{
  "best_metric": 1.9195754528045654,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.03191701575902653,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015958507879513265,
      "grad_norm": 0.5689706206321716,
      "learning_rate": 1e-05,
      "loss": 2.3312,
      "step": 1
    },
    {
      "epoch": 0.00015958507879513265,
      "eval_loss": 2.3574635982513428,
      "eval_runtime": 312.8431,
      "eval_samples_per_second": 33.736,
      "eval_steps_per_second": 8.436,
      "step": 1
    },
    {
      "epoch": 0.0003191701575902653,
      "grad_norm": 0.7195130586624146,
      "learning_rate": 2e-05,
      "loss": 2.0797,
      "step": 2
    },
    {
      "epoch": 0.00047875523638539794,
      "grad_norm": 0.8184091448783875,
      "learning_rate": 3e-05,
      "loss": 2.3107,
      "step": 3
    },
    {
      "epoch": 0.0006383403151805306,
      "grad_norm": 0.7070271372795105,
      "learning_rate": 4e-05,
      "loss": 2.0782,
      "step": 4
    },
    {
      "epoch": 0.0007979253939756633,
      "grad_norm": 0.6683346629142761,
      "learning_rate": 5e-05,
      "loss": 2.1288,
      "step": 5
    },
    {
      "epoch": 0.0009575104727707959,
      "grad_norm": 0.7057511210441589,
      "learning_rate": 6e-05,
      "loss": 2.2192,
      "step": 6
    },
    {
      "epoch": 0.0011170955515659286,
      "grad_norm": 0.7663440704345703,
      "learning_rate": 7e-05,
      "loss": 2.0143,
      "step": 7
    },
    {
      "epoch": 0.0012766806303610612,
      "grad_norm": 0.6650269627571106,
      "learning_rate": 8e-05,
      "loss": 1.975,
      "step": 8
    },
    {
      "epoch": 0.001436265709156194,
      "grad_norm": 0.6126298904418945,
      "learning_rate": 9e-05,
      "loss": 1.9482,
      "step": 9
    },
    {
      "epoch": 0.0015958507879513266,
      "grad_norm": 0.5007034540176392,
      "learning_rate": 0.0001,
      "loss": 2.0029,
      "step": 10
    },
    {
      "epoch": 0.0017554358667464592,
      "grad_norm": 0.5009804964065552,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.8719,
      "step": 11
    },
    {
      "epoch": 0.0019150209455415918,
      "grad_norm": 0.48847904801368713,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.899,
      "step": 12
    },
    {
      "epoch": 0.0020746060243367246,
      "grad_norm": 0.46820786595344543,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.8888,
      "step": 13
    },
    {
      "epoch": 0.002234191103131857,
      "grad_norm": 0.46582266688346863,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.9258,
      "step": 14
    },
    {
      "epoch": 0.0023937761819269898,
      "grad_norm": 0.4986919164657593,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.8704,
      "step": 15
    },
    {
      "epoch": 0.0025533612607221224,
      "grad_norm": 0.4819354712963104,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.8824,
      "step": 16
    },
    {
      "epoch": 0.002712946339517255,
      "grad_norm": 0.4644220173358917,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.8658,
      "step": 17
    },
    {
      "epoch": 0.002872531418312388,
      "grad_norm": 0.4527943432331085,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.8965,
      "step": 18
    },
    {
      "epoch": 0.0030321164971075206,
      "grad_norm": 0.4372904896736145,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.9967,
      "step": 19
    },
    {
      "epoch": 0.003191701575902653,
      "grad_norm": 0.4805839955806732,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.9829,
      "step": 20
    },
    {
      "epoch": 0.0033512866546977858,
      "grad_norm": 0.4864383637905121,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.996,
      "step": 21
    },
    {
      "epoch": 0.0035108717334929184,
      "grad_norm": 0.46260684728622437,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.9218,
      "step": 22
    },
    {
      "epoch": 0.003670456812288051,
      "grad_norm": 0.45888015627861023,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.9602,
      "step": 23
    },
    {
      "epoch": 0.0038300418910831835,
      "grad_norm": 0.44635823369026184,
      "learning_rate": 9.86663298624003e-05,
      "loss": 2.0009,
      "step": 24
    },
    {
      "epoch": 0.003989626969878316,
