{
  "best_metric": 1.1199445724487305,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.0802407221664995,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00040120361083249747,
      "grad_norm": 0.6669679284095764,
      "learning_rate": 1e-05,
      "loss": 3.3174,
      "step": 1
    },
    {
      "epoch": 0.00040120361083249747,
      "eval_loss": 2.958653450012207,
      "eval_runtime": 318.2208,
      "eval_samples_per_second": 13.192,
      "eval_steps_per_second": 3.3,
      "step": 1
    },
    {
      "epoch": 0.0008024072216649949,
      "grad_norm": 0.7321765422821045,
      "learning_rate": 2e-05,
      "loss": 3.3793,
      "step": 2
    },
    {
      "epoch": 0.0012036108324974925,
      "grad_norm": 0.7900415658950806,
      "learning_rate": 3e-05,
      "loss": 3.4988,
      "step": 3
    },
    {
      "epoch": 0.0016048144433299899,
      "grad_norm": 0.5777308940887451,
      "learning_rate": 4e-05,
      "loss": 2.7664,
      "step": 4
    },
    {
      "epoch": 0.0020060180541624875,
      "grad_norm": 0.5825851559638977,
      "learning_rate": 5e-05,
      "loss": 2.9569,
      "step": 5
    },
    {
      "epoch": 0.002407221664994985,
      "grad_norm": 0.6091576218605042,
      "learning_rate": 6e-05,
      "loss": 2.654,
      "step": 6
    },
    {
      "epoch": 0.0028084252758274826,
      "grad_norm": 0.7425055503845215,
      "learning_rate": 7e-05,
      "loss": 2.881,
      "step": 7
    },
    {
      "epoch": 0.0032096288866599798,
      "grad_norm": 0.6636602878570557,
      "learning_rate": 8e-05,
      "loss": 2.9286,
      "step": 8
    },
    {
      "epoch": 0.0036108324974924774,
      "grad_norm": 1.162257432937622,
      "learning_rate": 9e-05,
      "loss": 2.6507,
      "step": 9
    },
    {
      "epoch": 0.004012036108324975,
      "grad_norm": 1.0945292711257935,
      "learning_rate": 0.0001,
      "loss": 2.4989,
      "step": 10
    },
    {
      "epoch": 0.0044132397191574725,
      "grad_norm": 0.6690190434455872,
      "learning_rate": 9.999316524962345e-05,
      "loss": 2.5261,
      "step": 11
    },
    {
      "epoch": 0.00481444332998997,
      "grad_norm": 0.672607958316803,
      "learning_rate": 9.997266286704631e-05,
      "loss": 2.4882,
      "step": 12
    },
    {
      "epoch": 0.005215646940822468,
      "grad_norm": 0.7343330979347229,
      "learning_rate": 9.993849845741524e-05,
      "loss": 2.4481,
      "step": 13
    },
    {
      "epoch": 0.005616850551654965,
      "grad_norm": 0.6780744194984436,
      "learning_rate": 9.989068136093873e-05,
      "loss": 2.4699,
      "step": 14
    },
    {
      "epoch": 0.006018054162487462,
      "grad_norm": 0.5904457569122314,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.0998,
      "step": 15
    },
    {
      "epoch": 0.0064192577733199595,
      "grad_norm": 0.6801204681396484,
      "learning_rate": 9.975414512725057e-05,
      "loss": 2.1852,
      "step": 16
    },
    {
      "epoch": 0.006820461384152457,
      "grad_norm": 0.6831610798835754,
      "learning_rate": 9.966546331768191e-05,
      "loss": 2.1386,
      "step": 17
    },
    {
      "epoch": 0.007221664994984955,
      "grad_norm": 0.6511374711990356,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.7376,
      "step": 18
    },
    {
      "epoch": 0.007622868605817452,
      "grad_norm": 0.6357225179672241,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.6317,
      "step": 19
    },
    {
      "epoch": 0.00802407221664995,
      "grad_norm": 0.5412874817848206,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.4271,
      "step": 20
    },
    {
      "epoch": 0.008425275827482447,
      "grad_norm": 0.6024720668792725,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.7927,
      "step": 21
    },
    {
      "epoch": 0.008826479438314945,
      "grad_norm": 0.5297130346298218,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.5211,
      "step": 22
    },
    {
      "epoch": 0.009227683049147442,
      "grad_norm": 0.7351126670837402,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.7366,
      "step": 23
    },
    {
      "epoch": 0.00962888665997994,
      "grad_norm": 0.6614333987236023,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.7496,
      "step": 24
    },
    {
      "epoch": 0.010030090270812437,
      "grad_norm": 0.691881000995636,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.5191,
      "step": 25
    },
    {
      "epoch": 0.010431293881644935,
      "grad_norm": 0.6896193027496338,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.2835,
      "step": 26
    },
    {
      "epoch": 0.010832497492477432,
      "grad_norm": 0.6280005574226379,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.2201,
      "step": 27
    },
    {
      "epoch": 0.01123370110330993,
      "grad_norm": 0.7473313212394714,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.1415,
