{
  "best_metric": 0.9521539807319641,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.5623242736644799,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0037488284910965324,
      "grad_norm": 0.31679341197013855,
      "learning_rate": 1e-05,
      "loss": 0.7074,
      "step": 1
    },
    {
      "epoch": 0.0037488284910965324,
      "eval_loss": 1.2508360147476196,
      "eval_runtime": 20.2565,
      "eval_samples_per_second": 22.215,
      "eval_steps_per_second": 5.578,
      "step": 1
    },
    {
      "epoch": 0.007497656982193065,
      "grad_norm": 0.35684728622436523,
      "learning_rate": 2e-05,
      "loss": 0.902,
      "step": 2
    },
    {
      "epoch": 0.011246485473289597,
      "grad_norm": 0.42902156710624695,
      "learning_rate": 3e-05,
      "loss": 0.9928,
      "step": 3
    },
    {
      "epoch": 0.01499531396438613,
      "grad_norm": 0.3997367024421692,
      "learning_rate": 4e-05,
      "loss": 0.9488,
      "step": 4
    },
    {
      "epoch": 0.01874414245548266,
      "grad_norm": 0.35822993516921997,
      "learning_rate": 5e-05,
      "loss": 1.0835,
      "step": 5
    },
    {
      "epoch": 0.022492970946579195,
      "grad_norm": 0.39229267835617065,
      "learning_rate": 6e-05,
      "loss": 0.9941,
      "step": 6
    },
    {
      "epoch": 0.026241799437675725,
      "grad_norm": 0.37683796882629395,
      "learning_rate": 7e-05,
      "loss": 0.9435,
      "step": 7
    },
    {
      "epoch": 0.02999062792877226,
      "grad_norm": 0.40337347984313965,
      "learning_rate": 8e-05,
      "loss": 0.9366,
      "step": 8
    },
    {
      "epoch": 0.033739456419868794,
      "grad_norm": 0.38738805055618286,
      "learning_rate": 9e-05,
      "loss": 0.9532,
      "step": 9
    },
    {
      "epoch": 0.03748828491096532,
      "grad_norm": 0.4414096772670746,
      "learning_rate": 0.0001,
      "loss": 0.9354,
      "step": 10
    },
    {
      "epoch": 0.041237113402061855,
      "grad_norm": 0.42699843645095825,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.8913,
      "step": 11
    },
    {
      "epoch": 0.04498594189315839,
      "grad_norm": 0.40462222695350647,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.9613,
      "step": 12
    },
    {
      "epoch": 0.04873477038425492,
      "grad_norm": 0.4474236071109772,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.8565,
      "step": 13
    },
    {
      "epoch": 0.05248359887535145,
      "grad_norm": 0.4120841920375824,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.9703,
      "step": 14
    },
    {
      "epoch": 0.056232427366447985,
      "grad_norm": 0.43965059518814087,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.0001,
      "step": 15
    },
    {
      "epoch": 0.05998125585754452,
      "grad_norm": 0.4135129749774933,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.9151,
      "step": 16
    },
    {
      "epoch": 0.06373008434864105,
      "grad_norm": 0.3968392014503479,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.9239,
      "step": 17
    },
    {
      "epoch": 0.06747891283973759,
      "grad_norm": 0.4430868327617645,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.9606,
      "step": 18
    },
    {
      "epoch": 0.07122774133083412,
      "grad_norm": 0.4117301404476166,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.9951,
      "step": 19
    },
    {
      "epoch": 0.07497656982193064,
      "grad_norm": 0.4057822823524475,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.9083,
      "step": 20
    },
    {
      "epoch": 0.07872539831302718,
      "grad_norm": 0.4247874319553375,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.9071,
      "step": 21
    },
    {
      "epoch": 0.08247422680412371,
      "grad_norm": 0.4510324001312256,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.003,
      "step": 22
    },
    {
      "epoch": 0.08622305529522024,
      "grad_norm": 0.45904019474983215,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.0173,
      "step": 23
    },
    {
      "epoch": 0.08997188378631678,
      "grad_norm": 0.42046481370925903,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.9275,
      "step": 24
    },
    {
      "epoch": 0.09372071227741331,
      "grad_norm": 0.48092198371887207,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.0359,
      "step": 25
    },
    {
      "epoch": 0.09746954076850985,
      "grad_norm": 0.47308149933815,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.9108,
      "step": 26
    },
    {
      "epoch": 0.10121836925960637,
      "grad_norm": 0.49878472089767456,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.0235,
      "step": 27
    },
    {
      "epoch": 0.1049671977507029,
      "grad_norm": 0.5273634195327759,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.0648,
      "step": 28
    },
    {
      "epoch": 0.10871602624179943,
      "grad_norm": 0.5255836844444275,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.9461,
      "step": 29
    },
    {
      "epoch": 0.11246485473289597,