      "grad_norm": 0.4354296922683716,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.8565,
      "step": 25
    },
    {
      "epoch": 0.004149212048673449,
      "grad_norm": 0.42106199264526367,
      "learning_rate": 9.826044551386744e-05,
      "loss": 2.0653,
      "step": 26
    },
    {
      "epoch": 0.004308797127468581,
      "grad_norm": 0.4422471225261688,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.9638,
      "step": 27
    },
    {
      "epoch": 0.004468382206263714,
      "grad_norm": 0.45815718173980713,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.983,
      "step": 28
    },
    {
      "epoch": 0.004627967285058847,
      "grad_norm": 0.4270409941673279,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.8913,
      "step": 29
    },
    {
      "epoch": 0.0047875523638539795,
      "grad_norm": 0.4948173463344574,
      "learning_rate": 9.729086208503174e-05,
      "loss": 2.0674,
      "step": 30
    },
    {
      "epoch": 0.0049471374426491126,
      "grad_norm": 0.4433998167514801,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.9556,
      "step": 31
    },
    {
      "epoch": 0.005106722521444245,
      "grad_norm": 0.4293866455554962,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.6452,
      "step": 32
    },
    {
      "epoch": 0.005266307600239378,
      "grad_norm": 0.43146762251853943,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.8313,
      "step": 33
    },
    {
      "epoch": 0.00542589267903451,
      "grad_norm": 0.4376092255115509,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.8412,
      "step": 34
    },
    {
      "epoch": 0.005585477757829643,
      "grad_norm": 0.45436200499534607,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.9347,
      "step": 35
    },
    {
      "epoch": 0.005745062836624776,
      "grad_norm": 0.4766467809677124,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.2512,
      "step": 36
    },
    {
      "epoch": 0.005904647915419908,
      "grad_norm": 0.45935651659965515,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.95,
      "step": 37
    },
    {
      "epoch": 0.006064232994215041,
      "grad_norm": 0.44688135385513306,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.9407,
      "step": 38
    },
    {
      "epoch": 0.006223818073010173,
      "grad_norm": 0.4399092197418213,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.1975,
      "step": 39
    },
    {
      "epoch": 0.006383403151805306,
      "grad_norm": 0.42060983180999756,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.9614,
      "step": 40
    },
    {
      "epoch": 0.0065429882306004385,
      "grad_norm": 0.48404574394226074,
      "learning_rate": 9.357421218136386e-05,
      "loss": 2.0166,
      "step": 41
    },
    {
      "epoch": 0.0067025733093955715,
      "grad_norm": 0.5269433259963989,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.1636,
      "step": 42
    },
    {
      "epoch": 0.0068621583881907046,
      "grad_norm": 0.4586423933506012,
      "learning_rate": 9.273963562927695e-05,
      "loss": 2.3141,
      "step": 43
    },
    {
      "epoch": 0.007021743466985837,
      "grad_norm": 0.4473651051521301,
      "learning_rate": 9.230476262104677e-05,
      "loss": 2.0192,
      "step": 44
    },
    {
      "epoch": 0.00718132854578097,
      "grad_norm": 0.4448000490665436,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.2572,
      "step": 45
    },
    {
      "epoch": 0.007340913624576102,
      "grad_norm": 0.4458993971347809,
      "learning_rate": 9.140044155740101e-05,
      "loss": 2.1632,
      "step": 46
    },
    {
      "epoch": 0.007500498703371235,
      "grad_norm": 0.48745936155319214,
      "learning_rate": 9.093124073433463e-05,
      "loss": 2.0038,
      "step": 47
    },
    {
      "epoch": 0.007660083782166367,
      "grad_norm": 0.4828518331050873,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.1621,
      "step": 48
    },
    {
      "epoch": 0.0078196688609615,
      "grad_norm": 0.4804685413837433,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.0477,
      "step": 49
    },
    {
      "epoch": 0.007979253939756632,
      "grad_norm": 0.5345922112464905,
      "learning_rate": 8.945702546981969e-05,
      "loss": 2.1869,
      "step": 50
    },
    {
      "epoch": 0.007979253939756632,
