{
  "best_metric": 0.6930665969848633,
  "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": 0.449655681848526,
      "learning_rate": 1e-05,
      "loss": 0.8695,
      "step": 1
    },
    {
      "epoch": 0.0005621135469364812,
      "eval_loss": 0.9304347634315491,
      "eval_runtime": 152.0097,
      "eval_samples_per_second": 19.716,
      "eval_steps_per_second": 4.934,
      "step": 1
    },
    {
      "epoch": 0.0011242270938729624,
      "grad_norm": 0.5023356080055237,
      "learning_rate": 2e-05,
      "loss": 0.8821,
      "step": 2
    },
    {
      "epoch": 0.0016863406408094434,
      "grad_norm": 0.46654871106147766,
      "learning_rate": 3e-05,
      "loss": 0.832,
      "step": 3
    },
    {
      "epoch": 0.0022484541877459247,
      "grad_norm": 0.4256797730922699,
      "learning_rate": 4e-05,
      "loss": 0.9229,
      "step": 4
    },
    {
      "epoch": 0.002810567734682406,
      "grad_norm": 0.3425302803516388,
      "learning_rate": 5e-05,
      "loss": 0.8384,
      "step": 5
    },
    {
      "epoch": 0.003372681281618887,
      "grad_norm": 0.3166348338127136,
      "learning_rate": 6e-05,
      "loss": 0.8376,
      "step": 6
    },
    {
      "epoch": 0.0039347948285553686,
      "grad_norm": 0.3200496435165405,
      "learning_rate": 7e-05,
      "loss": 0.7849,
      "step": 7
    },
    {
      "epoch": 0.004496908375491849,
      "grad_norm": 0.3059157431125641,
      "learning_rate": 8e-05,
      "loss": 0.6981,
      "step": 8
    },
    {
      "epoch": 0.00505902192242833,
      "grad_norm": 0.3440568149089813,
      "learning_rate": 9e-05,
      "loss": 0.8787,
      "step": 9
    },
    {
      "epoch": 0.005621135469364812,
      "grad_norm": 0.2907848060131073,
      "learning_rate": 0.0001,
      "loss": 0.7491,
      "step": 10
    },
    {
      "epoch": 0.006183249016301293,
      "grad_norm": 0.27447807788848877,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.8138,
      "step": 11
    },
    {
      "epoch": 0.006745362563237774,
      "grad_norm": 0.26786839962005615,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.8122,
      "step": 12
    },
    {
      "epoch": 0.007307476110174255,
      "grad_norm": 0.24878999590873718,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.7189,
      "step": 13
    },
    {
      "epoch": 0.007869589657110737,
      "grad_norm": 0.2382345348596573,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.6952,
      "step": 14
    },
    {
      "epoch": 0.008431703204047217,
      "grad_norm": 0.2620311677455902,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.8115,
      "step": 15
    },
    {
      "epoch": 0.008993816750983699,
      "grad_norm": 0.24003832042217255,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.7422,
      "step": 16
    },
    {
      "epoch": 0.00955593029792018,
      "grad_norm": 0.22492513060569763,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.7292,
      "step": 17
    },
    {
      "epoch": 0.01011804384485666,
      "grad_norm": 0.23531891405582428,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.7661,
      "step": 18
    },
    {
      "epoch": 0.010680157391793142,
      "grad_norm": 0.23544137179851532,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.7771,
      "step": 19
    },
    {
      "epoch": 0.011242270938729624,
      "grad_norm": 0.2348058670759201,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.6644,
      "step": 20
    },
    {
      "epoch": 0.011804384485666104,
      "grad_norm": 0.22824856638908386,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.7761,
      "step": 21
    },
    {
      "epoch": 0.012366498032602586,
      "grad_norm": 0.24772630631923676,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.8046,
      "step": 22
    },
    {
      "epoch": 0.012928611579539067,
      "grad_norm": 0.2400537133216858,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.7292,
      "step": 23
    },
    {
      "epoch": 0.013490725126475547,
      "grad_norm": 0.23345544934272766,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.692,
      "step": 24
    },
    {
      "epoch": 0.014052838673412029,
      "grad_norm": 0.2513226568698883,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.7507,
      "step": 25
    },
    {
      "epoch": 0.01461495222034851,
      "grad_norm": 0.2558189034461975,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.7479,
      "step": 26
    },
    {
      "epoch": 0.01517706576728499,
      "grad_norm": 0.2522766888141632,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.8997,
      "step": 27
    },
    {
      "epoch": 0.015739179314221474,
      "grad_norm": 0.2469606250524521,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.8191,
      "step": 28
    },
    {
      "epoch": 0.016301292861157952,
