{
  "best_metric": 11.918663024902344,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.08523332623055614,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004261666311527807,
      "grad_norm": 0.010783566161990166,
      "learning_rate": 1e-05,
      "loss": 11.9333,
      "step": 1
    },
    {
      "epoch": 0.0004261666311527807,
      "eval_loss": 11.932735443115234,
      "eval_runtime": 19.889,
      "eval_samples_per_second": 198.703,
      "eval_steps_per_second": 49.676,
      "step": 1
    },
    {
      "epoch": 0.0008523332623055614,
      "grad_norm": 0.01525061298161745,
      "learning_rate": 2e-05,
      "loss": 11.9324,
      "step": 2
    },
    {
      "epoch": 0.0012784998934583422,
      "grad_norm": 0.013187172822654247,
      "learning_rate": 3e-05,
      "loss": 11.9335,
      "step": 3
    },
    {
      "epoch": 0.0017046665246111229,
      "grad_norm": 0.013145486824214458,
      "learning_rate": 4e-05,
      "loss": 11.9339,
      "step": 4
    },
    {
      "epoch": 0.002130833155763904,
      "grad_norm": 0.011725656688213348,
      "learning_rate": 5e-05,
      "loss": 11.9345,
      "step": 5
    },
    {
      "epoch": 0.0025569997869166845,
      "grad_norm": 0.01819816790521145,
      "learning_rate": 6e-05,
      "loss": 11.932,
      "step": 6
    },
    {
      "epoch": 0.002983166418069465,
      "grad_norm": 0.014085367321968079,
      "learning_rate": 7e-05,
      "loss": 11.9337,
      "step": 7
    },
    {
      "epoch": 0.0034093330492222457,
      "grad_norm": 0.016248401254415512,
      "learning_rate": 8e-05,
      "loss": 11.9334,
      "step": 8
    },
    {
      "epoch": 0.0038354996803750267,
      "grad_norm": 0.016225440427660942,
      "learning_rate": 9e-05,
      "loss": 11.9319,
      "step": 9
    },
    {
      "epoch": 0.004261666311527808,
      "grad_norm": 0.015917429700493813,
      "learning_rate": 0.0001,
      "loss": 11.9329,
      "step": 10
    },
    {
      "epoch": 0.004687832942680588,
      "grad_norm": 0.016813913360238075,
      "learning_rate": 9.999316524962345e-05,
      "loss": 11.933,
      "step": 11
    },
    {
      "epoch": 0.005113999573833369,
      "grad_norm": 0.021408552303910255,
      "learning_rate": 9.997266286704631e-05,
      "loss": 11.9332,
      "step": 12
    },
    {
      "epoch": 0.00554016620498615,
      "grad_norm": 0.02441178262233734,
      "learning_rate": 9.993849845741524e-05,
      "loss": 11.9313,
      "step": 13
    },
    {
      "epoch": 0.00596633283613893,
      "grad_norm": 0.027301784604787827,
      "learning_rate": 9.989068136093873e-05,
      "loss": 11.9315,
      "step": 14
    },
    {
      "epoch": 0.006392499467291711,
      "grad_norm": 0.02429843135178089,
      "learning_rate": 9.98292246503335e-05,
      "loss": 11.9339,
      "step": 15
    },
    {
      "epoch": 0.006818666098444491,
      "grad_norm": 0.02345540001988411,
      "learning_rate": 9.975414512725057e-05,
      "loss": 11.9353,
      "step": 16
    },
    {
      "epoch": 0.007244832729597273,
      "grad_norm": 0.029322655871510506,
      "learning_rate": 9.966546331768191e-05,
      "loss": 11.9339,
      "step": 17
    },
    {
      "epoch": 0.0076709993607500535,
      "grad_norm": 0.040709082037210464,
      "learning_rate": 9.956320346634876e-05,
      "loss": 11.9309,
      "step": 18
    },
    {
      "epoch": 0.008097165991902834,
      "grad_norm": 0.04418151453137398,
      "learning_rate": 9.944739353007344e-05,
      "loss": 11.9298,
      "step": 19
    },
    {
      "epoch": 0.008523332623055616,
      "grad_norm": 0.048950254917144775,
      "learning_rate": 9.931806517013612e-05,
      "loss": 11.9332,
      "step": 20
    },
    {
      "epoch": 0.008949499254208395,
      "grad_norm": 0.047790639102458954,
      "learning_rate": 9.917525374361912e-05,
      "loss": 11.9331,
      "step": 21
    },
    {
      "epoch": 0.009375665885361177,
      "grad_norm": 0.04140250012278557,
      "learning_rate": 9.901899829374047e-05,
      "loss": 11.9326,
      "step": 22
    },
    {
      "epoch": 0.009801832516513957,
      "grad_norm": 0.052673064172267914,
      "learning_rate": 9.884934153917997e-05,
      "loss": 11.9291,
      "step": 23
    },
    {
      "epoch": 0.010227999147666738,
      "grad_norm": 0.05368907004594803,
      "learning_rate": 9.86663298624003e-05,
      "loss": 11.9327,
      "step": 24
    },
    {
      "epoch": 0.010654165778819518,
      "grad_norm": 0.07620558887720108,
