537942664,
      "grad_norm": 0.20880624651908875,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.7201,
      "step": 72
    },
    {
      "epoch": 0.04103428892636313,
      "grad_norm": 0.21248884499073029,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.7228,
      "step": 73
    },
    {
      "epoch": 0.041596402473299605,
      "grad_norm": 0.21593786776065826,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.7126,
      "step": 74
    },
    {
      "epoch": 0.04215851602023609,
      "grad_norm": 0.21736711263656616,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.7311,
      "step": 75
    },
    {
      "epoch": 0.04272062956717257,
      "grad_norm": 0.2159949243068695,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.6953,
      "step": 76
    },
    {
      "epoch": 0.04328274311410905,
      "grad_norm": 0.21280749142169952,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.7162,
      "step": 77
    },
    {
      "epoch": 0.04384485666104553,
      "grad_norm": 0.2282567173242569,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.7542,
      "step": 78
    },
    {
      "epoch": 0.04440697020798201,
      "grad_norm": 0.2286519706249237,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.7036,
      "step": 79
    },
    {
      "epoch": 0.044969083754918496,
      "grad_norm": 0.2355959266424179,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.7293,
      "step": 80
    },
    {
      "epoch": 0.045531197301854974,
      "grad_norm": 0.23940454423427582,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7111,
      "step": 81
    },
    {
      "epoch": 0.04609331084879146,
      "grad_norm": 0.23693278431892395,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.7084,
      "step": 82
    },
    {
      "epoch": 0.04665542439572794,
      "grad_norm": 0.2305186539888382,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.678,
      "step": 83
    },
    {
      "epoch": 0.047217537942664416,
      "grad_norm": 0.23121798038482666,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.7146,
      "step": 84
    },
    {
      "epoch": 0.0477796514896009,
      "grad_norm": 0.22582241892814636,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.644,
      "step": 85
    },
    {
      "epoch": 0.04834176503653738,
      "grad_norm": 0.2523897588253021,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8116,
      "step": 86
    },
    {
      "epoch": 0.048903878583473864,
      "grad_norm": 0.23738685250282288,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.6794,
      "step": 87
    },
    {
      "epoch": 0.04946599213041034,
      "grad_norm": 0.24177047610282898,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.7249,
      "step": 88
    },
    {
      "epoch": 0.05002810567734682,
      "grad_norm": 0.25494056940078735,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.6669,
      "step": 89
    },
    {
      "epoch": 0.050590219224283306,
      "grad_norm": 0.25937730073928833,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.6994,
      "step": 90
    },
    {
      "epoch": 0.051152332771219784,
      "grad_norm": 0.25830528140068054,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.7231,
      "step": 91
    },
    {
      "epoch": 0.05171444631815627,
      "grad_norm": 0.27011650800704956,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.6136,
      "step": 92
    },
    {
      "epoch": 0.05227655986509275,
      "grad_norm": 0.2645992040634155,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.6306,
      "step": 93
    },
    {
      "epoch": 0.05283867341202923,
      "grad_norm": 0.27044710516929626,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.6751,
      "step": 94
    },
    {
      "epoch": 0.05340078695896571,
      "grad_norm": 0.3029738664627075,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.7697,
      "step": 95
    },
    {
      "epoch": 0.05396290050590219,
      "grad_norm": 0.3133673667907715,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.6462,
      "step": 96
    },
    {
      "epoch": 0.054525014052838675,
      "grad_norm": 0.32998842000961304,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.7367,
      "step": 97
    },
    {
      "epoch": 0.05508712759977515,
      "grad_norm": 0.3464261293411255,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.6787,
      "step": 98
    },
    {
      "epoch": 0.05564924114671164,
      "grad_norm": 0.3732531666755676,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.691,
      "step": 99
    },
    {
      "epoch": 0.056211354693648116,
      "grad_norm": 0.5396194458007812,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.8679,
      "step": 100
    },
    {
      "epoch": 0.056211354693648116,
      "eval_loss": 0.7106400728225708,
      "eval_runtime": 153.5192,
      "eval_samples_per_second": 19.522,
      "eval_steps_per_second": 4.885,
      "step": 100
    },
    {
      "epoch": 0.0567734682405846,
      "grad_norm": 0.25219881534576416,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.7376,
      "step": 101
    },
    {
      "epoch": 0.05733558178752108,
      "grad_norm": 0.23978988826274872,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.6557,
      "step": 102
    },
    {
      "epoch": 0.05789769533445756,
      "grad_norm": 0.25832971930503845,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.7746,
      "step": 103
    },
    {
      "epoch": 0.05845980888139404,
