{
  "best_metric": 10.303131103515625,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.022470647716420426,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011235323858210213,
      "grad_norm": 0.8394333124160767,
      "learning_rate": 1e-05,
      "loss": 41.5096,
      "step": 1
    },
    {
      "epoch": 0.00011235323858210213,
      "eval_loss": 10.377470016479492,
      "eval_runtime": 34.1977,
      "eval_samples_per_second": 438.333,
      "eval_steps_per_second": 109.598,
      "step": 1
    },
    {
      "epoch": 0.00022470647716420425,
      "grad_norm": 1.020003080368042,
      "learning_rate": 2e-05,
      "loss": 41.5086,
      "step": 2
    },
    {
      "epoch": 0.00033705971574630637,
      "grad_norm": 0.7538110017776489,
      "learning_rate": 3e-05,
      "loss": 41.5074,
      "step": 3
    },
    {
      "epoch": 0.0004494129543284085,
      "grad_norm": 0.6975579857826233,
      "learning_rate": 4e-05,
      "loss": 41.5174,
      "step": 4
    },
    {
      "epoch": 0.0005617661929105106,
      "grad_norm": 0.7488065361976624,
      "learning_rate": 5e-05,
      "loss": 41.5078,
      "step": 5
    },
    {
      "epoch": 0.0006741194314926127,
      "grad_norm": 0.712092399597168,
      "learning_rate": 6e-05,
      "loss": 41.5158,
      "step": 6
    },
    {
      "epoch": 0.0007864726700747149,
      "grad_norm": 0.7675595879554749,
      "learning_rate": 7e-05,
      "loss": 41.5058,
      "step": 7
    },
    {
      "epoch": 0.000898825908656817,
      "grad_norm": 0.7482902407646179,
      "learning_rate": 8e-05,
      "loss": 41.4912,
      "step": 8
    },
    {
      "epoch": 0.0010111791472389193,
      "grad_norm": 0.8864248394966125,
      "learning_rate": 9e-05,
      "loss": 41.4955,
      "step": 9
    },
    {
      "epoch": 0.0011235323858210212,
      "grad_norm": 0.8515605330467224,
      "learning_rate": 0.0001,
      "loss": 41.4889,
      "step": 10
    },
    {
      "epoch": 0.0012358856244031233,
      "grad_norm": 0.8117326498031616,
      "learning_rate": 9.999316524962345e-05,
      "loss": 41.4924,
      "step": 11
    },
    {
      "epoch": 0.0013482388629852255,
      "grad_norm": 0.8973363637924194,
      "learning_rate": 9.997266286704631e-05,
      "loss": 41.4847,
      "step": 12
    },
    {
      "epoch": 0.0014605921015673276,
      "grad_norm": 0.8886382579803467,
      "learning_rate": 9.993849845741524e-05,
      "loss": 41.492,
      "step": 13
    },
    {
      "epoch": 0.0015729453401494297,
      "grad_norm": 0.9821717143058777,
      "learning_rate": 9.989068136093873e-05,
      "loss": 41.4703,
      "step": 14
    },
    {
      "epoch": 0.0016852985787315319,
      "grad_norm": 1.154563307762146,
      "learning_rate": 9.98292246503335e-05,
      "loss": 41.4605,
      "step": 15
    },
    {
      "epoch": 0.001797651817313634,
      "grad_norm": 1.0592628717422485,
      "learning_rate": 9.975414512725057e-05,
      "loss": 41.4726,
      "step": 16
    },
    {
      "epoch": 0.0019100050558957362,
      "grad_norm": 1.3152652978897095,
      "learning_rate": 9.966546331768191e-05,
      "loss": 41.4577,
      "step": 17
    },
    {
      "epoch": 0.0020223582944778385,
      "grad_norm": 1.388919472694397,
      "learning_rate": 9.956320346634876e-05,
      "loss": 41.4496,
      "step": 18
    },
    {
      "epoch": 0.0021347115330599404,