      "learning_rate": 9.847001329696653e-05,
      "loss": 11.9301,
      "step": 25
    },
    {
      "epoch": 0.0110803324099723,
      "grad_norm": 0.06529633700847626,
      "learning_rate": 9.826044551386744e-05,
      "loss": 11.9302,
      "step": 26
    },
    {
      "epoch": 0.01150649904112508,
      "grad_norm": 0.0779736265540123,
      "learning_rate": 9.803768380684242e-05,
      "loss": 11.9268,
      "step": 27
    },
    {
      "epoch": 0.01193266567227786,
      "grad_norm": 0.08377201110124588,
      "learning_rate": 9.780178907671789e-05,
      "loss": 11.9313,
      "step": 28
    },
    {
      "epoch": 0.012358832303430642,
      "grad_norm": 0.07553629577159882,
      "learning_rate": 9.755282581475769e-05,
      "loss": 11.9281,
      "step": 29
    },
    {
      "epoch": 0.012784998934583422,
      "grad_norm": 0.10072767734527588,
      "learning_rate": 9.729086208503174e-05,
      "loss": 11.9296,
      "step": 30
    },
    {
      "epoch": 0.013211165565736203,
      "grad_norm": 0.07085242122411728,
      "learning_rate": 9.701596950580806e-05,
      "loss": 11.9294,
      "step": 31
    },
    {
      "epoch": 0.013637332196888983,
      "grad_norm": 0.11301127076148987,
      "learning_rate": 9.672822322997305e-05,
      "loss": 11.9276,
      "step": 32
    },
    {
      "epoch": 0.014063498828041764,
      "grad_norm": 0.10090602189302444,
      "learning_rate": 9.642770192448536e-05,
      "loss": 11.9301,
      "step": 33
    },
    {
      "epoch": 0.014489665459194546,
      "grad_norm": 0.09605599194765091,
      "learning_rate": 9.611448774886924e-05,
      "loss": 11.9299,
      "step": 34
    },
    {
      "epoch": 0.014915832090347326,
      "grad_norm": 0.112775519490242,
      "learning_rate": 9.578866633275288e-05,
      "loss": 11.924,
      "step": 35
    },
    {
      "epoch": 0.015341998721500107,
      "grad_norm": 0.128156378865242,
      "learning_rate": 9.545032675245813e-05,
      "loss": 11.9261,
      "step": 36
    },
    {
      "epoch": 0.015768165352652887,
      "grad_norm": 0.11732214689254761,
      "learning_rate": 9.509956150664796e-05,
      "loss": 11.9265,
      "step": 37
    },
    {
      "epoch": 0.016194331983805668,
      "grad_norm": 0.14842940866947174,
      "learning_rate": 9.473646649103818e-05,
      "loss": 11.9251,
      "step": 38
    },
    {
      "epoch": 0.01662049861495845,
      "grad_norm": 0.11704577505588531,
      "learning_rate": 9.43611409721806e-05,
      "loss": 11.924,
      "step": 39
    },
    {
      "epoch": 0.01704666524611123,
      "grad_norm": 0.114938884973526,
      "learning_rate": 9.397368756032445e-05,
      "loss": 11.9213,
      "step": 40
    },
    {
      "epoch": 0.01747283187726401,
      "grad_norm": 0.12612271308898926,
      "learning_rate": 9.357421218136386e-05,
      "loss": 11.9197,
      "step": 41
    },
    {
      "epoch": 0.01789899850841679,
      "grad_norm": 0.10184342414140701,
      "learning_rate": 9.316282404787871e-05,
      "loss": 11.9227,
      "step": 42
    },
    {
      "epoch": 0.018325165139569572,
      "grad_norm": 0.1259440779685974,
      "learning_rate": 9.273963562927695e-05,
      "loss": 11.9176,
      "step": 43
    },
    {
      "epoch": 0.018751331770722354,
      "grad_norm": 0.08236672729253769,
      "learning_rate": 9.230476262104677e-05,
      "loss": 11.9204,
      "step": 44
    },
    {
      "epoch": 0.01917749840187513,
      "grad_norm": 0.10719214379787445,
      "learning_rate": 9.185832391312644e-05,
      "loss": 11.9212,
      "step": 45
    },
    {
      "epoch": 0.019603665033027913,
      "grad_norm": 0.08748386800289154,
      "learning_rate": 9.140044155740101e-05,
      "loss": 11.921,
      "step": 46
    },
    {
      "epoch": 0.020029831664180694,
      "grad_norm": 0.0807666927576065,
      "learning_rate": 9.093124073433463e-05,
      "loss": 11.9181,
      "step": 47
    },
    {
      "epoch": 0.020455998295333476,
      "grad_norm": 0.07043169438838959,
      "learning_rate": 9.045084971874738e-05,
      "loss": 11.9173,
      "step": 48
    },
    {
      "epoch": 0.020882164926486257,
      "grad_norm": 0.08117137849330902,
      "learning_rate": 8.995939984474624e-05,
      "loss": 11.9203,
      "step": 49
    },
    {
      "epoch": 0.021308331557639035,
      "grad_norm": 0.0718555673956871,
      "learning_rate": 8.945702546981969e-05,
      "loss": 11.9179,
      "step": 50
    },
    {