      "grad_norm": 0.2306554764509201,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.7309,
      "step": 104
    },
    {
      "epoch": 0.05902192242833052,
      "grad_norm": 0.23142923414707184,
      "learning_rate": 5e-05,
      "loss": 0.7269,
      "step": 105
    },
    {
      "epoch": 0.059584035975267007,
      "grad_norm": 0.2094535231590271,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.6608,
      "step": 106
    },
    {
      "epoch": 0.060146149522203485,
      "grad_norm": 0.20212790369987488,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.663,
      "step": 107
    },
    {
      "epoch": 0.06070826306913996,
      "grad_norm": 0.20047086477279663,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.6567,
      "step": 108
    },
    {
      "epoch": 0.06127037661607645,
      "grad_norm": 0.1974254548549652,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.6729,
      "step": 109
    },
    {
      "epoch": 0.061832490163012926,
      "grad_norm": 0.20390832424163818,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.6601,
      "step": 110
    },
    {
      "epoch": 0.06239460370994941,
      "grad_norm": 0.19846083223819733,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.726,
      "step": 111
    },
    {
      "epoch": 0.0629567172568859,
      "grad_norm": 0.2027653455734253,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.6859,
      "step": 112
    },
    {
      "epoch": 0.06351883080382237,
      "grad_norm": 0.23045727610588074,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.761,
      "step": 113
    },
    {
      "epoch": 0.06408094435075885,
      "grad_norm": 0.21308928728103638,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.6768,
      "step": 114
    },
    {
      "epoch": 0.06464305789769534,
      "grad_norm": 0.223859503865242,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.6919,
      "step": 115
    },
    {
      "epoch": 0.06520517144463181,
      "grad_norm": 0.21096834540367126,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.6719,
      "step": 116
    },
    {
      "epoch": 0.0657672849915683,
      "grad_norm": 0.21819078922271729,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.7287,
      "step": 117
    },
    {
      "epoch": 0.06632939853850478,
      "grad_norm": 0.22057586908340454,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.7245,
      "step": 118
    },
    {
      "epoch": 0.06689151208544127,
      "grad_norm": 0.2194376438856125,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.7402,
      "step": 119
    },
    {
      "epoch": 0.06745362563237774,
      "grad_norm": 0.21218986809253693,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.7249,
      "step": 120
    },
    {
      "epoch": 0.06801573917931422,
      "grad_norm": 0.21695610880851746,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.6909,
      "step": 121
    },
    {
      "epoch": 0.06857785272625071,
      "grad_norm": 0.2092410922050476,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.6797,
      "step": 122
    },
    {
      "epoch": 0.06913996627318718,
      "grad_norm": 0.23209603130817413,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.758,
      "step": 123
    },
    {
      "epoch": 0.06970207982012366,
      "grad_norm": 0.2241065353155136,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.758,
      "step": 124
    },
    {
      "epoch": 0.07026419336706015,
      "grad_norm": 0.2176084816455841,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.7124,
      "step": 125
    },
    {
      "epoch": 0.07082630691399663,
      "grad_norm": 0.21726448833942413,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.6623,
      "step": 126
    },
    {
      "epoch": 0.0713884204609331,
      "grad_norm": 0.22122825682163239,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.704,
      "step": 127
    },
    {
      "epoch": 0.07195053400786959,
      "grad_norm": 0.22026145458221436,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.6553,
      "step": 128
    },
    {
      "epoch": 0.07251264755480608,
      "grad_norm": 0.22657331824302673,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.7277,
      "step": 129
    },
    {
      "epoch": 0.07307476110174255,
      "grad_norm": 0.23302213847637177,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.7764,
      "step": 130
    },
    {
      "epoch": 0.07363687464867903,
      "grad_norm": 0.22964607179164886,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.7003,
      "step": 131
    },
    {
      "epoch": 0.07419898819561552,
      "grad_norm": 0.23007339239120483,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.7108,
      "step": 132
    },
    {
      "epoch": 0.07476110174255199,
      "grad_norm": 0.23773565888404846,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.7214,
      "step": 133
    },
    {
      "epoch": 0.07532321528948847,
      "grad_norm": 0.23461517691612244,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.7306,
      "step": 134
    },
    {
      "epoch": 0.07588532883642496,
      "grad_norm": 0.24239563941955566,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.6907,
      "step": 135
    },
    {
      "epoch": 0.07644744238336144,
      "grad_norm": 0.24784526228904724,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.7281,
      "step": 136
    },
    {
      "epoch": 0.07700955593029792,
      "grad_norm": 0.24869398772716522,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.7153,