      "grad_norm": 0.638592004776001,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.1944,
      "step": 30
    },
    {
      "epoch": 0.1162136832239925,
      "grad_norm": 0.5737610459327698,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.9481,
      "step": 31
    },
    {
      "epoch": 0.11996251171508904,
      "grad_norm": 0.6336954832077026,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.0825,
      "step": 32
    },
    {
      "epoch": 0.12371134020618557,
      "grad_norm": 0.7441895008087158,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.018,
      "step": 33
    },
    {
      "epoch": 0.1274601686972821,
      "grad_norm": 0.7783705592155457,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.9827,
      "step": 34
    },
    {
      "epoch": 0.13120899718837864,
      "grad_norm": 0.7787414789199829,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.0465,
      "step": 35
    },
    {
      "epoch": 0.13495782567947517,
      "grad_norm": 0.7003400921821594,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.1124,
      "step": 36
    },
    {
      "epoch": 0.1387066541705717,
      "grad_norm": 0.7841488122940063,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.1447,
      "step": 37
    },
    {
      "epoch": 0.14245548266166824,
      "grad_norm": 0.7686071395874023,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.0302,
      "step": 38
    },
    {
      "epoch": 0.14620431115276475,
      "grad_norm": 0.7470108866691589,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.0587,
      "step": 39
    },
    {
      "epoch": 0.14995313964386128,
      "grad_norm": 0.8082842230796814,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.1201,
      "step": 40
    },
    {
      "epoch": 0.15370196813495782,
      "grad_norm": 0.8214188814163208,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.1126,
      "step": 41
    },
    {
      "epoch": 0.15745079662605435,
      "grad_norm": 0.8241232633590698,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.0597,
      "step": 42
    },
    {
      "epoch": 0.16119962511715089,
      "grad_norm": 0.8922351598739624,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.1883,
      "step": 43
    },
    {
      "epoch": 0.16494845360824742,
      "grad_norm": 0.9459320902824402,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.0895,
      "step": 44
    },
    {
      "epoch": 0.16869728209934395,
      "grad_norm": 0.9130051732063293,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.0781,
      "step": 45
    },
    {
      "epoch": 0.1724461105904405,
      "grad_norm": 1.0389268398284912,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.13,
      "step": 46
    },
    {
      "epoch": 0.17619493908153702,
      "grad_norm": 0.9850935935974121,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.1097,
      "step": 47
    },
    {
      "epoch": 0.17994376757263356,
      "grad_norm": 1.080594539642334,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.0774,
      "step": 48
    },
    {
      "epoch": 0.1836925960637301,
      "grad_norm": 0.9982865452766418,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.0644,
      "step": 49
    },
    {
      "epoch": 0.18744142455482662,
      "grad_norm": 1.4918893575668335,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.2589,
      "step": 50
    },
    {
      "epoch": 0.18744142455482662,
      "eval_loss": 1.0242154598236084,
      "eval_runtime": 20.7,
      "eval_samples_per_second": 21.739,
      "eval_steps_per_second": 5.459,
      "step": 50
    },
    {
      "epoch": 0.19119025304592316,
      "grad_norm": 0.5081945061683655,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.7838,
      "step": 51
    },
    {
      "epoch": 0.1949390815370197,
      "grad_norm": 0.4391409754753113,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.9001,
      "step": 52
    },
    {
      "epoch": 0.19868791002811623,
      "grad_norm": 0.4722622334957123,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.8787,
      "step": 53
    },
    {
      "epoch": 0.20243673851921273,
      "grad_norm": 0.3832034170627594,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.9396,
      "step": 54
    },
    {
      "epoch": 0.20618556701030927,
      "grad_norm": 0.3658829927444458,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.0097,
      "step": 55
    },
    {
      "epoch": 0.2099343955014058,
      "grad_norm": 0.32071611285209656,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.9597,
      "step": 56
    },
    {
      "epoch": 0.21368322399250234,
      "grad_norm": 0.3354572355747223,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.9362,
      "step": 57
    },
    {
      "epoch": 0.21743205248359887,
      "grad_norm": 0.3265805244445801,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.8831,
      "step": 58
    },
    {
      "epoch": 0.2211808809746954,
      "grad_norm": 0.3415479063987732,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.9097,
      "step": 59
    },
    {
      "epoch": 0.22492970946579194,