      "step": 28
    },
    {
      "epoch": 0.011634904714142427,
      "grad_norm": 0.6307004690170288,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.0427,
      "step": 29
    },
    {
      "epoch": 0.012036108324974924,
      "grad_norm": 0.5661408305168152,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.9848,
      "step": 30
    },
    {
      "epoch": 0.012437311935807422,
      "grad_norm": 0.5856786370277405,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.9406,
      "step": 31
    },
    {
      "epoch": 0.012838515546639919,
      "grad_norm": 0.7579771280288696,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.1825,
      "step": 32
    },
    {
      "epoch": 0.013239719157472418,
      "grad_norm": 0.559369683265686,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.9536,
      "step": 33
    },
    {
      "epoch": 0.013640922768304914,
      "grad_norm": 0.5556255578994751,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.9235,
      "step": 34
    },
    {
      "epoch": 0.014042126379137413,
      "grad_norm": 0.7395801544189453,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.0528,
      "step": 35
    },
    {
      "epoch": 0.01444332998996991,
      "grad_norm": 0.567768931388855,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.9248,
      "step": 36
    },
    {
      "epoch": 0.014844533600802408,
      "grad_norm": 0.6621676087379456,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.0275,
      "step": 37
    },
    {
      "epoch": 0.015245737211634905,
      "grad_norm": 0.6595890522003174,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.8947,
      "step": 38
    },
    {
      "epoch": 0.0156469408224674,
      "grad_norm": 0.5635279417037964,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.81,
      "step": 39
    },
    {
      "epoch": 0.0160481444332999,
      "grad_norm": 0.5657234787940979,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.7624,
      "step": 40
    },
    {
      "epoch": 0.016449348044132398,
      "grad_norm": 0.629128098487854,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.786,
      "step": 41
    },
    {
      "epoch": 0.016850551654964893,
      "grad_norm": 0.6042339205741882,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.7992,
      "step": 42
    },
    {
      "epoch": 0.01725175526579739,
      "grad_norm": 0.6492327451705933,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.8354,
      "step": 43
    },
    {
      "epoch": 0.01765295887662989,
      "grad_norm": 0.5606724619865417,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.6832,
      "step": 44
    },
    {
      "epoch": 0.01805416248746239,
      "grad_norm": 0.7098550796508789,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.7427,
      "step": 45
    },
    {
      "epoch": 0.018455366098294883,
      "grad_norm": 0.7635481953620911,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.8373,
      "step": 46
    },
    {
      "epoch": 0.018856569709127382,
      "grad_norm": 0.7095775604248047,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.6067,
      "step": 47
    },
    {
      "epoch": 0.01925777331995988,
      "grad_norm": 0.6480351090431213,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.6311,
      "step": 48
    },
    {
      "epoch": 0.01965897693079238,
      "grad_norm": 0.9735925197601318,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.7786,
      "step": 49
    },
    {
      "epoch": 0.020060180541624874,
      "grad_norm": 1.0782945156097412,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.5901,
      "step": 50
    },
    {
      "epoch": 0.020060180541624874,
      "eval_loss": 1.4300074577331543,
      "eval_runtime": 319.9718,
      "eval_samples_per_second": 13.12,
      "eval_steps_per_second": 3.282,
      "step": 50
    },
    {
      "epoch": 0.020461384152457372,
      "grad_norm": 0.7460092902183533,
      "learning_rate": 8.894386393810563e-05,
      "loss": 2.5858,
      "step": 51
    },
    {
      "epoch": 0.02086258776328987,
      "grad_norm": 0.668900191783905,
      "learning_rate": 8.842005554284296e-05,
      "loss": 2.564,
      "step": 52
    },
    {
      "epoch": 0.021263791374122366,
      "grad_norm": 0.5384716987609863,
      "learning_rate": 8.788574348801675e-05,
      "loss": 2.4562,
      "step": 53
    },
    {
      "epoch": 0.021664994984954864,
      "grad_norm": 0.43091005086898804,
      "learning_rate": 8.73410738492077e-05,
      "loss": 2.1191,
      "step": 54
    },
    {
      "epoch": 0.022066198595787363,
      "grad_norm": 0.4116343855857849,
      "learning_rate": 8.678619553365659e-05,
      "loss": 2.1816,
      "step": 55
    },
    {
      "epoch": 0.02246740220661986,
      "grad_norm": 0.42210501432418823,
      "learning_rate": 8.622126023955446e-05,
      "loss": 2.043,
      "step": 56
    },