      "epoch": 0.021308331557639035,
      "eval_loss": 11.92057991027832,
      "eval_runtime": 19.8524,
      "eval_samples_per_second": 199.069,
      "eval_steps_per_second": 49.767,
      "step": 50
    },
    {
      "epoch": 0.021734498188791817,
      "grad_norm": 0.06575246900320053,
      "learning_rate": 8.894386393810563e-05,
      "loss": 11.9226,
      "step": 51
    },
    {
      "epoch": 0.0221606648199446,
      "grad_norm": 0.05350646376609802,
      "learning_rate": 8.842005554284296e-05,
      "loss": 11.9232,
      "step": 52
    },
    {
      "epoch": 0.02258683145109738,
      "grad_norm": 0.06506114453077316,
      "learning_rate": 8.788574348801675e-05,
      "loss": 11.9247,
      "step": 53
    },
    {
      "epoch": 0.02301299808225016,
      "grad_norm": 0.057568348944187164,
      "learning_rate": 8.73410738492077e-05,
      "loss": 11.9228,
      "step": 54
    },
    {
      "epoch": 0.02343916471340294,
      "grad_norm": 0.039165034890174866,
      "learning_rate": 8.678619553365659e-05,
      "loss": 11.9238,
      "step": 55
    },
    {
      "epoch": 0.02386533134455572,
      "grad_norm": 0.056112293154001236,
      "learning_rate": 8.622126023955446e-05,
      "loss": 11.9215,
      "step": 56
    },
    {
      "epoch": 0.024291497975708502,
      "grad_norm": 0.05309688672423363,
      "learning_rate": 8.564642241456986e-05,
      "loss": 11.9218,
      "step": 57
    },
    {
      "epoch": 0.024717664606861284,
      "grad_norm": 0.048616014420986176,
      "learning_rate": 8.506183921362443e-05,
      "loss": 11.9219,
      "step": 58
    },
    {
      "epoch": 0.025143831238014065,
      "grad_norm": 0.04642653837800026,
      "learning_rate": 8.44676704559283e-05,
      "loss": 11.9233,
      "step": 59
    },
    {
      "epoch": 0.025569997869166843,
      "grad_norm": 0.036669518798589706,
      "learning_rate": 8.386407858128706e-05,
      "loss": 11.923,
      "step": 60
    },
    {
      "epoch": 0.025996164500319625,
      "grad_norm": 0.047157276421785355,
      "learning_rate": 8.32512286056924e-05,
      "loss": 11.9248,
      "step": 61
    },
    {
      "epoch": 0.026422331131472406,
      "grad_norm": 0.0599622018635273,
      "learning_rate": 8.262928807620843e-05,
      "loss": 11.9243,
      "step": 62
    },
    {
      "epoch": 0.026848497762625188,
      "grad_norm": 0.04673381894826889,
      "learning_rate": 8.199842702516583e-05,
      "loss": 11.9219,
      "step": 63
    },
    {
      "epoch": 0.027274664393777966,
      "grad_norm": 0.06018264219164848,
      "learning_rate": 8.135881792367686e-05,
      "loss": 11.9191,
      "step": 64
    },
    {
      "epoch": 0.027700831024930747,
      "grad_norm": 0.05312344431877136,
      "learning_rate": 8.07106356344834e-05,
      "loss": 11.9222,
      "step": 65
    },
    {
      "epoch": 0.02812699765608353,
      "grad_norm": 0.03183679282665253,
      "learning_rate": 8.005405736415126e-05,
      "loss": 11.9188,
      "step": 66
    },
    {
      "epoch": 0.02855316428723631,
      "grad_norm": 0.050023071467876434,
      "learning_rate": 7.938926261462366e-05,
      "loss": 11.9218,
      "step": 67
    },
    {
      "epoch": 0.02897933091838909,
      "grad_norm": 0.02788991667330265,
      "learning_rate": 7.871643313414718e-05,
      "loss": 11.9193,
      "step": 68
    },
    {
      "epoch": 0.02940549754954187,
      "grad_norm": 0.02796361781656742,
      "learning_rate": 7.803575286758364e-05,
      "loss": 11.9179,
      "step": 69
    },
    {
      "epoch": 0.02983166418069465,
      "grad_norm": 0.057033803313970566,
      "learning_rate": 7.734740790612136e-05,
      "loss": 11.9194,
      "step": 70
    },
    {
      "epoch": 0.030257830811847432,
      "grad_norm": 0.04260317608714104,
      "learning_rate": 7.66515864363997e-05,
      "loss": 11.9191,
      "step": 71
    },
    {
      "epoch": 0.030683997443000214,
      "grad_norm": 0.03333442658185959,
      "learning_rate": 7.594847868906076e-05,
      "loss": 11.9164,
      "step": 72
    },
    {
      "epoch": 0.031110164074152995,
      "grad_norm": 0.0197952501475811,
      "learning_rate": 7.52382768867422e-05,
      "loss": 11.9194,
      "step": 73
    },
    {
      "epoch": 0.03153633070530577,
      "grad_norm": 0.045446738600730896,
      "learning_rate": 7.452117519152542e-05,
      "loss": 11.9188,
      "step": 74
    },
    {
      "epoch": 0.031962497336458555,
      "grad_norm": 0.046279408037662506,