      "grad_norm": 1.3259446620941162,
      "learning_rate": 9.944739353007344e-05,
      "loss": 41.451,
      "step": 19
    },
    {
      "epoch": 0.0022470647716420424,
      "grad_norm": 1.4101603031158447,
      "learning_rate": 9.931806517013612e-05,
      "loss": 41.4368,
      "step": 20
    },
    {
      "epoch": 0.0023594180102241447,
      "grad_norm": 1.527879238128662,
      "learning_rate": 9.917525374361912e-05,
      "loss": 41.4347,
      "step": 21
    },
    {
      "epoch": 0.0024717712488062466,
      "grad_norm": 1.5636837482452393,
      "learning_rate": 9.901899829374047e-05,
      "loss": 41.4057,
      "step": 22
    },
    {
      "epoch": 0.002584124487388349,
      "grad_norm": 1.5471636056900024,
      "learning_rate": 9.884934153917997e-05,
      "loss": 41.4087,
      "step": 23
    },
    {
      "epoch": 0.002696477725970451,
      "grad_norm": 1.6354128122329712,
      "learning_rate": 9.86663298624003e-05,
      "loss": 41.4109,
      "step": 24
    },
    {
      "epoch": 0.0028088309645525533,
      "grad_norm": 1.6948407888412476,
      "learning_rate": 9.847001329696653e-05,
      "loss": 41.3788,
      "step": 25
    },
    {
      "epoch": 0.002921184203134655,
      "grad_norm": 1.9301602840423584,
      "learning_rate": 9.826044551386744e-05,
      "loss": 41.3759,
      "step": 26
    },
    {
      "epoch": 0.0030335374417167576,
      "grad_norm": 1.6842283010482788,
      "learning_rate": 9.803768380684242e-05,
      "loss": 41.3826,
      "step": 27
    },
    {
      "epoch": 0.0031458906802988595,
      "grad_norm": 1.775986909866333,
      "learning_rate": 9.780178907671789e-05,
      "loss": 41.3538,
      "step": 28
    },
    {
      "epoch": 0.003258243918880962,
      "grad_norm": 1.6640071868896484,
      "learning_rate": 9.755282581475769e-05,
      "loss": 41.358,
      "step": 29
    },
    {
      "epoch": 0.0033705971574630638,
      "grad_norm": 1.7200181484222412,
      "learning_rate": 9.729086208503174e-05,
      "loss": 41.3515,
      "step": 30
    },
    {
      "epoch": 0.003482950396045166,
      "grad_norm": 1.6980204582214355,
      "learning_rate": 9.701596950580806e-05,
      "loss": 41.3274,
      "step": 31
    },
    {
      "epoch": 0.003595303634627268,
      "grad_norm": 1.6180922985076904,
      "learning_rate": 9.672822322997305e-05,
      "loss": 41.3226,
      "step": 32
    },
    {
      "epoch": 0.0037076568732093704,
      "grad_norm": 1.4642963409423828,
      "learning_rate": 9.642770192448536e-05,
      "loss": 41.3318,
      "step": 33
    },
    {
      "epoch": 0.0038200101117914723,
      "grad_norm": 1.5084538459777832,
      "learning_rate": 9.611448774886924e-05,
      "loss": 41.32,
      "step": 34
    },
    {
      "epoch": 0.003932363350373574,
      "grad_norm": 1.3335824012756348,
      "learning_rate": 9.578866633275288e-05,
      "loss": 41.3252,
      "step": 35
    },
    {
      "epoch": 0.004044716588955677,
      "grad_norm": 1.3950356245040894,
      "learning_rate": 9.545032675245813e-05,
      "loss": 41.3085,
      "step": 36
    },
    {
      "epoch": 0.004157069827537779,
      "grad_norm": 1.2780814170837402,
      "learning_rate": 9.509956150664796e-05,
      "loss": 41.2935,
      "step": 37
    },
    {
      "epoch": 0.004269423066119881,
      "grad_norm": 1.0999070405960083,
      "learning_rate": 9.473646649103818e-05,