    {
      "epoch": 0.022868605817452356,
      "grad_norm": 0.38796713948249817,
      "learning_rate": 8.564642241456986e-05,
      "loss": 2.0217,
      "step": 57
    },
    {
      "epoch": 0.023269809428284854,
      "grad_norm": 0.4110553562641144,
      "learning_rate": 8.506183921362443e-05,
      "loss": 2.0948,
      "step": 58
    },
    {
      "epoch": 0.023671013039117353,
      "grad_norm": 0.8085715174674988,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.5066,
      "step": 59
    },
    {
      "epoch": 0.024072216649949848,
      "grad_norm": 1.0500621795654297,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.2154,
      "step": 60
    },
    {
      "epoch": 0.024473420260782346,
      "grad_norm": 0.5011671185493469,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.8199,
      "step": 61
    },
    {
      "epoch": 0.024874623871614845,
      "grad_norm": 0.48888733983039856,
      "learning_rate": 8.262928807620843e-05,
      "loss": 2.0569,
      "step": 62
    },
    {
      "epoch": 0.025275827482447343,
      "grad_norm": 0.4736348092556,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.8595,
      "step": 63
    },
    {
      "epoch": 0.025677031093279838,
      "grad_norm": 0.4854435920715332,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.7749,
      "step": 64
    },
    {
      "epoch": 0.026078234704112337,
      "grad_norm": 0.48253872990608215,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.6403,
      "step": 65
    },
    {
      "epoch": 0.026479438314944835,
      "grad_norm": 0.49176353216171265,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.7806,
      "step": 66
    },
    {
      "epoch": 0.026880641925777334,
      "grad_norm": 0.473366916179657,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.4689,
      "step": 67
    },
    {
      "epoch": 0.02728184553660983,
      "grad_norm": 0.41739487648010254,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.3693,
      "step": 68
    },
    {
      "epoch": 0.027683049147442327,
      "grad_norm": 0.45353350043296814,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.3453,
      "step": 69
    },
    {
      "epoch": 0.028084252758274825,
      "grad_norm": 0.5225381255149841,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.399,
      "step": 70
    },
    {
      "epoch": 0.02848545636910732,
      "grad_norm": 0.4625832140445709,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.3805,
      "step": 71
    },
    {
      "epoch": 0.02888665997993982,
      "grad_norm": 0.4747093617916107,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.3489,
      "step": 72
    },
    {
      "epoch": 0.029287863590772317,
      "grad_norm": 0.4805883467197418,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.2853,
      "step": 73
    },
    {
      "epoch": 0.029689067201604816,
      "grad_norm": 0.4113385081291199,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.0318,
      "step": 74
    },
    {
      "epoch": 0.03009027081243731,
      "grad_norm": 0.4107489287853241,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.0268,
      "step": 75
    },
    {
      "epoch": 0.03049147442326981,
      "grad_norm": 0.4987661838531494,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.0678,
      "step": 76
    },
    {
      "epoch": 0.030892678034102308,
      "grad_norm": 0.4337654411792755,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.0321,
      "step": 77
    },
    {
      "epoch": 0.0312938816449348,
      "grad_norm": 0.5489122271537781,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.1425,
      "step": 78
    },
    {
      "epoch": 0.0316950852557673,
      "grad_norm": 0.45944860577583313,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.0744,
      "step": 79
    },
    {
      "epoch": 0.0320962888665998,
      "grad_norm": 0.5054852366447449,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.9376,
      "step": 80
    },
    {
      "epoch": 0.0324974924774323,
      "grad_norm": 0.43092572689056396,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.9343,
      "step": 81
    },
    {
      "epoch": 0.032898696088264796,
      "grad_norm": 0.43316012620925903,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.8464,
      "step": 82
    },
    {
      "epoch": 0.033299899699097295,
      "grad_norm": 0.4557117223739624,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.8745,
      "step": 83
    },
    {
      "epoch": 0.033701103309929786,
      "grad_norm": 0.4856351613998413,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.884,
      "step": 84
    },
    {
      "epoch": 0.034102306920762285,
      "grad_norm": 0.4982066750526428,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.8456,
      "step": 85
    },
    {
      "epoch": 0.03450351053159478,
      "grad_norm": 0.5404598712921143,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.9801,