      "grad_norm": 0.35654333233833313,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.9686,
      "step": 60
    },
    {
      "epoch": 0.22867853795688847,
      "grad_norm": 0.4099575877189636,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.941,
      "step": 61
    },
    {
      "epoch": 0.232427366447985,
      "grad_norm": 0.3779386281967163,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.9996,
      "step": 62
    },
    {
      "epoch": 0.23617619493908154,
      "grad_norm": 0.39320096373558044,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.9238,
      "step": 63
    },
    {
      "epoch": 0.23992502343017807,
      "grad_norm": 0.34283924102783203,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.9214,
      "step": 64
    },
    {
      "epoch": 0.2436738519212746,
      "grad_norm": 0.3750361502170563,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.9483,
      "step": 65
    },
    {
      "epoch": 0.24742268041237114,
      "grad_norm": 0.35264351963996887,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.909,
      "step": 66
    },
    {
      "epoch": 0.2511715089034677,
      "grad_norm": 0.35964611172676086,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8735,
      "step": 67
    },
    {
      "epoch": 0.2549203373945642,
      "grad_norm": 0.3703603148460388,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.9116,
      "step": 68
    },
    {
      "epoch": 0.25866916588566075,
      "grad_norm": 0.4141576886177063,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.9103,
      "step": 69
    },
    {
      "epoch": 0.2624179943767573,
      "grad_norm": 0.38713309168815613,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.9738,
      "step": 70
    },
    {
      "epoch": 0.2661668228678538,
      "grad_norm": 0.37721550464630127,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.8843,
      "step": 71
    },
    {
      "epoch": 0.26991565135895035,
      "grad_norm": 0.38859471678733826,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.9337,
      "step": 72
    },
    {
      "epoch": 0.2736644798500469,
      "grad_norm": 0.4152131974697113,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.9016,
      "step": 73
    },
    {
      "epoch": 0.2774133083411434,
      "grad_norm": 0.4538514018058777,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.9975,
      "step": 74
    },
    {
      "epoch": 0.28116213683223995,
      "grad_norm": 0.4288105368614197,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.861,
      "step": 75
    },
    {
      "epoch": 0.2849109653233365,
      "grad_norm": 0.4608365297317505,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.9113,
      "step": 76
    },
    {
      "epoch": 0.28865979381443296,
      "grad_norm": 0.49569573998451233,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.003,
      "step": 77
    },
    {
      "epoch": 0.2924086223055295,
      "grad_norm": 0.4870223104953766,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.9732,
      "step": 78
    },
    {
      "epoch": 0.29615745079662603,
      "grad_norm": 0.5530253052711487,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.9203,
      "step": 79
    },
    {
      "epoch": 0.29990627928772257,
      "grad_norm": 0.5791155099868774,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.9646,
      "step": 80
    },
    {
      "epoch": 0.3036551077788191,
      "grad_norm": 0.5287548303604126,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.0219,
      "step": 81
    },
    {
      "epoch": 0.30740393626991563,
      "grad_norm": 0.6269212365150452,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.9871,
      "step": 82
    },
    {
      "epoch": 0.31115276476101217,
      "grad_norm": 0.6427403688430786,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.0519,
      "step": 83
    },
    {
      "epoch": 0.3149015932521087,
      "grad_norm": 0.6051539182662964,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.0181,
      "step": 84
    },
    {
      "epoch": 0.31865042174320524,
      "grad_norm": 0.6866359710693359,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.1258,
      "step": 85
    },
    {
      "epoch": 0.32239925023430177,
      "grad_norm": 0.6848306655883789,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.0811,
      "step": 86
    },
    {
      "epoch": 0.3261480787253983,
      "grad_norm": 0.778276801109314,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.9853,
      "step": 87
    },
    {
      "epoch": 0.32989690721649484,
      "grad_norm": 0.6934621334075928,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.0929,
      "step": 88
    },
    {
      "epoch": 0.3336457357075914,
      "grad_norm": 0.6698548197746277,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.9147,
      "step": 89
    },
    {
      "epoch": 0.3373945641986879,
      "grad_norm": 0.699309766292572,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.9323,
      "step": 90
    },
    {
      "epoch": 0.34114339268978444,
      "grad_norm": 0.752902626991272,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.0437,