      "grad_norm": 0.23547065258026123,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.6997,
      "step": 29
    },
    {
      "epoch": 0.016863406408094434,
      "grad_norm": 0.2420210987329483,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.7514,
      "step": 30
    },
    {
      "epoch": 0.017425519955030916,
      "grad_norm": 0.24130995571613312,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.6844,
      "step": 31
    },
    {
      "epoch": 0.017987633501967398,
      "grad_norm": 0.25418171286582947,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.7961,
      "step": 32
    },
    {
      "epoch": 0.01854974704890388,
      "grad_norm": 0.2484334260225296,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.7189,
      "step": 33
    },
    {
      "epoch": 0.01911186059584036,
      "grad_norm": 0.24717803299427032,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.7269,
      "step": 34
    },
    {
      "epoch": 0.01967397414277684,
      "grad_norm": 0.25569289922714233,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.7147,
      "step": 35
    },
    {
      "epoch": 0.02023608768971332,
      "grad_norm": 0.26822730898857117,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.8485,
      "step": 36
    },
    {
      "epoch": 0.020798201236649803,
      "grad_norm": 0.2532746195793152,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.7367,
      "step": 37
    },
    {
      "epoch": 0.021360314783586284,
      "grad_norm": 0.25245583057403564,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.7264,
      "step": 38
    },
    {
      "epoch": 0.021922428330522766,
      "grad_norm": 0.2603718638420105,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.7419,
      "step": 39
    },
    {
      "epoch": 0.022484541877459248,
      "grad_norm": 0.2641009986400604,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.7735,
      "step": 40
    },
    {
      "epoch": 0.02304665542439573,
      "grad_norm": 0.27816465497016907,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.7441,
      "step": 41
    },
    {
      "epoch": 0.023608768971332208,
      "grad_norm": 0.2899934649467468,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.7451,
      "step": 42
    },
    {
      "epoch": 0.02417088251826869,
      "grad_norm": 0.29349198937416077,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.638,
      "step": 43
    },
    {
      "epoch": 0.02473299606520517,
      "grad_norm": 0.3182656466960907,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.7343,
      "step": 44
    },
    {
      "epoch": 0.025295109612141653,
      "grad_norm": 0.31128615140914917,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.6523,
      "step": 45
    },
    {
      "epoch": 0.025857223159078135,
      "grad_norm": 0.3211795687675476,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.6658,
      "step": 46
    },
    {
      "epoch": 0.026419336706014616,
      "grad_norm": 0.3387065529823303,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.8223,
      "step": 47
    },
    {
      "epoch": 0.026981450252951095,
      "grad_norm": 0.4117791950702667,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8557,
      "step": 48
    },
    {
      "epoch": 0.027543563799887576,
      "grad_norm": 0.43003883957862854,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.8476,
      "step": 49
    },
    {
      "epoch": 0.028105677346824058,
      "grad_norm": 0.5390227437019348,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.9311,
      "step": 50
    },
    {
      "epoch": 0.028105677346824058,
      "eval_loss": 0.7394875884056091,
      "eval_runtime": 152.6153,
      "eval_samples_per_second": 19.638,
      "eval_steps_per_second": 4.914,
      "step": 50
    },
    {
      "epoch": 0.02866779089376054,
      "grad_norm": 0.328805536031723,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.7461,
      "step": 51
    },
    {
      "epoch": 0.02922990444069702,
      "grad_norm": 0.33998236060142517,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.868,
      "step": 52
    },
    {
      "epoch": 0.029792017987633503,
      "grad_norm": 0.2628476917743683,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.7035,
      "step": 53
    },
    {
      "epoch": 0.03035413153456998,
      "grad_norm": 0.2293473780155182,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.7382,
      "step": 54
    },
    {
      "epoch": 0.030916245081506463,
      "grad_norm": 0.22472500801086426,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.7453,
      "step": 55
    },
    {
      "epoch": 0.03147835862844295,
      "grad_norm": 0.20862101018428802,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.6398,
      "step": 56
    },
    {
      "epoch": 0.03204047217537943,
      "grad_norm": 0.21950207650661469,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.7376,