      "learning_rate": 7.379736965185368e-05,
      "loss": 11.9182,
      "step": 75
    },
    {
      "epoch": 0.032388663967611336,
      "grad_norm": 0.03939951956272125,
      "learning_rate": 7.30670581489344e-05,
      "loss": 11.9187,
      "step": 76
    },
    {
      "epoch": 0.03281483059876412,
      "grad_norm": 0.041478779166936874,
      "learning_rate": 7.233044034264034e-05,
      "loss": 11.9191,
      "step": 77
    },
    {
      "epoch": 0.0332409972299169,
      "grad_norm": 0.035528745502233505,
      "learning_rate": 7.158771761692464e-05,
      "loss": 11.9194,
      "step": 78
    },
    {
      "epoch": 0.03366716386106968,
      "grad_norm": 0.041090380400419235,
      "learning_rate": 7.083909302476453e-05,
      "loss": 11.918,
      "step": 79
    },
    {
      "epoch": 0.03409333049222246,
      "grad_norm": 0.05140626057982445,
      "learning_rate": 7.008477123264848e-05,
      "loss": 11.9191,
      "step": 80
    },
    {
      "epoch": 0.03451949712337524,
      "grad_norm": 0.04735744744539261,
      "learning_rate": 6.932495846462261e-05,
      "loss": 11.9232,
      "step": 81
    },
    {
      "epoch": 0.03494566375452802,
      "grad_norm": 0.05660935118794441,
      "learning_rate": 6.855986244591104e-05,
      "loss": 11.9188,
      "step": 82
    },
    {
      "epoch": 0.0353718303856808,
      "grad_norm": 0.04198070615530014,
      "learning_rate": 6.778969234612584e-05,
      "loss": 11.9171,
      "step": 83
    },
    {
      "epoch": 0.03579799701683358,
      "grad_norm": 0.04368012398481369,
      "learning_rate": 6.701465872208216e-05,
      "loss": 11.9202,
      "step": 84
    },
    {
      "epoch": 0.03622416364798636,
      "grad_norm": 0.04552308842539787,
      "learning_rate": 6.623497346023418e-05,
      "loss": 11.9161,
      "step": 85
    },
    {
      "epoch": 0.036650330279139144,
      "grad_norm": 0.04900360107421875,
      "learning_rate": 6.545084971874738e-05,
      "loss": 11.9196,
      "step": 86
    },
    {
      "epoch": 0.037076496910291926,
      "grad_norm": 0.03567694500088692,
      "learning_rate": 6.466250186922325e-05,
      "loss": 11.9191,
      "step": 87
    },
    {
      "epoch": 0.03750266354144471,
      "grad_norm": 0.06178225949406624,
      "learning_rate": 6.387014543809223e-05,
      "loss": 11.9184,
      "step": 88
    },
    {
      "epoch": 0.03792883017259749,
      "grad_norm": 0.04395047575235367,
      "learning_rate": 6.307399704769099e-05,
      "loss": 11.9179,
      "step": 89
    },
    {
      "epoch": 0.03835499680375026,
      "grad_norm": 0.03420117869973183,
      "learning_rate": 6.227427435703997e-05,
      "loss": 11.9167,
      "step": 90
    },
    {
      "epoch": 0.038781163434903045,
      "grad_norm": 0.03919035941362381,
      "learning_rate": 6.147119600233758e-05,
      "loss": 11.919,
      "step": 91
    },
    {
      "epoch": 0.039207330066055826,
      "grad_norm": 0.04492755979299545,
      "learning_rate": 6.066498153718735e-05,
      "loss": 11.9159,
      "step": 92
    },
    {
      "epoch": 0.03963349669720861,
      "grad_norm": 0.03987622261047363,
      "learning_rate": 5.985585137257401e-05,
      "loss": 11.9161,
      "step": 93
    },
    {
      "epoch": 0.04005966332836139,
      "grad_norm": 0.06534025073051453,
      "learning_rate": 5.90440267166055e-05,
      "loss": 11.9151,
      "step": 94
    },
    {
      "epoch": 0.04048582995951417,
      "grad_norm": 0.05829080194234848,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 11.916,
      "step": 95
    },
    {
      "epoch": 0.04091199659066695,
      "grad_norm": 0.06628172099590302,
      "learning_rate": 5.74131823855921e-05,
      "loss": 11.916,
      "step": 96
    },
    {
      "epoch": 0.04133816322181973,
      "grad_norm": 0.0619095116853714,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 11.9159,
      "step": 97
    },
    {
      "epoch": 0.041764329852972515,
      "grad_norm": 0.05408721789717674,
      "learning_rate": 5.577423184847932e-05,
      "loss": 11.915,
      "step": 98
    },
    {
      "epoch": 0.042190496484125296,
      "grad_norm": 0.04741065949201584,
      "learning_rate": 5.495227651252315e-05,
      "loss": 11.9175,
      "step": 99
    },
    {
      "epoch": 0.04261666311527807,
      "grad_norm": 0.028685856610536575,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 11.9154,
      "step": 100
    },
    {
      "epoch": 0.04261666311527807,