      "step": 137
    },
    {
      "epoch": 0.0775716694772344,
      "grad_norm": 0.25245699286460876,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.7461,
      "step": 138
    },
    {
      "epoch": 0.07813378302417089,
      "grad_norm": 0.25910723209381104,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.7329,
      "step": 139
    },
    {
      "epoch": 0.07869589657110736,
      "grad_norm": 0.25259318947792053,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.647,
      "step": 140
    },
    {
      "epoch": 0.07925801011804384,
      "grad_norm": 0.2578543424606323,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.7205,
      "step": 141
    },
    {
      "epoch": 0.07982012366498033,
      "grad_norm": 0.2650565505027771,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.6793,
      "step": 142
    },
    {
      "epoch": 0.08038223721191681,
      "grad_norm": 0.2742520272731781,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.684,
      "step": 143
    },
    {
      "epoch": 0.08094435075885328,
      "grad_norm": 0.272744745016098,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.6809,
      "step": 144
    },
    {
      "epoch": 0.08150646430578977,
      "grad_norm": 0.2816363573074341,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.6062,
      "step": 145
    },
    {
      "epoch": 0.08206857785272625,
      "grad_norm": 0.2931676208972931,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.7059,
      "step": 146
    },
    {
      "epoch": 0.08263069139966273,
      "grad_norm": 0.3188605010509491,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.7238,
      "step": 147
    },
    {
      "epoch": 0.08319280494659921,
      "grad_norm": 0.3395642936229706,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.7183,
      "step": 148
    },
    {
      "epoch": 0.0837549184935357,
      "grad_norm": 0.34683701395988464,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.6822,
      "step": 149
    },
    {
      "epoch": 0.08431703204047218,
      "grad_norm": 0.43051016330718994,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.7637,
      "step": 150
    },
    {
      "epoch": 0.08431703204047218,
      "eval_loss": 0.695939838886261,
      "eval_runtime": 153.7065,
      "eval_samples_per_second": 19.498,
      "eval_steps_per_second": 4.879,
      "step": 150
    },
    {
      "epoch": 0.08487914558740865,
      "grad_norm": 0.2130131870508194,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.6602,
      "step": 151
    },
    {
      "epoch": 0.08544125913434514,
      "grad_norm": 0.22044633328914642,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.7375,
      "step": 152
    },
    {
      "epoch": 0.08600337268128162,
      "grad_norm": 0.22082433104515076,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.7209,
      "step": 153
    },
    {
      "epoch": 0.0865654862282181,
      "grad_norm": 0.22511936724185944,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.7309,
      "step": 154
    },
    {
      "epoch": 0.08712759977515458,
      "grad_norm": 0.2308863252401352,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.7923,
      "step": 155
    },
    {
      "epoch": 0.08768971332209106,
      "grad_norm": 0.21585489809513092,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.7136,
      "step": 156
    },
    {
      "epoch": 0.08825182686902755,
      "grad_norm": 0.1969076246023178,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.6307,
      "step": 157
    },
    {
      "epoch": 0.08881394041596402,
      "grad_norm": 0.20867222547531128,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.7262,
      "step": 158
    },
    {
      "epoch": 0.0893760539629005,
      "grad_norm": 0.2237229198217392,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.8582,
      "step": 159
    },
    {
      "epoch": 0.08993816750983699,
      "grad_norm": 0.20306715369224548,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.6869,
      "step": 160
    },
    {
      "epoch": 0.09050028105677346,
      "grad_norm": 0.20422999560832977,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.6442,
      "step": 161
    },
    {
      "epoch": 0.09106239460370995,
      "grad_norm": 0.2120133638381958,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7157,
      "step": 162
    },
    {
      "epoch": 0.09162450815064643,
      "grad_norm": 0.20366635918617249,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.667,
      "step": 163
    },
    {
      "epoch": 0.09218662169758292,
      "grad_norm": 0.20207980275154114,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.668,
      "step": 164
    },
    {
      "epoch": 0.09274873524451939,
      "grad_norm": 0.21069107949733734,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.6796,
      "step": 165
    },
    {
      "epoch": 0.09331084879145587,
      "grad_norm": 0.2175239622592926,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.7184,
      "step": 166
    },
    {
      "epoch": 0.09387296233839236,
      "grad_norm": 0.21470816433429718,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.7699,
      "step": 167
    },
    {
      "epoch": 0.09443507588532883,
      "grad_norm": 0.22422847151756287,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.7401,
      "step": 168
    },
    {
      "epoch": 0.09499718943226532,
      "grad_norm": 0.20559588074684143,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.6683,