      "step": 57
    },
    {
      "epoch": 0.032602585722315905,
      "grad_norm": 0.22642666101455688,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.6904,
      "step": 58
    },
    {
      "epoch": 0.03316469926925239,
      "grad_norm": 0.2184956967830658,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.6677,
      "step": 59
    },
    {
      "epoch": 0.03372681281618887,
      "grad_norm": 0.2059151977300644,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.6943,
      "step": 60
    },
    {
      "epoch": 0.034288926363125354,
      "grad_norm": 0.20753073692321777,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.7104,
      "step": 61
    },
    {
      "epoch": 0.03485103991006183,
      "grad_norm": 0.20797058939933777,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.7273,
      "step": 62
    },
    {
      "epoch": 0.03541315345699832,
      "grad_norm": 0.2004324048757553,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.621,
      "step": 63
    },
    {
      "epoch": 0.035975267003934795,
      "grad_norm": 0.2056368589401245,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.6748,
      "step": 64
    },
    {
      "epoch": 0.03653738055087127,
      "grad_norm": 0.20332691073417664,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.7194,
      "step": 65
    },
    {
      "epoch": 0.03709949409780776,
      "grad_norm": 0.21475742757320404,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.7574,
      "step": 66
    },
    {
      "epoch": 0.03766160764474424,
      "grad_norm": 0.21810247004032135,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.736,
      "step": 67
    },
    {
      "epoch": 0.03822372119168072,
      "grad_norm": 0.2109690010547638,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.735,
      "step": 68
    },
    {
      "epoch": 0.0387858347386172,
      "grad_norm": 0.21837064623832703,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.7252,
      "step": 69
    },
    {
      "epoch": 0.03934794828555368,
      "grad_norm": 0.20757514238357544,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.728,
      "step": 70
    },
    {
      "epoch": 0.039910061832490164,
      "grad_norm": 0.21207264065742493,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.7625,
      "step": 71
    },
    {
      "epoch": 0.04047217537942664,
      "grad_norm": 0.20816613733768463,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.7204,
      "step": 72
    },
    {
      "epoch": 0.04103428892636313,
      "grad_norm": 0.21276846528053284,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.7226,
      "step": 73
    },
    {
      "epoch": 0.041596402473299605,
      "grad_norm": 0.21693867444992065,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.7129,
      "step": 74
    },
    {
      "epoch": 0.04215851602023609,
      "grad_norm": 0.21719211339950562,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.731,
      "step": 75
    },
    {
      "epoch": 0.04272062956717257,
      "grad_norm": 0.2159098982810974,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.695,
      "step": 76
    },
    {
      "epoch": 0.04328274311410905,
      "grad_norm": 0.21332460641860962,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.7161,
      "step": 77
    },
    {
      "epoch": 0.04384485666104553,
      "grad_norm": 0.22994939982891083,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.754,
      "step": 78
    },
    {
      "epoch": 0.04440697020798201,
      "grad_norm": 0.22945700585842133,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.7042,
      "step": 79
    },
    {
      "epoch": 0.044969083754918496,
      "grad_norm": 0.23664583265781403,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.7297,
      "step": 80
    },
    {
      "epoch": 0.045531197301854974,
      "grad_norm": 0.23979917168617249,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7108,
      "step": 81
    },
    {
      "epoch": 0.04609331084879146,
      "grad_norm": 0.23731853067874908,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.7092,
      "step": 82
    },
    {
      "epoch": 0.04665542439572794,
      "grad_norm": 0.23034045100212097,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.6778,
      "step": 83
    },
    {
      "epoch": 0.047217537942664416,
      "grad_norm": 0.23124980926513672,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.7142,
      "step": 84
    },
    {
      "epoch": 0.0477796514896009,
      "grad_norm": 0.22591619193553925,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.6442,
      "step": 85
    },
    {
      "epoch": 0.04834176503653738,
      "grad_norm": 0.2527121901512146,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.811,
      "step": 86
    },
    {
      "epoch": 0.048903878583473864,