      "eval_loss": 11.918998718261719,
      "eval_runtime": 19.8459,
      "eval_samples_per_second": 199.135,
      "eval_steps_per_second": 49.784,
      "step": 100
    },
    {
      "epoch": 0.04304282974643085,
      "grad_norm": 0.036599818617105484,
      "learning_rate": 5.330452921628497e-05,
      "loss": 11.9236,
      "step": 101
    },
    {
      "epoch": 0.043468996377583634,
      "grad_norm": 0.03515402972698212,
      "learning_rate": 5.247918773366112e-05,
      "loss": 11.9218,
      "step": 102
    },
    {
      "epoch": 0.043895163008736415,
      "grad_norm": 0.028733957558870316,
      "learning_rate": 5.165316846586541e-05,
      "loss": 11.9212,
      "step": 103
    },
    {
      "epoch": 0.0443213296398892,
      "grad_norm": 0.03964085876941681,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 11.9237,
      "step": 104
    },
    {
      "epoch": 0.04474749627104198,
      "grad_norm": 0.03138640522956848,
      "learning_rate": 5e-05,
      "loss": 11.9219,
      "step": 105
    },
    {
      "epoch": 0.04517366290219476,
      "grad_norm": 0.037518151104450226,
      "learning_rate": 4.917330276168208e-05,
      "loss": 11.9208,
      "step": 106
    },
    {
      "epoch": 0.04559982953334754,
      "grad_norm": 0.028903013095259666,
      "learning_rate": 4.834683153413459e-05,
      "loss": 11.9214,
      "step": 107
    },
    {
      "epoch": 0.04602599616450032,
      "grad_norm": 0.03345424681901932,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 11.9218,
      "step": 108
    },
    {
      "epoch": 0.0464521627956531,
      "grad_norm": 0.04321468621492386,
      "learning_rate": 4.669547078371504e-05,
      "loss": 11.9208,
      "step": 109
    },
    {
      "epoch": 0.04687832942680588,
      "grad_norm": 0.027104416862130165,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 11.9205,
      "step": 110
    },
    {
      "epoch": 0.04730449605795866,
      "grad_norm": 0.046303555369377136,
      "learning_rate": 4.504772348747687e-05,
      "loss": 11.9198,
      "step": 111
    },
    {
      "epoch": 0.04773066268911144,
      "grad_norm": 0.020268265157938004,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 11.921,
      "step": 112
    },
    {
      "epoch": 0.04815682932026422,
      "grad_norm": 0.02363026887178421,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 11.9179,
      "step": 113
    },
    {
      "epoch": 0.048582995951417005,
      "grad_norm": 0.028702935203909874,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 11.9184,
      "step": 114
    },
    {
      "epoch": 0.049009162582569786,
      "grad_norm": 0.0349009670317173,
      "learning_rate": 4.17702704859633e-05,
      "loss": 11.9194,
      "step": 115
    },
    {
      "epoch": 0.04943532921372257,
      "grad_norm": 0.029482070356607437,
      "learning_rate": 4.095597328339452e-05,
      "loss": 11.9202,
      "step": 116
    },
    {
      "epoch": 0.04986149584487535,
      "grad_norm": 0.024747077375650406,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 11.9204,
      "step": 117
    },
    {
      "epoch": 0.05028766247602813,
      "grad_norm": 0.02398655191063881,
      "learning_rate": 3.933501846281267e-05,
      "loss": 11.9204,
      "step": 118
    },
    {
      "epoch": 0.050713829107180905,
      "grad_norm": 0.02014654129743576,
      "learning_rate": 3.852880399766243e-05,
      "loss": 11.9201,
      "step": 119
    },
    {
      "epoch": 0.051139995738333686,
      "grad_norm": 0.03822954371571541,
      "learning_rate": 3.772572564296005e-05,
      "loss": 11.9176,
      "step": 120
    },
    {
      "epoch": 0.05156616236948647,
      "grad_norm": 0.02022726647555828,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 11.9203,
      "step": 121
    },
    {
      "epoch": 0.05199232900063925,
      "grad_norm": 0.029549848288297653,
      "learning_rate": 3.612985456190778e-05,
      "loss": 11.9173,
      "step": 122
    },
    {
      "epoch": 0.05241849563179203,
      "grad_norm": 0.02898990735411644,
      "learning_rate": 3.533749813077677e-05,
      "loss": 11.9162,
      "step": 123
    },
    {
      "epoch": 0.05284466226294481,
      "grad_norm": 0.025192702189087868,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 11.9207,
      "step": 124
    },
    {
      "epoch": 0.053270828894097594,
      "grad_norm": 0.043277643620967865,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 11.9167,
      "step": 125
    },
    {