      "step": 169
    },
    {
      "epoch": 0.0955593029792018,
      "grad_norm": 0.2030762881040573,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.6298,
      "step": 170
    },
    {
      "epoch": 0.09612141652613827,
      "grad_norm": 0.2249382585287094,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.7109,
      "step": 171
    },
    {
      "epoch": 0.09668353007307476,
      "grad_norm": 0.20573142170906067,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.6841,
      "step": 172
    },
    {
      "epoch": 0.09724564362001124,
      "grad_norm": 0.21552424132823944,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.7023,
      "step": 173
    },
    {
      "epoch": 0.09780775716694773,
      "grad_norm": 0.23321565985679626,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.7863,
      "step": 174
    },
    {
      "epoch": 0.0983698707138842,
      "grad_norm": 0.22396357357501984,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.6949,
      "step": 175
    },
    {
      "epoch": 0.09893198426082069,
      "grad_norm": 0.221019446849823,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.6837,
      "step": 176
    },
    {
      "epoch": 0.09949409780775717,
      "grad_norm": 0.23884433507919312,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.7241,
      "step": 177
    },
    {
      "epoch": 0.10005621135469364,
      "grad_norm": 0.22143976390361786,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.6508,
      "step": 178
    },
    {
      "epoch": 0.10061832490163013,
      "grad_norm": 0.21537278592586517,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.6533,
      "step": 179
    },
    {
      "epoch": 0.10118043844856661,
      "grad_norm": 0.2413482517004013,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.6989,
      "step": 180
    },
    {
      "epoch": 0.1017425519955031,
      "grad_norm": 0.2332078218460083,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.6716,
      "step": 181
    },
    {
      "epoch": 0.10230466554243957,
      "grad_norm": 0.23012611269950867,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.6486,
      "step": 182
    },
    {
      "epoch": 0.10286677908937605,
      "grad_norm": 0.24042926728725433,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.7261,
      "step": 183
    },
    {
      "epoch": 0.10342889263631254,
      "grad_norm": 0.24805034697055817,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.7689,
      "step": 184
    },
    {
      "epoch": 0.10399100618324901,
      "grad_norm": 0.23157480359077454,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.6196,
      "step": 185
    },
    {
      "epoch": 0.1045531197301855,
      "grad_norm": 0.24432821571826935,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.63,
      "step": 186
    },
    {
      "epoch": 0.10511523327712198,
      "grad_norm": 0.25453731417655945,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.7884,
      "step": 187
    },
    {
      "epoch": 0.10567734682405847,
      "grad_norm": 0.24758335947990417,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.6942,
      "step": 188
    },
    {
      "epoch": 0.10623946037099494,
      "grad_norm": 0.2643246352672577,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.7022,
      "step": 189
    },
    {
      "epoch": 0.10680157391793142,
      "grad_norm": 0.2577090561389923,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.6797,
      "step": 190
    },
    {
      "epoch": 0.10736368746486791,
      "grad_norm": 0.2560056447982788,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.6244,
      "step": 191
    },
    {
      "epoch": 0.10792580101180438,
      "grad_norm": 0.275604248046875,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.7325,
      "step": 192
    },
    {
      "epoch": 0.10848791455874086,
      "grad_norm": 0.28054916858673096,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.6345,
      "step": 193
    },
    {
      "epoch": 0.10905002810567735,
      "grad_norm": 0.28916385769844055,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.6774,
      "step": 194
    },
    {
      "epoch": 0.10961214165261383,
      "grad_norm": 0.3085208535194397,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.6975,
      "step": 195
    },
    {
      "epoch": 0.1101742551995503,
      "grad_norm": 0.3017449975013733,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.6729,
      "step": 196
    },
    {
      "epoch": 0.11073636874648679,
      "grad_norm": 0.33686646819114685,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.6607,
      "step": 197
    },
    {
      "epoch": 0.11129848229342328,
      "grad_norm": 0.34082940220832825,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.6851,
      "step": 198
    },
    {
      "epoch": 0.11186059584035975,
      "grad_norm": 0.38982468843460083,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.8287,
      "step": 199
    },
    {
      "epoch": 0.11242270938729623,
      "grad_norm": 0.5186094641685486,
      "learning_rate": 0.0,
      "loss": 0.6823,
      "step": 200
    },
    {
      "epoch": 0.11242270938729623,
      "eval_loss": 0.6931376457214355,
      "eval_runtime": 153.9477,
      "eval_samples_per_second": 19.468,
      "eval_steps_per_second": 4.872,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.545476428791808e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}