      "grad_norm": 0.2379622459411621,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.6786,
      "step": 87
    },
    {
      "epoch": 0.04946599213041034,
      "grad_norm": 0.2407558411359787,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.7249,
      "step": 88
    },
    {
      "epoch": 0.05002810567734682,
      "grad_norm": 0.25664445757865906,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.6669,
      "step": 89
    },
    {
      "epoch": 0.050590219224283306,
      "grad_norm": 0.2580859959125519,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.6994,
      "step": 90
    },
    {
      "epoch": 0.051152332771219784,
      "grad_norm": 0.25966179370880127,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.7234,
      "step": 91
    },
    {
      "epoch": 0.05171444631815627,
      "grad_norm": 0.27060139179229736,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.613,
      "step": 92
    },
    {
      "epoch": 0.05227655986509275,
      "grad_norm": 0.26522526144981384,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.6309,
      "step": 93
    },
    {
      "epoch": 0.05283867341202923,
      "grad_norm": 0.2706226408481598,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.6742,
      "step": 94
    },
    {
      "epoch": 0.05340078695896571,
      "grad_norm": 0.30376970767974854,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.7692,
      "step": 95
    },
    {
      "epoch": 0.05396290050590219,
      "grad_norm": 0.31754347681999207,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.646,
      "step": 96
    },
    {
      "epoch": 0.054525014052838675,
      "grad_norm": 0.3306269943714142,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.7368,
      "step": 97
    },
    {
      "epoch": 0.05508712759977515,
      "grad_norm": 0.34835872054100037,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.6777,
      "step": 98
    },
    {
      "epoch": 0.05564924114671164,
      "grad_norm": 0.3743361234664917,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.6904,
      "step": 99
    },
    {
      "epoch": 0.056211354693648116,
      "grad_norm": 0.5413866639137268,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.8674,
      "step": 100
    },
    {
      "epoch": 0.056211354693648116,
      "eval_loss": 0.7103737592697144,
      "eval_runtime": 152.8241,
      "eval_samples_per_second": 19.611,
      "eval_steps_per_second": 4.908,
      "step": 100
    },
    {
      "epoch": 0.0567734682405846,
      "grad_norm": 0.2531059682369232,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.7374,
      "step": 101
    },
    {
      "epoch": 0.05733558178752108,
      "grad_norm": 0.23978598415851593,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.6552,
      "step": 102
    },
    {
      "epoch": 0.05789769533445756,
      "grad_norm": 0.2574896812438965,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.7747,
      "step": 103
    },
    {
      "epoch": 0.05845980888139404,
      "grad_norm": 0.23103006184101105,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.7304,
      "step": 104
    },
    {
      "epoch": 0.05902192242833052,
      "grad_norm": 0.2309071272611618,
      "learning_rate": 5e-05,
      "loss": 0.7275,
      "step": 105
    },
    {
      "epoch": 0.059584035975267007,
      "grad_norm": 0.21041204035282135,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.6609,
      "step": 106
    },
    {
      "epoch": 0.060146149522203485,
      "grad_norm": 0.2023843675851822,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.6624,
      "step": 107
    },
    {
      "epoch": 0.06070826306913996,
      "grad_norm": 0.20038451254367828,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.657,
      "step": 108
    },
    {
      "epoch": 0.06127037661607645,
      "grad_norm": 0.19799694418907166,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.673,
      "step": 109
    },
    {
      "epoch": 0.061832490163012926,
      "grad_norm": 0.203295037150383,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.66,
      "step": 110
    },
    {
      "epoch": 0.06239460370994941,
      "grad_norm": 0.19961732625961304,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.7261,
      "step": 111
    },
    {
      "epoch": 0.0629567172568859,
      "grad_norm": 0.20259259641170502,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.6855,
      "step": 112
    },
    {
      "epoch": 0.06351883080382237,
      "grad_norm": 0.2183270901441574,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.761,
      "step": 113
    },
    {
      "epoch": 0.06408094435075885,
      "grad_norm": 0.21282760798931122,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.6757,
      "step": 114
    },
    {
      "epoch": 0.06464305789769534,