      "step": 86
    },
    {
      "epoch": 0.03490471414242728,
      "grad_norm": 0.5297891497612,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.9028,
      "step": 87
    },
    {
      "epoch": 0.03530591775325978,
      "grad_norm": 0.5060041546821594,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.8043,
      "step": 88
    },
    {
      "epoch": 0.03570712136409228,
      "grad_norm": 0.4737092852592468,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.8111,
      "step": 89
    },
    {
      "epoch": 0.03610832497492478,
      "grad_norm": 0.46270066499710083,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.7353,
      "step": 90
    },
    {
      "epoch": 0.03650952858575727,
      "grad_norm": 0.507361888885498,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.7936,
      "step": 91
    },
    {
      "epoch": 0.03691073219658977,
      "grad_norm": 0.5811742544174194,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.7645,
      "step": 92
    },
    {
      "epoch": 0.037311935807422265,
      "grad_norm": 0.5755809545516968,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.7753,
      "step": 93
    },
    {
      "epoch": 0.037713139418254764,
      "grad_norm": 0.5196595191955566,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.6765,
      "step": 94
    },
    {
      "epoch": 0.03811434302908726,
      "grad_norm": 0.541668176651001,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.6652,
      "step": 95
    },
    {
      "epoch": 0.03851554663991976,
      "grad_norm": 0.5494287014007568,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.6345,
      "step": 96
    },
    {
      "epoch": 0.03891675025075226,
      "grad_norm": 0.4493606686592102,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.5375,
      "step": 97
    },
    {
      "epoch": 0.03931795386158476,
      "grad_norm": 0.4859435558319092,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.4783,
      "step": 98
    },
    {
      "epoch": 0.03971915747241725,
      "grad_norm": 0.8724290728569031,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.6409,
      "step": 99
    },
    {
      "epoch": 0.04012036108324975,
      "grad_norm": 1.1208146810531616,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.7023,
      "step": 100
    },
    {
      "epoch": 0.04012036108324975,
      "eval_loss": 1.2349821329116821,
      "eval_runtime": 320.8341,
      "eval_samples_per_second": 13.085,
      "eval_steps_per_second": 3.273,
      "step": 100
    },
    {
      "epoch": 0.040521564694082246,
      "grad_norm": 0.593967616558075,
      "learning_rate": 5.330452921628497e-05,
      "loss": 2.2783,
      "step": 101
    },
    {
      "epoch": 0.040922768304914744,
      "grad_norm": 0.5376036167144775,
      "learning_rate": 5.247918773366112e-05,
      "loss": 2.4485,
      "step": 102
    },
    {
      "epoch": 0.04132397191574724,
      "grad_norm": 0.41999951004981995,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.9955,
      "step": 103
    },
    {
      "epoch": 0.04172517552657974,
      "grad_norm": 0.38799425959587097,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.8047,
      "step": 104
    },
    {
      "epoch": 0.04212637913741224,
      "grad_norm": 0.3821459710597992,
      "learning_rate": 5e-05,
      "loss": 2.0009,
      "step": 105
    },
    {
      "epoch": 0.04252758274824473,
      "grad_norm": 0.36412644386291504,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.9527,
      "step": 106
    },
    {
      "epoch": 0.04292878635907723,
      "grad_norm": 0.3631185293197632,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.7935,
      "step": 107
    },
    {
      "epoch": 0.04332998996990973,
      "grad_norm": 0.3843073844909668,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.6368,
      "step": 108
    },
    {
      "epoch": 0.04373119358074223,
      "grad_norm": 1.2277952432632446,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.7248,
      "step": 109
    },
    {
      "epoch": 0.044132397191574725,
      "grad_norm": 0.6860705018043518,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.9059,
      "step": 110
    },
    {
      "epoch": 0.044533600802407224,
      "grad_norm": 0.3851066827774048,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.9783,
      "step": 111
    },
    {
      "epoch": 0.04493480441323972,
      "grad_norm": 0.3939480483531952,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.7066,
      "step": 112
    },
    {
      "epoch": 0.045336008024072214,
      "grad_norm": 0.39341041445732117,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.8135,
      "step": 113
    },
    {
      "epoch": 0.04573721163490471,
      "grad_norm": 0.43110090494155884,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.9389,
      "step": 114
    },
    {