      "step": 91
    },
    {
      "epoch": 0.344892221180881,
      "grad_norm": 0.8060910701751709,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.0366,
      "step": 92
    },
    {
      "epoch": 0.3486410496719775,
      "grad_norm": 0.8134373426437378,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.0094,
      "step": 93
    },
    {
      "epoch": 0.35238987816307404,
      "grad_norm": 0.8147566914558411,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.999,
      "step": 94
    },
    {
      "epoch": 0.3561387066541706,
      "grad_norm": 0.7697128653526306,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.9543,
      "step": 95
    },
    {
      "epoch": 0.3598875351452671,
      "grad_norm": 0.829299807548523,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.0159,
      "step": 96
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.9377629160881042,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.0377,
      "step": 97
    },
    {
      "epoch": 0.3673851921274602,
      "grad_norm": 0.9740127921104431,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.0688,
      "step": 98
    },
    {
      "epoch": 0.3711340206185567,
      "grad_norm": 1.1065244674682617,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.0641,
      "step": 99
    },
    {
      "epoch": 0.37488284910965325,
      "grad_norm": 1.4678974151611328,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.2111,
      "step": 100
    },
    {
      "epoch": 0.37488284910965325,
      "eval_loss": 0.9811466932296753,
      "eval_runtime": 20.8104,
      "eval_samples_per_second": 21.624,
      "eval_steps_per_second": 5.43,
      "step": 100
    },
    {
      "epoch": 0.3786316776007498,
      "grad_norm": 0.3575192391872406,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.6942,
      "step": 101
    },
    {
      "epoch": 0.3823805060918463,
      "grad_norm": 0.31599247455596924,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.8247,
      "step": 102
    },
    {
      "epoch": 0.38612933458294285,
      "grad_norm": 0.35906827449798584,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.8857,
      "step": 103
    },
    {
      "epoch": 0.3898781630740394,
      "grad_norm": 0.33249327540397644,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.9295,
      "step": 104
    },
    {
      "epoch": 0.3936269915651359,
      "grad_norm": 0.32756689190864563,
      "learning_rate": 5e-05,
      "loss": 0.8471,
      "step": 105
    },
    {
      "epoch": 0.39737582005623245,
      "grad_norm": 0.3289243280887604,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.8969,
      "step": 106
    },
    {
      "epoch": 0.40112464854732893,
      "grad_norm": 0.31799304485321045,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.9489,
      "step": 107
    },
    {
      "epoch": 0.40487347703842547,
      "grad_norm": 0.31175363063812256,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.9386,
      "step": 108
    },
    {
      "epoch": 0.408622305529522,
      "grad_norm": 0.3153715431690216,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.912,
      "step": 109
    },
    {
      "epoch": 0.41237113402061853,
      "grad_norm": 0.30276235938072205,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.9109,
      "step": 110
    },
    {
      "epoch": 0.41611996251171507,
      "grad_norm": 0.3206758201122284,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.8837,
      "step": 111
    },
    {
      "epoch": 0.4198687910028116,
      "grad_norm": 0.3105361759662628,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.8786,
      "step": 112
    },
    {
      "epoch": 0.42361761949390814,
      "grad_norm": 0.2993127107620239,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.8757,
      "step": 113
    },
    {
      "epoch": 0.42736644798500467,
      "grad_norm": 0.31823205947875977,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.8649,
      "step": 114
    },
    {
      "epoch": 0.4311152764761012,
      "grad_norm": 0.3383299708366394,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.9032,
      "step": 115
    },
    {
      "epoch": 0.43486410496719774,
      "grad_norm": 0.37144601345062256,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.8691,
      "step": 116
    },
    {
      "epoch": 0.4386129334582943,
      "grad_norm": 0.3267931342124939,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.9388,
      "step": 117
    },
    {
      "epoch": 0.4423617619493908,
      "grad_norm": 0.34755590558052063,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.9583,
      "step": 118
    },
    {
      "epoch": 0.44611059044048734,
      "grad_norm": 0.3316834568977356,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.8613,
      "step": 119
    },
    {
      "epoch": 0.4498594189315839,
      "grad_norm": 0.3462877869606018,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.8717,
      "step": 120
    },
    {
      "epoch": 0.4536082474226804,
      "grad_norm": 0.37453365325927734,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.8908,