      "loss": 41.2913,
      "step": 38
    },
    {
      "epoch": 0.004381776304701983,
      "grad_norm": 1.1295652389526367,
      "learning_rate": 9.43611409721806e-05,
      "loss": 41.2579,
      "step": 39
    },
    {
      "epoch": 0.004494129543284085,
      "grad_norm": 1.0421503782272339,
      "learning_rate": 9.397368756032445e-05,
      "loss": 41.2802,
      "step": 40
    },
    {
      "epoch": 0.0046064827818661875,
      "grad_norm": 1.01857590675354,
      "learning_rate": 9.357421218136386e-05,
      "loss": 41.258,
      "step": 41
    },
    {
      "epoch": 0.0047188360204482895,
      "grad_norm": 0.8823058605194092,
      "learning_rate": 9.316282404787871e-05,
      "loss": 41.2528,
      "step": 42
    },
    {
      "epoch": 0.004831189259030391,
      "grad_norm": 0.8466707468032837,
      "learning_rate": 9.273963562927695e-05,
      "loss": 41.248,
      "step": 43
    },
    {
      "epoch": 0.004943542497612493,
      "grad_norm": 0.7720403075218201,
      "learning_rate": 9.230476262104677e-05,
      "loss": 41.2742,
      "step": 44
    },
    {
      "epoch": 0.005055895736194596,
      "grad_norm": 0.7159811854362488,
      "learning_rate": 9.185832391312644e-05,
      "loss": 41.2416,
      "step": 45
    },
    {
      "epoch": 0.005168248974776698,
      "grad_norm": 0.6696586012840271,
      "learning_rate": 9.140044155740101e-05,
      "loss": 41.2552,
      "step": 46
    },
    {
      "epoch": 0.0052806022133588,
      "grad_norm": 0.6373426914215088,
      "learning_rate": 9.093124073433463e-05,
      "loss": 41.2641,
      "step": 47
    },
    {
      "epoch": 0.005392955451940902,
      "grad_norm": 0.6086274981498718,
      "learning_rate": 9.045084971874738e-05,
      "loss": 41.2658,
      "step": 48
    },
    {
      "epoch": 0.005505308690523005,
      "grad_norm": 0.6172379851341248,
      "learning_rate": 8.995939984474624e-05,
      "loss": 41.2588,
      "step": 49
    },
    {
      "epoch": 0.005617661929105107,
      "grad_norm": 0.5523455142974854,
      "learning_rate": 8.945702546981969e-05,
      "loss": 41.2561,
      "step": 50
    },
    {
      "epoch": 0.005617661929105107,
      "eval_loss": 10.308499336242676,
      "eval_runtime": 34.0586,
      "eval_samples_per_second": 440.124,
      "eval_steps_per_second": 110.046,
      "step": 50
    },
    {
      "epoch": 0.0057300151676872085,
      "grad_norm": 0.6354011297225952,
      "learning_rate": 8.894386393810563e-05,
      "loss": 41.2471,
      "step": 51
    },
    {
      "epoch": 0.00584236840626931,
      "grad_norm": 0.9131802320480347,
      "learning_rate": 8.842005554284296e-05,
      "loss": 41.2193,
      "step": 52
    },
    {
      "epoch": 0.005954721644851413,
      "grad_norm": 0.6471925973892212,
      "learning_rate": 8.788574348801675e-05,
      "loss": 41.2433,
      "step": 53
    },
    {
      "epoch": 0.006067074883433515,
      "grad_norm": 0.5279708504676819,
      "learning_rate": 8.73410738492077e-05,
      "loss": 41.2363,
      "step": 54
    },
    {
      "epoch": 0.006179428122015617,
      "grad_norm": 0.43017682433128357,
      "learning_rate": 8.678619553365659e-05,
      "loss": 41.2428,
      "step": 55
    },
    {
      "epoch": 0.006291781360597719,
      "grad_norm": 0.48331451416015625,
      "learning_rate": 8.622126023955446e-05,
      "loss": 41.2183,