      "epoch": 0.04613841524573721,
      "grad_norm": 0.37727785110473633,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.5708,
      "step": 115
    },
    {
      "epoch": 0.04653961885656971,
      "grad_norm": 0.3743235766887665,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.4699,
      "step": 116
    },
    {
      "epoch": 0.04694082246740221,
      "grad_norm": 0.3967227041721344,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.4696,
      "step": 117
    },
    {
      "epoch": 0.047342026078234706,
      "grad_norm": 0.4840269982814789,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.2232,
      "step": 118
    },
    {
      "epoch": 0.047743229689067204,
      "grad_norm": 0.40134578943252563,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.2688,
      "step": 119
    },
    {
      "epoch": 0.048144433299899696,
      "grad_norm": 0.42059680819511414,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.1811,
      "step": 120
    },
    {
      "epoch": 0.048545636910732194,
      "grad_norm": 0.4518502354621887,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.206,
      "step": 121
    },
    {
      "epoch": 0.04894684052156469,
      "grad_norm": 0.49335548281669617,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.4262,
      "step": 122
    },
    {
      "epoch": 0.04934804413239719,
      "grad_norm": 0.44594264030456543,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.2665,
      "step": 123
    },
    {
      "epoch": 0.04974924774322969,
      "grad_norm": 0.4851684272289276,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.1955,
      "step": 124
    },
    {
      "epoch": 0.05015045135406219,
      "grad_norm": 0.46362921595573425,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.1405,
      "step": 125
    },
    {
      "epoch": 0.050551654964894686,
      "grad_norm": 0.4825708270072937,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.0892,
      "step": 126
    },
    {
      "epoch": 0.050952858575727185,
      "grad_norm": 0.4526834487915039,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.9943,
      "step": 127
    },
    {
      "epoch": 0.051354062186559676,
      "grad_norm": 0.42253831028938293,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.8304,
      "step": 128
    },
    {
      "epoch": 0.051755265797392175,
      "grad_norm": 0.5022033452987671,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.9545,
      "step": 129
    },
    {
      "epoch": 0.05215646940822467,
      "grad_norm": 0.4628879427909851,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.823,
      "step": 130
    },
    {
      "epoch": 0.05255767301905717,
      "grad_norm": 0.5029376149177551,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.8687,
      "step": 131
    },
    {
      "epoch": 0.05295887662988967,
      "grad_norm": 0.5153740644454956,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.897,
      "step": 132
    },
    {
      "epoch": 0.05336008024072217,
      "grad_norm": 0.4819236695766449,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.8503,
      "step": 133
    },
    {
      "epoch": 0.05376128385155467,
      "grad_norm": 0.4883153438568115,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.8159,
      "step": 134
    },
    {
      "epoch": 0.05416248746238716,
      "grad_norm": 0.5309092402458191,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.9678,
      "step": 135
    },
    {
      "epoch": 0.05456369107321966,
      "grad_norm": 0.4953545928001404,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.7786,
      "step": 136
    },
    {
      "epoch": 0.054964894684052155,
      "grad_norm": 0.564425528049469,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.9306,
      "step": 137
    },
    {
      "epoch": 0.055366098294884654,
      "grad_norm": 0.4907301664352417,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.8145,
      "step": 138
    },
    {
      "epoch": 0.05576730190571715,
      "grad_norm": 0.476572185754776,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.7392,
      "step": 139
    },
    {
      "epoch": 0.05616850551654965,
      "grad_norm": 0.5938035845756531,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.8439,
      "step": 140
    },
    {
      "epoch": 0.05656970912738215,
      "grad_norm": 0.47795119881629944,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.8043,
      "step": 141
    },
    {
      "epoch": 0.05697091273821464,
      "grad_norm": 0.43849867582321167,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.6911,
      "step": 142
    },
    {
      "epoch": 0.05737211634904714,
      "grad_norm": 0.5385690927505493,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7205,
      "step": 143
    },
    {
      "epoch": 0.05777331995987964,
      "grad_norm": 0.4803493916988373,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.5661,