      "step": 121
    },
    {
      "epoch": 0.45735707591377694,
      "grad_norm": 0.3717382252216339,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.9988,
      "step": 122
    },
    {
      "epoch": 0.4611059044048735,
      "grad_norm": 0.39408352971076965,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.9501,
      "step": 123
    },
    {
      "epoch": 0.46485473289597,
      "grad_norm": 0.4256141483783722,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.914,
      "step": 124
    },
    {
      "epoch": 0.46860356138706655,
      "grad_norm": 0.4107443690299988,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.9253,
      "step": 125
    },
    {
      "epoch": 0.4723523898781631,
      "grad_norm": 0.4722575545310974,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.9535,
      "step": 126
    },
    {
      "epoch": 0.4761012183692596,
      "grad_norm": 0.47176846861839294,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.9184,
      "step": 127
    },
    {
      "epoch": 0.47985004686035615,
      "grad_norm": 0.486392617225647,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.9515,
      "step": 128
    },
    {
      "epoch": 0.4835988753514527,
      "grad_norm": 0.4838985204696655,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.9586,
      "step": 129
    },
    {
      "epoch": 0.4873477038425492,
      "grad_norm": 0.5224278569221497,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.1063,
      "step": 130
    },
    {
      "epoch": 0.49109653233364575,
      "grad_norm": 0.5882999897003174,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.9966,
      "step": 131
    },
    {
      "epoch": 0.4948453608247423,
      "grad_norm": 0.565453290939331,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.0058,
      "step": 132
    },
    {
      "epoch": 0.4985941893158388,
      "grad_norm": 0.6657898426055908,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.0503,
      "step": 133
    },
    {
      "epoch": 0.5023430178069354,
      "grad_norm": 0.5977612137794495,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.8594,
      "step": 134
    },
    {
      "epoch": 0.5060918462980318,
      "grad_norm": 0.5637332201004028,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.9948,
      "step": 135
    },
    {
      "epoch": 0.5098406747891284,
      "grad_norm": 0.6925244331359863,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.9501,
      "step": 136
    },
    {
      "epoch": 0.5135895032802249,
      "grad_norm": 0.6315667629241943,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.9955,
      "step": 137
    },
    {
      "epoch": 0.5173383317713215,
      "grad_norm": 0.6699217557907104,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.0051,
      "step": 138
    },
    {
      "epoch": 0.521087160262418,
      "grad_norm": 0.6867546439170837,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.0129,
      "step": 139
    },
    {
      "epoch": 0.5248359887535146,
      "grad_norm": 0.7504917979240417,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.0773,
      "step": 140
    },
    {
      "epoch": 0.528584817244611,
      "grad_norm": 0.7592334151268005,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.985,
      "step": 141
    },
    {
      "epoch": 0.5323336457357076,
      "grad_norm": 0.7560880780220032,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.0159,
      "step": 142
    },
    {
      "epoch": 0.5360824742268041,
      "grad_norm": 0.7213366031646729,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.0412,
      "step": 143
    },
    {
      "epoch": 0.5398313027179007,
      "grad_norm": 0.7502860426902771,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.0144,
      "step": 144
    },
    {
      "epoch": 0.5435801312089972,
      "grad_norm": 0.8330617547035217,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.035,
      "step": 145
    },
    {
      "epoch": 0.5473289597000938,
      "grad_norm": 0.7836589217185974,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.9362,
      "step": 146
    },
    {
      "epoch": 0.5510777881911902,
      "grad_norm": 0.8202426433563232,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.9897,
      "step": 147
    },
    {
      "epoch": 0.5548266166822868,
      "grad_norm": 0.8087556958198547,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.9869,
      "step": 148
    },
    {
      "epoch": 0.5585754451733833,
      "grad_norm": 1.006156325340271,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.0094,
      "step": 149
    },
    {
      "epoch": 0.5623242736644799,
      "grad_norm": 1.302259087562561,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.076,
      "step": 150
    },
    {
      "epoch": 0.5623242736644799,
      "eval_loss": 0.9521539807319641,
      "eval_runtime": 20.5002,
      "eval_samples_per_second": 21.951,
      "eval_steps_per_second": 5.512,
      "step": 150
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.929295176669594e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}