      "epoch": 0.053696995525250375,
      "grad_norm": 0.03845348209142685,
      "learning_rate": 3.298534127791785e-05,
      "loss": 11.9196,
      "step": 126
    },
    {
      "epoch": 0.05412316215640316,
      "grad_norm": 0.039395108819007874,
      "learning_rate": 3.221030765387417e-05,
      "loss": 11.917,
      "step": 127
    },
    {
      "epoch": 0.05454932878755593,
      "grad_norm": 0.03365875035524368,
      "learning_rate": 3.144013755408895e-05,
      "loss": 11.9194,
      "step": 128
    },
    {
      "epoch": 0.05497549541870871,
      "grad_norm": 0.0218888521194458,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 11.9198,
      "step": 129
    },
    {
      "epoch": 0.055401662049861494,
      "grad_norm": 0.05459000542759895,
      "learning_rate": 2.991522876735154e-05,
      "loss": 11.9176,
      "step": 130
    },
    {
      "epoch": 0.055827828681014276,
      "grad_norm": 0.06031973287463188,
      "learning_rate": 2.916090697523549e-05,
      "loss": 11.9192,
      "step": 131
    },
    {
      "epoch": 0.05625399531216706,
      "grad_norm": 0.048292942345142365,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 11.9163,
      "step": 132
    },
    {
      "epoch": 0.05668016194331984,
      "grad_norm": 0.027853483334183693,
      "learning_rate": 2.766955965735968e-05,
      "loss": 11.9172,
      "step": 133
    },
    {
      "epoch": 0.05710632857447262,
      "grad_norm": 0.021714165806770325,
      "learning_rate": 2.693294185106562e-05,
      "loss": 11.916,
      "step": 134
    },
    {
      "epoch": 0.0575324952056254,
      "grad_norm": 0.03132518753409386,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 11.9173,
      "step": 135
    },
    {
      "epoch": 0.05795866183677818,
      "grad_norm": 0.04859468340873718,
      "learning_rate": 2.547882480847461e-05,
      "loss": 11.9175,
      "step": 136
    },
    {
      "epoch": 0.05838482846793096,
      "grad_norm": 0.046058133244514465,
      "learning_rate": 2.476172311325783e-05,
      "loss": 11.9207,
      "step": 137
    },
    {
      "epoch": 0.05881099509908374,
      "grad_norm": 0.05537068098783493,
      "learning_rate": 2.405152131093926e-05,
      "loss": 11.9171,
      "step": 138
    },
    {
      "epoch": 0.05923716173023652,
      "grad_norm": 0.05426519364118576,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 11.9195,
      "step": 139
    },
    {
      "epoch": 0.0596633283613893,
      "grad_norm": 0.027803629636764526,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 11.9159,
      "step": 140
    },
    {
      "epoch": 0.060089494992542083,
      "grad_norm": 0.06105147302150726,
      "learning_rate": 2.196424713241637e-05,
      "loss": 11.9184,
      "step": 141
    },
    {
      "epoch": 0.060515661623694865,
      "grad_norm": 0.030715011060237885,
      "learning_rate": 2.128356686585282e-05,
      "loss": 11.917,
      "step": 142
    },
    {
      "epoch": 0.060941828254847646,
      "grad_norm": 0.05231258645653725,
      "learning_rate": 2.061073738537635e-05,
      "loss": 11.9182,
      "step": 143
    },
    {
      "epoch": 0.06136799488600043,
      "grad_norm": 0.025369372218847275,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 11.9174,
      "step": 144
    },
    {
      "epoch": 0.06179416151715321,
      "grad_norm": 0.04663919657468796,
      "learning_rate": 1.928936436551661e-05,
      "loss": 11.9172,
      "step": 145
    },
    {
      "epoch": 0.06222032814830599,
      "grad_norm": 0.0509616956114769,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 11.9151,
      "step": 146
    },
    {
      "epoch": 0.06264649477945877,
      "grad_norm": 0.06879665702581406,
      "learning_rate": 1.800157297483417e-05,
      "loss": 11.9183,
      "step": 147
    },
    {
      "epoch": 0.06307266141061155,
      "grad_norm": 0.03109815903007984,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 11.9157,
      "step": 148
    },
    {
      "epoch": 0.06349882804176434,
      "grad_norm": 0.0557471439242363,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 11.9145,
      "step": 149
    },
    {
      "epoch": 0.06392499467291711,
      "grad_norm": 0.052083831280469894,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 11.9181,
      "step": 150
    },
    {
      "epoch": 0.06392499467291711,
      "eval_loss": 11.91872501373291,
      "eval_runtime": 19.8407,
      "eval_samples_per_second": 199.186,
      "eval_steps_per_second": 49.797,