      "step": 144
    },
    {
      "epoch": 0.058174523570712136,
      "grad_norm": 0.5465977787971497,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.7099,
      "step": 145
    },
    {
      "epoch": 0.058575727181544635,
      "grad_norm": 0.5279889702796936,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.6579,
      "step": 146
    },
    {
      "epoch": 0.05897693079237713,
      "grad_norm": 0.46241751313209534,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.4422,
      "step": 147
    },
    {
      "epoch": 0.05937813440320963,
      "grad_norm": 0.5649749040603638,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.5902,
      "step": 148
    },
    {
      "epoch": 0.05977933801404212,
      "grad_norm": 0.8206795454025269,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.6965,
      "step": 149
    },
    {
      "epoch": 0.06018054162487462,
      "grad_norm": 0.8265851140022278,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.3014,
      "step": 150
    },
    {
      "epoch": 0.06018054162487462,
      "eval_loss": 1.1492105722427368,
      "eval_runtime": 321.1454,
      "eval_samples_per_second": 13.072,
      "eval_steps_per_second": 3.27,
      "step": 150
    },
    {
      "epoch": 0.06058174523570712,
      "grad_norm": 0.4687737822532654,
      "learning_rate": 1.553232954407171e-05,
      "loss": 2.2184,
      "step": 151
    },
    {
      "epoch": 0.06098294884653962,
      "grad_norm": 0.45375385880470276,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 2.106,
      "step": 152
    },
    {
      "epoch": 0.06138415245737212,
      "grad_norm": 0.3856009244918823,
      "learning_rate": 1.435357758543015e-05,
      "loss": 2.0607,
      "step": 153
    },
    {
      "epoch": 0.061785356068204615,
      "grad_norm": 0.41044384241104126,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.8568,
      "step": 154
    },
    {
      "epoch": 0.062186559679037114,
      "grad_norm": 0.36708319187164307,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.8734,
      "step": 155
    },
    {
      "epoch": 0.0625877632898696,
      "grad_norm": 0.35161256790161133,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.8056,
      "step": 156
    },
    {
      "epoch": 0.0629889669007021,
      "grad_norm": 0.34521928429603577,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.5235,
      "step": 157
    },
    {
      "epoch": 0.0633901705115346,
      "grad_norm": 0.3890172839164734,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.8295,
      "step": 158
    },
    {
      "epoch": 0.0637913741223671,
      "grad_norm": 1.5498108863830566,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.8973,
      "step": 159
    },
    {
      "epoch": 0.0641925777331996,
      "grad_norm": 1.5455256700515747,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.7668,
      "step": 160
    },
    {
      "epoch": 0.0645937813440321,
      "grad_norm": 0.677179217338562,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.2803,
      "step": 161
    },
    {
      "epoch": 0.0649949849548646,
      "grad_norm": 0.4167575240135193,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.8435,
      "step": 162
    },
    {
      "epoch": 0.0653961885656971,
      "grad_norm": 0.44335922598838806,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.7009,
      "step": 163
    },
    {
      "epoch": 0.06579739217652959,
      "grad_norm": 0.45982488989830017,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.6857,
      "step": 164
    },
    {
      "epoch": 0.06619859578736209,
      "grad_norm": 0.44522663950920105,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.5996,
      "step": 165
    },
    {
      "epoch": 0.06659979939819459,
      "grad_norm": 0.47833219170570374,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.6294,
      "step": 166
    },
    {
      "epoch": 0.06700100300902709,
      "grad_norm": 0.48346447944641113,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.3198,
      "step": 167
    },
    {
      "epoch": 0.06740220661985957,
      "grad_norm": 0.47792771458625793,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.315,
      "step": 168
    },
    {
      "epoch": 0.06780341023069207,
      "grad_norm": 0.47757798433303833,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.2415,
      "step": 169
    },
    {
      "epoch": 0.06820461384152457,
      "grad_norm": 0.4740765392780304,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.2926,
      "step": 170
    },
    {
      "epoch": 0.06860581745235707,
      "grad_norm": 0.5008906722068787,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.391,
      "step": 171
    },
    {
      "epoch": 0.06900702106318957,
      "grad_norm": 0.5195507407188416,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.3142,
      "step": 172
    },
    {