      "eval_loss": 1.9438155889511108,
      "eval_runtime": 314.4038,
      "eval_samples_per_second": 33.568,
      "eval_steps_per_second": 8.394,
      "step": 50
    },
    {
      "epoch": 0.008138839018551766,
      "grad_norm": 0.43491092324256897,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.9212,
      "step": 51
    },
    {
      "epoch": 0.008298424097346898,
      "grad_norm": 0.42076626420021057,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.9896,
      "step": 52
    },
    {
      "epoch": 0.00845800917614203,
      "grad_norm": 0.43394774198532104,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.9284,
      "step": 53
    },
    {
      "epoch": 0.008617594254937163,
      "grad_norm": 0.41931065917015076,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.8968,
      "step": 54
    },
    {
      "epoch": 0.008777179333732297,
      "grad_norm": 0.4129103422164917,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.7485,
      "step": 55
    },
    {
      "epoch": 0.008936764412527429,
      "grad_norm": 0.39821457862854004,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.961,
      "step": 56
    },
    {
      "epoch": 0.00909634949132256,
      "grad_norm": 0.3745400011539459,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.8191,
      "step": 57
    },
    {
      "epoch": 0.009255934570117695,
      "grad_norm": 0.4160624146461487,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.9735,
      "step": 58
    },
    {
      "epoch": 0.009415519648912827,
      "grad_norm": 0.4110680818557739,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.9014,
      "step": 59
    },
    {
      "epoch": 0.009575104727707959,
      "grad_norm": 0.3943556845188141,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.6977,
      "step": 60
    },
    {
      "epoch": 0.009734689806503091,
      "grad_norm": 0.42828434705734253,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.7484,
      "step": 61
    },
    {
      "epoch": 0.009894274885298225,
      "grad_norm": 0.4538355767726898,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.8596,
      "step": 62
    },
    {
      "epoch": 0.010053859964093357,
      "grad_norm": 0.429342657327652,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.6079,
      "step": 63
    },
    {
      "epoch": 0.01021344504288849,
      "grad_norm": 0.4291363060474396,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.8463,
      "step": 64
    },
    {
      "epoch": 0.010373030121683623,
      "grad_norm": 0.4246358275413513,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.9376,
      "step": 65
    },
    {
      "epoch": 0.010532615200478756,
      "grad_norm": 0.3940020203590393,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.866,
      "step": 66
    },
    {
      "epoch": 0.010692200279273888,
      "grad_norm": 0.43030932545661926,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.7682,
      "step": 67
    },
    {
      "epoch": 0.01085178535806902,
      "grad_norm": 0.4225391447544098,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.9559,
      "step": 68
    },
    {
      "epoch": 0.011011370436864154,
      "grad_norm": 0.43834245204925537,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.919,
      "step": 69
    },
    {
      "epoch": 0.011170955515659286,
      "grad_norm": 0.3902847468852997,
      "learning_rate": 7.734740790612136e-05,
      "loss": 2.1008,
      "step": 70
    },
    {
      "epoch": 0.011330540594454418,
      "grad_norm": 0.43243396282196045,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.8066,
      "step": 71
    },
    {
      "epoch": 0.011490125673249552,
      "grad_norm": 0.3974666893482208,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.8482,
      "step": 72
    },
    {
      "epoch": 0.011649710752044684,
      "grad_norm": 0.4016903042793274,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.8938,
      "step": 73
    },
    {
      "epoch": 0.011809295830839816,
      "grad_norm": 0.43187522888183594,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.9788,
      "step": 74
    },
    {
      "epoch": 0.011968880909634948,
      "grad_norm": 0.40666618943214417,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.9411,
      "step": 75
    },
    {