      "grad_norm": 0.224282905459404,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.6913,
      "step": 115
    },
    {
      "epoch": 0.06520517144463181,
      "grad_norm": 0.2110433131456375,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.6718,
      "step": 116
    },
    {
      "epoch": 0.0657672849915683,
      "grad_norm": 0.21849676966667175,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.7287,
      "step": 117
    },
    {
      "epoch": 0.06632939853850478,
      "grad_norm": 0.22007882595062256,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.724,
      "step": 118
    },
    {
      "epoch": 0.06689151208544127,
      "grad_norm": 0.21841686964035034,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.7396,
      "step": 119
    },
    {
      "epoch": 0.06745362563237774,
      "grad_norm": 0.2120630294084549,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.7256,
      "step": 120
    },
    {
      "epoch": 0.06801573917931422,
      "grad_norm": 0.21770359575748444,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.6908,
      "step": 121
    },
    {
      "epoch": 0.06857785272625071,
      "grad_norm": 0.2096286565065384,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.6797,
      "step": 122
    },
    {
      "epoch": 0.06913996627318718,
      "grad_norm": 0.23203186690807343,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.7569,
      "step": 123
    },
    {
      "epoch": 0.06970207982012366,
      "grad_norm": 0.2251289188861847,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.758,
      "step": 124
    },
    {
      "epoch": 0.07026419336706015,
      "grad_norm": 0.21812288463115692,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.7121,
      "step": 125
    },
    {
      "epoch": 0.07082630691399663,
      "grad_norm": 0.21730251610279083,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.662,
      "step": 126
    },
    {
      "epoch": 0.0713884204609331,
      "grad_norm": 0.2211391180753708,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.7042,
      "step": 127
    },
    {
      "epoch": 0.07195053400786959,
      "grad_norm": 0.22021818161010742,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.6553,
      "step": 128
    },
    {
      "epoch": 0.07251264755480608,
      "grad_norm": 0.22702684998512268,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.7279,
      "step": 129
    },
    {
      "epoch": 0.07307476110174255,
      "grad_norm": 0.23390822112560272,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.7774,
      "step": 130
    },
    {
      "epoch": 0.07363687464867903,
      "grad_norm": 0.22979716956615448,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.7008,
      "step": 131
    },
    {
      "epoch": 0.07419898819561552,
      "grad_norm": 0.23003248870372772,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.7106,
      "step": 132
    },
    {
      "epoch": 0.07476110174255199,
      "grad_norm": 0.23892056941986084,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.7207,
      "step": 133
    },
    {
      "epoch": 0.07532321528948847,
      "grad_norm": 0.23476751148700714,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.7305,
      "step": 134
    },
    {
      "epoch": 0.07588532883642496,
      "grad_norm": 0.2423548549413681,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.6914,
      "step": 135
    },
    {
      "epoch": 0.07644744238336144,
      "grad_norm": 0.24808691442012787,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.7278,
      "step": 136
    },
    {
      "epoch": 0.07700955593029792,
      "grad_norm": 0.24975475668907166,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.7155,
      "step": 137
    },
    {
      "epoch": 0.0775716694772344,
      "grad_norm": 0.25328946113586426,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.7462,
      "step": 138
    },
    {
      "epoch": 0.07813378302417089,
      "grad_norm": 0.2595827579498291,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.7338,
      "step": 139
    },
    {
      "epoch": 0.07869589657110736,
      "grad_norm": 0.25283992290496826,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.6471,
      "step": 140
    },
    {
      "epoch": 0.07925801011804384,
      "grad_norm": 0.2585476040840149,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.7207,
      "step": 141
    },
    {
      "epoch": 0.07982012366498033,
      "grad_norm": 0.2651914954185486,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.6792,
      "step": 142
    },
    {
      "epoch": 0.08038223721191681,
      "grad_norm": 0.27403396368026733,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6848,
      "step": 143
    },
    {
      "epoch": 0.08094435075885328,
      "grad_norm": 0.2739570140838623,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.68,