      "step": 150
    },
    {
      "epoch": 0.0643511613040699,
      "grad_norm": 0.02206737920641899,
      "learning_rate": 1.553232954407171e-05,
      "loss": 11.9231,
      "step": 151
    },
    {
      "epoch": 0.06477732793522267,
      "grad_norm": 0.03517240285873413,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 11.9217,
      "step": 152
    },
    {
      "epoch": 0.06520349456637545,
      "grad_norm": 0.03711656108498573,
      "learning_rate": 1.435357758543015e-05,
      "loss": 11.9214,
      "step": 153
    },
    {
      "epoch": 0.06562966119752824,
      "grad_norm": 0.028357867151498795,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 11.9228,
      "step": 154
    },
    {
      "epoch": 0.06605582782868101,
      "grad_norm": 0.04135802388191223,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 11.9212,
      "step": 155
    },
    {
      "epoch": 0.0664819944598338,
      "grad_norm": 0.027849528938531876,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 11.9211,
      "step": 156
    },
    {
      "epoch": 0.06690816109098657,
      "grad_norm": 0.027743613347411156,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 11.9221,
      "step": 157
    },
    {
      "epoch": 0.06733432772213936,
      "grad_norm": 0.02826538123190403,
      "learning_rate": 1.157994445715706e-05,
      "loss": 11.9217,
      "step": 158
    },
    {
      "epoch": 0.06776049435329214,
      "grad_norm": 0.028083613142371178,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 11.9216,
      "step": 159
    },
    {
      "epoch": 0.06818666098444492,
      "grad_norm": 0.03189048543572426,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 11.9205,
      "step": 160
    },
    {
      "epoch": 0.0686128276155977,
      "grad_norm": 0.026526015251874924,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 11.9203,
      "step": 161
    },
    {
      "epoch": 0.06903899424675047,
      "grad_norm": 0.025359414517879486,
      "learning_rate": 9.549150281252633e-06,
      "loss": 11.9206,
      "step": 162
    },
    {
      "epoch": 0.06946516087790326,
      "grad_norm": 0.03614227473735809,
      "learning_rate": 9.068759265665384e-06,
      "loss": 11.9224,
      "step": 163
    },
    {
      "epoch": 0.06989132750905604,
      "grad_norm": 0.029648585245013237,
      "learning_rate": 8.599558442598998e-06,
      "loss": 11.9177,
      "step": 164
    },
    {
      "epoch": 0.07031749414020882,
      "grad_norm": 0.029727661982178688,
      "learning_rate": 8.141676086873572e-06,
      "loss": 11.9191,
      "step": 165
    },
    {
      "epoch": 0.0707436607713616,
      "grad_norm": 0.03479655832052231,
      "learning_rate": 7.695237378953223e-06,
      "loss": 11.9214,
      "step": 166
    },
    {
      "epoch": 0.07116982740251439,
      "grad_norm": 0.023519039154052734,
      "learning_rate": 7.260364370723044e-06,
      "loss": 11.9194,
      "step": 167
    },
    {
      "epoch": 0.07159599403366716,
      "grad_norm": 0.028942471370100975,
      "learning_rate": 6.837175952121306e-06,
      "loss": 11.9198,
      "step": 168
    },
    {
      "epoch": 0.07202216066481995,
      "grad_norm": 0.023210696876049042,
      "learning_rate": 6.425787818636131e-06,
      "loss": 11.921,
      "step": 169
    },
    {
      "epoch": 0.07244832729597273,
      "grad_norm": 0.026163075119256973,
      "learning_rate": 6.026312439675552e-06,
      "loss": 11.9209,
      "step": 170
    },
    {
      "epoch": 0.0728744939271255,
      "grad_norm": 0.021232161670923233,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 11.9177,
      "step": 171
    },
    {
      "epoch": 0.07330066055827829,
      "grad_norm": 0.043857429176568985,
      "learning_rate": 5.263533508961827e-06,
      "loss": 11.9215,
      "step": 172
    },
    {
      "epoch": 0.07372682718943106,
      "grad_norm": 0.03613021597266197,
      "learning_rate": 4.900438493352055e-06,
      "loss": 11.916,
      "step": 173
    },
    {
      "epoch": 0.07415299382058385,
      "grad_norm": 0.04972798749804497,
      "learning_rate": 4.549673247541875e-06,
      "loss": 11.9188,
      "step": 174
    },
    {
      "epoch": 0.07457916045173663,
      "grad_norm": 0.03918720781803131,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 11.9196,
      "step": 175
    },
    {
      "epoch": 0.07500532708288941,
      "grad_norm": 0.031602051109075546,
      "learning_rate": 3.885512251130763e-06,