      "epoch": 0.012128465988430082,
      "grad_norm": 0.43544089794158936,
      "learning_rate": 7.30670581489344e-05,
      "loss": 2.0836,
      "step": 76
    },
    {
      "epoch": 0.012288051067225214,
      "grad_norm": 0.4467950165271759,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.9766,
      "step": 77
    },
    {
      "epoch": 0.012447636146020347,
      "grad_norm": 0.41116830706596375,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.972,
      "step": 78
    },
    {
      "epoch": 0.01260722122481548,
      "grad_norm": 0.4361439049243927,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.8263,
      "step": 79
    },
    {
      "epoch": 0.012766806303610613,
      "grad_norm": 0.425064355134964,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.8673,
      "step": 80
    },
    {
      "epoch": 0.012926391382405745,
      "grad_norm": 0.433441698551178,
      "learning_rate": 6.932495846462261e-05,
      "loss": 2.009,
      "step": 81
    },
    {
      "epoch": 0.013085976461200877,
      "grad_norm": 0.40752309560775757,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.8884,
      "step": 82
    },
    {
      "epoch": 0.013245561539996011,
      "grad_norm": 0.44144394993782043,
      "learning_rate": 6.778969234612584e-05,
      "loss": 2.1434,
      "step": 83
    },
    {
      "epoch": 0.013405146618791143,
      "grad_norm": 0.5229665637016296,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.8876,
      "step": 84
    },
    {
      "epoch": 0.013564731697586275,
      "grad_norm": 0.466818243265152,
      "learning_rate": 6.623497346023418e-05,
      "loss": 2.0089,
      "step": 85
    },
    {
      "epoch": 0.013724316776381409,
      "grad_norm": 0.4119611084461212,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.9623,
      "step": 86
    },
    {
      "epoch": 0.013883901855176541,
      "grad_norm": 0.44634708762168884,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.9837,
      "step": 87
    },
    {
      "epoch": 0.014043486933971673,
      "grad_norm": 0.4318132698535919,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.9896,
      "step": 88
    },
    {
      "epoch": 0.014203072012766806,
      "grad_norm": 0.41148316860198975,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.9718,
      "step": 89
    },
    {
      "epoch": 0.01436265709156194,
      "grad_norm": 0.4657785892486572,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.9325,
      "step": 90
    },
    {
      "epoch": 0.014522242170357072,
      "grad_norm": 0.4558035731315613,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.9629,
      "step": 91
    },
    {
      "epoch": 0.014681827249152204,
      "grad_norm": 0.40718722343444824,
      "learning_rate": 6.066498153718735e-05,
      "loss": 2.1382,
      "step": 92
    },
    {
      "epoch": 0.014841412327947338,
      "grad_norm": 0.4715941250324249,
      "learning_rate": 5.985585137257401e-05,
      "loss": 2.143,
      "step": 93
    },
    {
      "epoch": 0.01500099740674247,
      "grad_norm": 0.4530062675476074,
      "learning_rate": 5.90440267166055e-05,
      "loss": 2.2169,
      "step": 94
    },
    {
      "epoch": 0.015160582485537602,
      "grad_norm": 0.44678160548210144,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 2.116,
      "step": 95
    },
    {
      "epoch": 0.015320167564332734,
      "grad_norm": 0.4804902672767639,
      "learning_rate": 5.74131823855921e-05,
      "loss": 2.0782,
      "step": 96
    },
    {
      "epoch": 0.015479752643127868,
      "grad_norm": 0.43269574642181396,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 2.0122,
      "step": 97
    },
    {
      "epoch": 0.015639337721923,
      "grad_norm": 0.46972429752349854,
      "learning_rate": 5.577423184847932e-05,
      "loss": 2.1773,
      "step": 98
    },
    {
      "epoch": 0.015798922800718134,
      "grad_norm": 0.45085468888282776,
      "learning_rate": 5.495227651252315e-05,
      "loss": 2.1888,
      "step": 99
    },
    {
      "epoch": 0.015958507879513265,
      "grad_norm": 0.5057016015052795,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 2.3141,
      "step": 100
    },
    {
      "epoch": 0.015958507879513265,
      "eval_loss": 1.9309347867965698,
      "eval_runtime": 314.8332,
      "eval_samples_per_second": 33.523,