      "step": 144
    },
    {
      "epoch": 0.08150646430578977,
      "grad_norm": 0.2819446325302124,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.6061,
      "step": 145
    },
    {
      "epoch": 0.08206857785272625,
      "grad_norm": 0.292952299118042,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.7049,
      "step": 146
    },
    {
      "epoch": 0.08263069139966273,
      "grad_norm": 0.32052895426750183,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.7227,
      "step": 147
    },
    {
      "epoch": 0.08319280494659921,
      "grad_norm": 0.3396679162979126,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.7174,
      "step": 148
    },
    {
      "epoch": 0.0837549184935357,
      "grad_norm": 0.34895652532577515,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.6836,
      "step": 149
    },
    {
      "epoch": 0.08431703204047218,
      "grad_norm": 0.43249768018722534,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.7647,
      "step": 150
    },
    {
      "epoch": 0.08431703204047218,
      "eval_loss": 0.6958631873130798,
      "eval_runtime": 152.889,
      "eval_samples_per_second": 19.602,
      "eval_steps_per_second": 4.906,
      "step": 150
    },
    {
      "epoch": 0.08487914558740865,
      "grad_norm": 0.21268592774868011,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.6601,
      "step": 151
    },
    {
      "epoch": 0.08544125913434514,
      "grad_norm": 0.2208387553691864,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.7372,
      "step": 152
    },
    {
      "epoch": 0.08600337268128162,
      "grad_norm": 0.22172459959983826,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.7209,
      "step": 153
    },
    {
      "epoch": 0.0865654862282181,
      "grad_norm": 0.2252526432275772,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.731,
      "step": 154
    },
    {
      "epoch": 0.08712759977515458,
      "grad_norm": 0.231217160820961,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.7922,
      "step": 155
    },
    {
      "epoch": 0.08768971332209106,
      "grad_norm": 0.21610644459724426,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.7132,
      "step": 156
    },
    {
      "epoch": 0.08825182686902755,
      "grad_norm": 0.19697825610637665,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.6307,
      "step": 157
    },
    {
      "epoch": 0.08881394041596402,
      "grad_norm": 0.20948463678359985,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.7262,
      "step": 158
    },
    {
      "epoch": 0.0893760539629005,
      "grad_norm": 0.22446687519550323,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.8578,
      "step": 159
    },
    {
      "epoch": 0.08993816750983699,
      "grad_norm": 0.20389561355113983,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.6874,
      "step": 160
    },
    {
      "epoch": 0.09050028105677346,
      "grad_norm": 0.20349334180355072,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.6439,
      "step": 161
    },
    {
      "epoch": 0.09106239460370995,
      "grad_norm": 0.21147523820400238,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7151,
      "step": 162
    },
    {
      "epoch": 0.09162450815064643,
      "grad_norm": 0.20206283032894135,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.6667,
      "step": 163
    },
    {
      "epoch": 0.09218662169758292,
      "grad_norm": 0.2018386870622635,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.668,
      "step": 164
    },
    {
      "epoch": 0.09274873524451939,
      "grad_norm": 0.21122212707996368,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.679,
      "step": 165
    },
    {
      "epoch": 0.09331084879145587,
      "grad_norm": 0.21643470227718353,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.7184,
      "step": 166
    },
    {
      "epoch": 0.09387296233839236,
      "grad_norm": 0.2142067402601242,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.7695,
      "step": 167
    },
    {
      "epoch": 0.09443507588532883,
      "grad_norm": 0.22435177862644196,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.7396,
      "step": 168
    },
    {
      "epoch": 0.09499718943226532,
      "grad_norm": 0.20659403502941132,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.6683,
      "step": 169
    },
    {
      "epoch": 0.0955593029792018,
      "grad_norm": 0.20291151106357574,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.6294,
      "step": 170
    },
    {
      "epoch": 0.09612141652613827,
      "grad_norm": 0.2253389060497284,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.7105,
      "step": 171
    },
    {
      "epoch": 0.09668353007307476,
      "grad_norm": 0.20599496364593506,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.6837,
      "step": 172
    },