      "step": 56
    },
    {
      "epoch": 0.006404134599179822,
      "grad_norm": 0.4361855983734131,
      "learning_rate": 8.564642241456986e-05,
      "loss": 41.2209,
      "step": 57
    },
    {
      "epoch": 0.006516487837761924,
      "grad_norm": 0.3000849485397339,
      "learning_rate": 8.506183921362443e-05,
      "loss": 41.2428,
      "step": 58
    },
    {
      "epoch": 0.006628841076344026,
      "grad_norm": 0.3213319778442383,
      "learning_rate": 8.44676704559283e-05,
      "loss": 41.2216,
      "step": 59
    },
    {
      "epoch": 0.0067411943149261275,
      "grad_norm": 0.39326193928718567,
      "learning_rate": 8.386407858128706e-05,
      "loss": 41.2454,
      "step": 60
    },
    {
      "epoch": 0.0068535475535082295,
      "grad_norm": 0.3042173683643341,
      "learning_rate": 8.32512286056924e-05,
      "loss": 41.238,
      "step": 61
    },
    {
      "epoch": 0.006965900792090332,
      "grad_norm": 0.3486955165863037,
      "learning_rate": 8.262928807620843e-05,
      "loss": 41.2088,
      "step": 62
    },
    {
      "epoch": 0.007078254030672434,
      "grad_norm": 0.35463428497314453,
      "learning_rate": 8.199842702516583e-05,
      "loss": 41.2277,
      "step": 63
    },
    {
      "epoch": 0.007190607269254536,
      "grad_norm": 0.33463189005851746,
      "learning_rate": 8.135881792367686e-05,
      "loss": 41.2425,
      "step": 64
    },
    {
      "epoch": 0.007302960507836638,
      "grad_norm": 0.3098670244216919,
      "learning_rate": 8.07106356344834e-05,
      "loss": 41.2047,
      "step": 65
    },
    {
      "epoch": 0.007415313746418741,
      "grad_norm": 0.3586290180683136,
      "learning_rate": 8.005405736415126e-05,
      "loss": 41.2334,
      "step": 66
    },
    {
      "epoch": 0.007527666985000843,
      "grad_norm": 0.23549406230449677,
      "learning_rate": 7.938926261462366e-05,
      "loss": 41.2059,
      "step": 67
    },
    {
      "epoch": 0.007640020223582945,
      "grad_norm": 0.33009931445121765,
      "learning_rate": 7.871643313414718e-05,
      "loss": 41.2251,
      "step": 68
    },
    {
      "epoch": 0.007752373462165047,
      "grad_norm": 0.25321194529533386,
      "learning_rate": 7.803575286758364e-05,
      "loss": 41.2165,
      "step": 69
    },
    {
      "epoch": 0.007864726700747149,
      "grad_norm": 0.20516608655452728,
      "learning_rate": 7.734740790612136e-05,
      "loss": 41.2217,
      "step": 70
    },
    {
      "epoch": 0.007977079939329251,
      "grad_norm": 0.25512322783470154,
      "learning_rate": 7.66515864363997e-05,
      "loss": 41.2353,
      "step": 71
    },
    {
      "epoch": 0.008089433177911354,
      "grad_norm": 0.2911408245563507,
      "learning_rate": 7.594847868906076e-05,
      "loss": 41.2281,
      "step": 72
    },
    {
      "epoch": 0.008201786416493455,
      "grad_norm": 0.2841276526451111,
      "learning_rate": 7.52382768867422e-05,
      "loss": 41.2275,
      "step": 73
    },
    {
      "epoch": 0.008314139655075558,
      "grad_norm": 0.2493758350610733,
      "learning_rate": 7.452117519152542e-05,
      "loss": 41.197,
      "step": 74
    },
    {
      "epoch": 0.008426492893657659,
      "grad_norm": 0.27761879563331604,
      "learning_rate": 7.379736965185368e-05,
      "loss": 41.2261,
      "step": 75
    },
    {
      "epoch": 0.008538846132239762,