      "eval_steps_per_second": 8.382,
      "step": 100
    },
    {
      "epoch": 0.0161180929583084,
      "grad_norm": 0.40853074193000793,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.7661,
      "step": 101
    },
    {
      "epoch": 0.016277678037103532,
      "grad_norm": 0.38783347606658936,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.8735,
      "step": 102
    },
    {
      "epoch": 0.016437263115898663,
      "grad_norm": 0.4041440486907959,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.7034,
      "step": 103
    },
    {
      "epoch": 0.016596848194693797,
      "grad_norm": 0.4036378562450409,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.8266,
      "step": 104
    },
    {
      "epoch": 0.016756433273488927,
      "grad_norm": 0.4113844037055969,
      "learning_rate": 5e-05,
      "loss": 1.7431,
      "step": 105
    },
    {
      "epoch": 0.01691601835228406,
      "grad_norm": 0.3834592401981354,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.6634,
      "step": 106
    },
    {
      "epoch": 0.017075603431079195,
      "grad_norm": 0.38620176911354065,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.7997,
      "step": 107
    },
    {
      "epoch": 0.017235188509874325,
      "grad_norm": 0.4023447036743164,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.9197,
      "step": 108
    },
    {
      "epoch": 0.01739477358866946,
      "grad_norm": 0.392505019903183,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.734,
      "step": 109
    },
    {
      "epoch": 0.017554358667464593,
      "grad_norm": 0.4143497943878174,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.8531,
      "step": 110
    },
    {
      "epoch": 0.017713943746259724,
      "grad_norm": 0.38709503412246704,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.7757,
      "step": 111
    },
    {
      "epoch": 0.017873528825054857,
      "grad_norm": 0.3901420533657074,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 2.0119,
      "step": 112
    },
    {
      "epoch": 0.01803311390384999,
      "grad_norm": 0.4669758081436157,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.8437,
      "step": 113
    },
    {
      "epoch": 0.01819269898264512,
      "grad_norm": 0.4631560146808624,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.9078,
      "step": 114
    },
    {
      "epoch": 0.018352284061440256,
      "grad_norm": 0.401100754737854,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.8856,
      "step": 115
    },
    {
      "epoch": 0.01851186914023539,
      "grad_norm": 0.4044717848300934,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.7542,
      "step": 116
    },
    {
      "epoch": 0.01867145421903052,
      "grad_norm": 0.412636935710907,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.776,
      "step": 117
    },
    {
      "epoch": 0.018831039297825654,
      "grad_norm": 0.4192257821559906,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.948,
      "step": 118
    },
    {
      "epoch": 0.018990624376620784,
      "grad_norm": 0.4110755920410156,
      "learning_rate": 3.852880399766243e-05,
      "loss": 2.087,
      "step": 119
    },
    {
      "epoch": 0.019150209455415918,
      "grad_norm": 0.42615073919296265,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.9849,
      "step": 120
    },
    {
      "epoch": 0.019309794534211052,
      "grad_norm": 0.4543478488922119,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 2.0077,
      "step": 121
    },
    {
      "epoch": 0.019469379613006182,
      "grad_norm": 0.41868171095848083,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.9363,
      "step": 122
    },
    {
      "epoch": 0.019628964691801316,
      "grad_norm": 0.40597444772720337,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.9942,
      "step": 123
    },
    {
      "epoch": 0.01978854977059645,
      "grad_norm": 0.40744879841804504,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.8368,
      "step": 124
    },
    {
      "epoch": 0.01994813484939158,
      "grad_norm": 0.4228390157222748,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.8297,
      "step": 125
    },
    {
      "epoch": 0.020107719928186715,
      "grad_norm": 0.4017251133918762,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.7046,