    {
      "epoch": 0.09724564362001124,
      "grad_norm": 0.21565525233745575,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.702,
      "step": 173
    },
    {
      "epoch": 0.09780775716694773,
      "grad_norm": 0.23385106027126312,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.7862,
      "step": 174
    },
    {
      "epoch": 0.0983698707138842,
      "grad_norm": 0.22500307857990265,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.6952,
      "step": 175
    },
    {
      "epoch": 0.09893198426082069,
      "grad_norm": 0.2215053141117096,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.6837,
      "step": 176
    },
    {
      "epoch": 0.09949409780775717,
      "grad_norm": 0.24003835022449493,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.7232,
      "step": 177
    },
    {
      "epoch": 0.10005621135469364,
      "grad_norm": 0.22238196432590485,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.6508,
      "step": 178
    },
    {
      "epoch": 0.10061832490163013,
      "grad_norm": 0.215393528342247,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.6523,
      "step": 179
    },
    {
      "epoch": 0.10118043844856661,
      "grad_norm": 0.24164272844791412,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.6992,
      "step": 180
    },
    {
      "epoch": 0.1017425519955031,
      "grad_norm": 0.23435017466545105,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.6724,
      "step": 181
    },
    {
      "epoch": 0.10230466554243957,
      "grad_norm": 0.22970615327358246,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.648,
      "step": 182
    },
    {
      "epoch": 0.10286677908937605,
      "grad_norm": 0.24069124460220337,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.7261,
      "step": 183
    },
    {
      "epoch": 0.10342889263631254,
      "grad_norm": 0.24915184080600739,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.77,
      "step": 184
    },
    {
      "epoch": 0.10399100618324901,
      "grad_norm": 0.23197710514068604,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.6192,
      "step": 185
    },
    {
      "epoch": 0.1045531197301855,
      "grad_norm": 0.24410854279994965,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.63,
      "step": 186
    },
    {
      "epoch": 0.10511523327712198,
      "grad_norm": 0.25532543659210205,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.788,
      "step": 187
    },
    {
      "epoch": 0.10567734682405847,
      "grad_norm": 0.24810117483139038,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.6942,
      "step": 188
    },
    {
      "epoch": 0.10623946037099494,
      "grad_norm": 0.2653409242630005,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.7018,
      "step": 189
    },
    {
      "epoch": 0.10680157391793142,
      "grad_norm": 0.25742265582084656,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.6796,
      "step": 190
    },
    {
      "epoch": 0.10736368746486791,
      "grad_norm": 0.25677254796028137,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.6252,
      "step": 191
    },
    {
      "epoch": 0.10792580101180438,
      "grad_norm": 0.2767215073108673,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.732,
      "step": 192
    },
    {
      "epoch": 0.10848791455874086,
      "grad_norm": 0.2799105942249298,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.6345,
      "step": 193
    },
    {
      "epoch": 0.10905002810567735,
      "grad_norm": 0.29010868072509766,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.6767,
      "step": 194
    },
    {
      "epoch": 0.10961214165261383,
      "grad_norm": 0.30900588631629944,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.6983,
      "step": 195
    },
    {
      "epoch": 0.1101742551995503,
      "grad_norm": 0.3021150827407837,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.6724,
      "step": 196
    },
    {
      "epoch": 0.11073636874648679,
      "grad_norm": 0.33853858709335327,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.6607,
      "step": 197
    },
    {
      "epoch": 0.11129848229342328,
      "grad_norm": 0.3432128429412842,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.686,
      "step": 198
    },
    {
      "epoch": 0.11186059584035975,
      "grad_norm": 0.39094990491867065,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.8275,
      "step": 199
    },
    {
      "epoch": 0.11242270938729623,
      "grad_norm": 0.5228344202041626,
      "learning_rate": 0.0,
      "loss": 0.6829,
      "step": 200
    },
    {
      "epoch": 0.11242270938729623,
      "eval_loss": 0.6930665969848633,
      "eval_runtime": 153.2308,
      "eval_samples_per_second": 19.559,
      "eval_steps_per_second": 4.895,
      "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
}