      "epoch": 0.06940822467402206,
      "grad_norm": 0.48969268798828125,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.1219,
      "step": 173
    },
    {
      "epoch": 0.06980942828485456,
      "grad_norm": 0.4899652898311615,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.0391,
      "step": 174
    },
    {
      "epoch": 0.07021063189568706,
      "grad_norm": 0.49886512756347656,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.0571,
      "step": 175
    },
    {
      "epoch": 0.07061183550651956,
      "grad_norm": 0.5899563431739807,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.1876,
      "step": 176
    },
    {
      "epoch": 0.07101303911735206,
      "grad_norm": 0.5365498661994934,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.0978,
      "step": 177
    },
    {
      "epoch": 0.07141424272818456,
      "grad_norm": 0.48978671431541443,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.9838,
      "step": 178
    },
    {
      "epoch": 0.07181544633901706,
      "grad_norm": 0.5520434975624084,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.0966,
      "step": 179
    },
    {
      "epoch": 0.07221664994984955,
      "grad_norm": 0.4561725854873657,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.8467,
      "step": 180
    },
    {
      "epoch": 0.07261785356068205,
      "grad_norm": 0.4608388841152191,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.7376,
      "step": 181
    },
    {
      "epoch": 0.07301905717151454,
      "grad_norm": 0.4796012341976166,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.856,
      "step": 182
    },
    {
      "epoch": 0.07342026078234704,
      "grad_norm": 0.5055034756660461,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.857,
      "step": 183
    },
    {
      "epoch": 0.07382146439317953,
      "grad_norm": 0.515639066696167,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.9017,
      "step": 184
    },
    {
      "epoch": 0.07422266800401203,
      "grad_norm": 0.5006952881813049,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.877,
      "step": 185
    },
    {
      "epoch": 0.07462387161484453,
      "grad_norm": 0.479093462228775,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.7399,
      "step": 186
    },
    {
      "epoch": 0.07502507522567703,
      "grad_norm": 0.4846677780151367,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.796,
      "step": 187
    },
    {
      "epoch": 0.07542627883650953,
      "grad_norm": 0.5465626120567322,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.7975,
      "step": 188
    },
    {
      "epoch": 0.07582748244734203,
      "grad_norm": 0.522148609161377,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.8269,
      "step": 189
    },
    {
      "epoch": 0.07622868605817452,
      "grad_norm": 0.514514684677124,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.7389,
      "step": 190
    },
    {
      "epoch": 0.07662988966900702,
      "grad_norm": 0.4962550401687622,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.7274,
      "step": 191
    },
    {
      "epoch": 0.07703109327983952,
      "grad_norm": 0.4189755916595459,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.6623,
      "step": 192
    },
    {
      "epoch": 0.07743229689067202,
      "grad_norm": 0.5472469329833984,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.7305,
      "step": 193
    },
    {
      "epoch": 0.07783350050150452,
      "grad_norm": 0.4706983268260956,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.6205,
      "step": 194
    },
    {
      "epoch": 0.07823470411233702,
      "grad_norm": 0.6054412126541138,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.7063,
      "step": 195
    },
    {
      "epoch": 0.07863590772316952,
      "grad_norm": 0.5226098299026489,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.5694,
      "step": 196
    },
    {
      "epoch": 0.079037111334002,
      "grad_norm": 0.553214967250824,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.6191,
      "step": 197
    },
    {
      "epoch": 0.0794383149448345,
      "grad_norm": 0.7137875556945801,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.6411,
      "step": 198
    },
    {
      "epoch": 0.079839518555667,
      "grad_norm": 0.5622249245643616,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.4585,
      "step": 199
    },
    {
      "epoch": 0.0802407221664995,
      "grad_norm": 0.7931567430496216,
      "learning_rate": 0.0,
      "loss": 0.4665,
      "step": 200
    },
    {
      "epoch": 0.0802407221664995,
      "eval_loss": 1.1199445724487305,
      "eval_runtime": 320.3026,
      "eval_samples_per_second": 13.106,
      "eval_steps_per_second": 3.278,
      "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": 2.847288530609111e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}