      "grad_norm": 0.23555432260036469,
      "learning_rate": 7.30670581489344e-05,
      "loss": 41.2146,
      "step": 76
    },
    {
      "epoch": 0.008651199370821865,
      "grad_norm": 0.30705100297927856,
      "learning_rate": 7.233044034264034e-05,
      "loss": 41.203,
      "step": 77
    },
    {
      "epoch": 0.008763552609403966,
      "grad_norm": 0.24371613562107086,
      "learning_rate": 7.158771761692464e-05,
      "loss": 41.2287,
      "step": 78
    },
    {
      "epoch": 0.008875905847986068,
      "grad_norm": 0.27437758445739746,
      "learning_rate": 7.083909302476453e-05,
      "loss": 41.2226,
      "step": 79
    },
    {
      "epoch": 0.00898825908656817,
      "grad_norm": 0.33063244819641113,
      "learning_rate": 7.008477123264848e-05,
      "loss": 41.2202,
      "step": 80
    },
    {
      "epoch": 0.009100612325150272,
      "grad_norm": 0.3659040331840515,
      "learning_rate": 6.932495846462261e-05,
      "loss": 41.1975,
      "step": 81
    },
    {
      "epoch": 0.009212965563732375,
      "grad_norm": 0.2900170087814331,
      "learning_rate": 6.855986244591104e-05,
      "loss": 41.2283,
      "step": 82
    },
    {
      "epoch": 0.009325318802314476,
      "grad_norm": 0.3087519109249115,
      "learning_rate": 6.778969234612584e-05,
      "loss": 41.2339,
      "step": 83
    },
    {
      "epoch": 0.009437672040896579,
      "grad_norm": 0.23411895334720612,
      "learning_rate": 6.701465872208216e-05,
      "loss": 41.2123,
      "step": 84
    },
    {
      "epoch": 0.009550025279478682,
      "grad_norm": 0.23332460224628448,
      "learning_rate": 6.623497346023418e-05,
      "loss": 41.2276,
      "step": 85
    },
    {
      "epoch": 0.009662378518060783,
      "grad_norm": 0.29801681637763977,
      "learning_rate": 6.545084971874738e-05,
      "loss": 41.2181,
      "step": 86
    },
    {
      "epoch": 0.009774731756642886,
      "grad_norm": 0.29691848158836365,
      "learning_rate": 6.466250186922325e-05,
      "loss": 41.2207,
      "step": 87
    },
    {
      "epoch": 0.009887084995224987,
      "grad_norm": 0.222100630402565,
      "learning_rate": 6.387014543809223e-05,
      "loss": 41.2032,
      "step": 88
    },
    {
      "epoch": 0.00999943823380709,
      "grad_norm": 0.25634244084358215,
      "learning_rate": 6.307399704769099e-05,
      "loss": 41.2168,
      "step": 89
    },
    {
      "epoch": 0.010111791472389192,
      "grad_norm": 0.3026779294013977,
      "learning_rate": 6.227427435703997e-05,
      "loss": 41.2174,
      "step": 90
    },
    {
      "epoch": 0.010224144710971293,
      "grad_norm": 0.20975500345230103,
      "learning_rate": 6.147119600233758e-05,
      "loss": 41.2173,
      "step": 91
    },
    {
      "epoch": 0.010336497949553396,
      "grad_norm": 0.28338366746902466,
      "learning_rate": 6.066498153718735e-05,
      "loss": 41.2261,
      "step": 92
    },
    {
      "epoch": 0.010448851188135499,
      "grad_norm": 0.2857464551925659,
      "learning_rate": 5.985585137257401e-05,
      "loss": 41.2139,
      "step": 93
    },
    {
      "epoch": 0.0105612044267176,
      "grad_norm": 0.33788928389549255,
      "learning_rate": 5.90440267166055e-05,
      "loss": 41.2152,
      "step": 94
    },
    {
      "epoch": 0.010673557665299703,
      "grad_norm": 0.2681242525577545,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 41.2299,