      "loss": 11.918,
      "step": 176
    },
    {
      "epoch": 0.07543149371404219,
      "grad_norm": 0.04737675189971924,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 11.9194,
      "step": 177
    },
    {
      "epoch": 0.07585766034519498,
      "grad_norm": 0.044106028974056244,
      "learning_rate": 3.271776770026963e-06,
      "loss": 11.9172,
      "step": 178
    },
    {
      "epoch": 0.07628382697634775,
      "grad_norm": 0.04422431066632271,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 11.9178,
      "step": 179
    },
    {
      "epoch": 0.07670999360750053,
      "grad_norm": 0.026723336428403854,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 11.9173,
      "step": 180
    },
    {
      "epoch": 0.07713616023865331,
      "grad_norm": 0.06505651772022247,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 11.9176,
      "step": 181
    },
    {
      "epoch": 0.07756232686980609,
      "grad_norm": 0.034520190209150314,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 11.9162,
      "step": 182
    },
    {
      "epoch": 0.07798849350095888,
      "grad_norm": 0.052895013242959976,
      "learning_rate": 1.962316193157593e-06,
      "loss": 11.9192,
      "step": 183
    },
    {
      "epoch": 0.07841466013211165,
      "grad_norm": 0.035937681794166565,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 11.9182,
      "step": 184
    },
    {
      "epoch": 0.07884082676326444,
      "grad_norm": 0.0382249541580677,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 11.916,
      "step": 185
    },
    {
      "epoch": 0.07926699339441722,
      "grad_norm": 0.03412754088640213,
      "learning_rate": 1.333670137599713e-06,
      "loss": 11.9198,
      "step": 186
    },
    {
      "epoch": 0.07969316002557,
      "grad_norm": 0.03203566372394562,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 11.9182,
      "step": 187
    },
    {
      "epoch": 0.08011932665672278,
      "grad_norm": 0.06936044245958328,
      "learning_rate": 9.810017062595322e-07,
      "loss": 11.9152,
      "step": 188
    },
    {
      "epoch": 0.08054549328787555,
      "grad_norm": 0.04827641695737839,
      "learning_rate": 8.247462563808817e-07,
      "loss": 11.9191,
      "step": 189
    },
    {
      "epoch": 0.08097165991902834,
      "grad_norm": 0.023047445341944695,
      "learning_rate": 6.819348298638839e-07,
      "loss": 11.9161,
      "step": 190
    },
    {
      "epoch": 0.08139782655018112,
      "grad_norm": 0.04772016778588295,
      "learning_rate": 5.526064699265753e-07,
      "loss": 11.9175,
      "step": 191
    },
    {
      "epoch": 0.0818239931813339,
      "grad_norm": 0.045728784054517746,
      "learning_rate": 4.367965336512403e-07,
      "loss": 11.9158,
      "step": 192
    },
    {
      "epoch": 0.08225015981248668,
      "grad_norm": 0.04323410615324974,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 11.9183,
      "step": 193
    },
    {
      "epoch": 0.08267632644363947,
      "grad_norm": 0.041189420968294144,
      "learning_rate": 2.458548727494292e-07,
      "loss": 11.9158,
      "step": 194
    },
    {
      "epoch": 0.08310249307479224,
      "grad_norm": 0.0382416695356369,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 11.9192,
      "step": 195
    },
    {
      "epoch": 0.08352865970594503,
      "grad_norm": 0.04960033670067787,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 11.9171,
      "step": 196
    },
    {
      "epoch": 0.0839548263370978,
      "grad_norm": 0.03230350837111473,
      "learning_rate": 6.150154258476315e-08,
      "loss": 11.9171,
      "step": 197
    },
    {
      "epoch": 0.08438099296825059,
      "grad_norm": 0.04565230756998062,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 11.9176,
      "step": 198
    },
    {
      "epoch": 0.08480715959940337,
      "grad_norm": 0.0707671120762825,
      "learning_rate": 6.834750376549792e-09,
      "loss": 11.917,
      "step": 199
    },
    {
      "epoch": 0.08523332623055614,
      "grad_norm": 0.06787197291851044,
      "learning_rate": 0.0,
      "loss": 11.9172,
      "step": 200
    },
    {
      "epoch": 0.08523332623055614,
      "eval_loss": 11.918663024902344,
      "eval_runtime": 19.8505,
      "eval_samples_per_second": 199.088,
      "eval_steps_per_second": 49.772,
      "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": 967781253120.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}