      "step": 126
    },
    {
      "epoch": 0.02026730500698185,
      "grad_norm": 0.45132604241371155,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.7563,
      "step": 127
    },
    {
      "epoch": 0.02042689008577698,
      "grad_norm": 0.3831186294555664,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.9197,
      "step": 128
    },
    {
      "epoch": 0.020586475164572113,
      "grad_norm": 0.41187921166419983,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.9798,
      "step": 129
    },
    {
      "epoch": 0.020746060243367247,
      "grad_norm": 0.42234599590301514,
      "learning_rate": 2.991522876735154e-05,
      "loss": 2.0938,
      "step": 130
    },
    {
      "epoch": 0.020905645322162377,
      "grad_norm": 0.4180166721343994,
      "learning_rate": 2.916090697523549e-05,
      "loss": 2.0518,
      "step": 131
    },
    {
      "epoch": 0.02106523040095751,
      "grad_norm": 0.4246877431869507,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 2.0585,
      "step": 132
    },
    {
      "epoch": 0.02122481547975264,
      "grad_norm": 0.4201193153858185,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.835,
      "step": 133
    },
    {
      "epoch": 0.021384400558547775,
      "grad_norm": 0.42230916023254395,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.8637,
      "step": 134
    },
    {
      "epoch": 0.02154398563734291,
      "grad_norm": 0.4284318685531616,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 2.0362,
      "step": 135
    },
    {
      "epoch": 0.02170357071613804,
      "grad_norm": 0.4159673750400543,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.7596,
      "step": 136
    },
    {
      "epoch": 0.021863155794933174,
      "grad_norm": 0.4322865903377533,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.9601,
      "step": 137
    },
    {
      "epoch": 0.022022740873728307,
      "grad_norm": 0.42884334921836853,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.8796,
      "step": 138
    },
    {
      "epoch": 0.022182325952523438,
      "grad_norm": 0.4259020686149597,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 2.0447,
      "step": 139
    },
    {
      "epoch": 0.022341911031318572,
      "grad_norm": 0.42449700832366943,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 2.0124,
      "step": 140
    },
    {
      "epoch": 0.022501496110113706,
      "grad_norm": 0.42931950092315674,
      "learning_rate": 2.196424713241637e-05,
      "loss": 2.1674,
      "step": 141
    },
    {
      "epoch": 0.022661081188908836,
      "grad_norm": 0.4168529808521271,
      "learning_rate": 2.128356686585282e-05,
      "loss": 2.0251,
      "step": 142
    },
    {
      "epoch": 0.02282066626770397,
      "grad_norm": 0.46725931763648987,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.1668,
      "step": 143
    },
    {
      "epoch": 0.022980251346499104,
      "grad_norm": 0.4844752848148346,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 2.0442,
      "step": 144
    },
    {
      "epoch": 0.023139836425294234,
      "grad_norm": 0.47044143080711365,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.8913,
      "step": 145
    },
    {
      "epoch": 0.023299421504089368,
      "grad_norm": 0.48870766162872314,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 2.3871,
      "step": 146
    },
    {
      "epoch": 0.0234590065828845,
      "grad_norm": 0.46377524733543396,
      "learning_rate": 1.800157297483417e-05,
      "loss": 2.1109,
      "step": 147
    },
    {
      "epoch": 0.023618591661679633,
      "grad_norm": 0.508398175239563,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.9995,
      "step": 148
    },
    {
      "epoch": 0.023778176740474766,
      "grad_norm": 0.4374549984931946,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 2.3447,
      "step": 149
    },
    {
      "epoch": 0.023937761819269897,
      "grad_norm": 0.5963560938835144,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 2.1833,
      "step": 150
    },
    {
      "epoch": 0.023937761819269897,
      "eval_loss": 1.9195754528045654,
      "eval_runtime": 314.3337,
      "eval_samples_per_second": 33.576,
      "eval_steps_per_second": 8.396,
      "step": 150
    },
    {
      "epoch": 0.02409734689806503,
      "grad_norm": 0.40311476588249207,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.772,
      "step": 151
    },
    {
      "epoch": 0.024256931976860165,
      "grad_norm": 0.44252851605415344,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.866,
      "step": 152
    },
    {
      "epoch": 0.024416517055655295,
      "grad_norm": 0.3997209966182709,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.8959,
      "step": 153
    },
    {
      "epoch": 0.02457610213445043,
      "grad_norm": 0.38131818175315857,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 2.0007,
      "step": 154
    },
    {
      "epoch": 0.024735687213245563,
      "grad_norm": 0.37809935212135315,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.7624,
      "step": 155
    },
    {
      "epoch": 0.024895272292040693,
      "grad_norm": 0.4161069989204407,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.7895,
      "step": 156
    },
    {
      "epoch": 0.025054857370835827,
      "grad_norm": 0.40481632947921753,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.7786,
      "step": 157
    },
    {
      "epoch": 0.02521444244963096,
      "grad_norm": 0.36874333024024963,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.9824,
      "step": 158
    },
    {
      "epoch": 0.02537402752842609,
      "grad_norm": 0.4039628803730011,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.9309,
      "step": 159
    },
    {
      "epoch": 0.025533612607221225,
      "grad_norm": 0.42655423283576965,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.7722,
      "step": 160
    },
    {
      "epoch": 0.025693197686016356,
      "grad_norm": 0.38772791624069214,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.9466,
      "step": 161
    },
    {
      "epoch": 0.02585278276481149,
      "grad_norm": 0.4154876172542572,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.9885,
      "step": 162
    },
    {
      "epoch": 0.026012367843606624,
      "grad_norm": 0.4108287990093231,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.9978,
      "step": 163
    },
    {
      "epoch": 0.026171952922401754,
      "grad_norm": 0.3967690169811249,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.897,
      "step": 164
    },
    {
      "epoch": 0.026331538001196888,
      "grad_norm": 0.44850876927375793,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.7393,
      "step": 165
    },
    {
      "epoch": 0.026491123079992022,
      "grad_norm": 0.4119727909564972,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.8126,
      "step": 166
    },
    {
      "epoch": 0.026650708158787152,
      "grad_norm": 0.4147897958755493,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.896,
      "step": 167
    },
    {
      "epoch": 0.026810293237582286,
      "grad_norm": 0.4452255368232727,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.971,
      "step": 168
    },
    {
      "epoch": 0.02696987831637742,
      "grad_norm": 0.4029068946838379,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.9962,
      "step": 169
    },
    {
      "epoch": 0.02712946339517255,
      "grad_norm": 0.4363248944282532,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.7952,
      "step": 170
    },
    {
      "epoch": 0.027289048473967684,
      "grad_norm": 0.4742037057876587,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 2.026,
      "step": 171
    },
    {
      "epoch": 0.027448633552762818,
      "grad_norm": 0.4489448666572571,
      "learning_rate": 5.263533508961827e-06,
      "loss": 2.1104,
      "step": 172
    },
    {
      "epoch": 0.02760821863155795,
      "grad_norm": 0.4327584207057953,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.9536,
      "step": 173
    },
    {
      "epoch": 0.027767803710353083,
      "grad_norm": 0.4127856194972992,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.9712,
      "step": 174
    },
    {
      "epoch": 0.027927388789148213,
      "grad_norm": 0.4236384630203247,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.8952,
      "step": 175
    },
    {
      "epoch": 0.028086973867943347,
      "grad_norm": 0.3837657868862152,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.808,
      "step": 176
    },
    {
      "epoch": 0.02824655894673848,
      "grad_norm": 0.4040832221508026,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.9199,
      "step": 177
    },
    {
      "epoch": 0.02840614402553361,
      "grad_norm": 0.41054508090019226,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.9265,
      "step": 178
    },
    {
      "epoch": 0.028565729104328745,
      "grad_norm": 0.4127732813358307,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.8843,
      "step": 179
    },
    {
      "epoch": 0.02872531418312388,
      "grad_norm": 0.4212985634803772,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 2.1253,
      "step": 180
    },
    {
      "epoch": 0.02888489926191901,
      "grad_norm": 0.42579999566078186,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.8974,
      "step": 181
    },
    {
      "epoch": 0.029044484340714143,
      "grad_norm": 0.45347926020622253,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.9212,
      "step": 182
    },
    {
      "epoch": 0.029204069419509277,
      "grad_norm": 0.45477989315986633,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.8848,
      "step": 183
    },
    {
      "epoch": 0.029363654498304408,
      "grad_norm": 0.4316115975379944,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.9165,
      "step": 184
    },
    {
      "epoch": 0.02952323957709954,
      "grad_norm": 0.4431774914264679,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.8971,
      "step": 185
    },
    {
      "epoch": 0.029682824655894675,
      "grad_norm": 0.433931440114975,
      "learning_rate": 1.333670137599713e-06,
      "loss": 2.0061,
      "step": 186
    },
    {
      "epoch": 0.029842409734689806,
      "grad_norm": 0.41841065883636475,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.9639,
      "step": 187
    },
    {
      "epoch": 0.03000199481348494,
      "grad_norm": 0.43690332770347595,
      "learning_rate": 9.810017062595322e-07,
      "loss": 2.0031,
      "step": 188
    },
    {
      "epoch": 0.03016157989228007,
      "grad_norm": 0.43187159299850464,
      "learning_rate": 8.247462563808817e-07,
      "loss": 2.1103,
      "step": 189
    },
    {
      "epoch": 0.030321164971075204,
      "grad_norm": 0.4385557472705841,
      "learning_rate": 6.819348298638839e-07,
      "loss": 2.0202,
      "step": 190
    },
    {
      "epoch": 0.030480750049870338,
      "grad_norm": 0.43355974555015564,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.8926,
      "step": 191
    },
    {
      "epoch": 0.03064033512866547,
      "grad_norm": 0.44955873489379883,
      "learning_rate": 4.367965336512403e-07,
      "loss": 2.1117,
      "step": 192
    },
    {
      "epoch": 0.030799920207460602,
      "grad_norm": 0.45828717947006226,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 2.0845,
      "step": 193
    },
    {
      "epoch": 0.030959505286255736,
      "grad_norm": 0.41999441385269165,
      "learning_rate": 2.458548727494292e-07,
      "loss": 2.1869,
      "step": 194
    },
    {
      "epoch": 0.031119090365050867,
      "grad_norm": 0.48708802461624146,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 2.0011,
      "step": 195
    },
    {
      "epoch": 0.031278675443846,
      "grad_norm": 0.4872084856033325,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 2.1655,
      "step": 196
    },
    {
      "epoch": 0.031438260522641134,
      "grad_norm": 0.4589422345161438,
      "learning_rate": 6.150154258476315e-08,
      "loss": 2.2748,
      "step": 197
    },
    {
      "epoch": 0.03159784560143627,
      "grad_norm": 0.4358261823654175,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 2.2571,
      "step": 198
    },
    {
      "epoch": 0.031757430680231395,
      "grad_norm": 0.4627312421798706,
      "learning_rate": 6.834750376549792e-09,
      "loss": 2.1363,
      "step": 199
    },
    {
      "epoch": 0.03191701575902653,
      "grad_norm": 0.5963596701622009,
      "learning_rate": 0.0,
      "loss": 2.3694,
      "step": 200
    },
    {
      "epoch": 0.03191701575902653,
      "eval_loss": 1.921610713005066,
      "eval_runtime": 314.4289,
      "eval_samples_per_second": 33.566,
      "eval_steps_per_second": 8.393,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.470109086777344e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}