      "step": 95
    },
    {
      "epoch": 0.010785910903881804,
      "grad_norm": 0.2598814368247986,
      "learning_rate": 5.74131823855921e-05,
      "loss": 41.2039,
      "step": 96
    },
    {
      "epoch": 0.010898264142463907,
      "grad_norm": 0.2513768672943115,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 41.2028,
      "step": 97
    },
    {
      "epoch": 0.01101061738104601,
      "grad_norm": 0.34942224621772766,
      "learning_rate": 5.577423184847932e-05,
      "loss": 41.2183,
      "step": 98
    },
    {
      "epoch": 0.01112297061962811,
      "grad_norm": 0.3314323425292969,
      "learning_rate": 5.495227651252315e-05,
      "loss": 41.2406,
      "step": 99
    },
    {
      "epoch": 0.011235323858210213,
      "grad_norm": 0.4192982614040375,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 41.2447,
      "step": 100
    },
    {
      "epoch": 0.011235323858210213,
      "eval_loss": 10.30439281463623,
      "eval_runtime": 34.069,
      "eval_samples_per_second": 439.989,
      "eval_steps_per_second": 110.012,
      "step": 100
    },
    {
      "epoch": 0.011347677096792314,
      "grad_norm": 0.49622422456741333,
      "learning_rate": 5.330452921628497e-05,
      "loss": 41.1855,
      "step": 101
    },
    {
      "epoch": 0.011460030335374417,
      "grad_norm": 0.8578363060951233,
      "learning_rate": 5.247918773366112e-05,
      "loss": 41.1997,
      "step": 102
    },
    {
      "epoch": 0.01157238357395652,
      "grad_norm": 0.5147648453712463,
      "learning_rate": 5.165316846586541e-05,
      "loss": 41.2097,
      "step": 103
    },
    {
      "epoch": 0.01168473681253862,
      "grad_norm": 0.345619261264801,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 41.2086,
      "step": 104
    },
    {
      "epoch": 0.011797090051120724,
      "grad_norm": 0.3661554455757141,
      "learning_rate": 5e-05,
      "loss": 41.2078,
      "step": 105
    },
    {
      "epoch": 0.011909443289702826,
      "grad_norm": 0.2916611135005951,
      "learning_rate": 4.917330276168208e-05,
      "loss": 41.2243,
      "step": 106
    },
    {
      "epoch": 0.012021796528284927,
      "grad_norm": 0.24037790298461914,
      "learning_rate": 4.834683153413459e-05,
      "loss": 41.2183,
      "step": 107
    },
    {
      "epoch": 0.01213414976686703,
      "grad_norm": 0.40441879630088806,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 41.1914,
      "step": 108
    },
    {
      "epoch": 0.012246503005449131,
      "grad_norm": 0.2370593249797821,
      "learning_rate": 4.669547078371504e-05,
      "loss": 41.2315,
      "step": 109
    },
    {
      "epoch": 0.012358856244031234,
      "grad_norm": 0.22881992161273956,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 41.231,
      "step": 110
    },
    {
      "epoch": 0.012471209482613337,
      "grad_norm": 0.3377077579498291,
      "learning_rate": 4.504772348747687e-05,
      "loss": 41.1971,
      "step": 111
    },
    {
      "epoch": 0.012583562721195438,
      "grad_norm": 0.2281845510005951,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 41.2372,
      "step": 112
    },
    {
      "epoch": 0.01269591595977754,
      "grad_norm": 0.32385313510894775,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 41.2126,
      "step": 113
    },
    {
      "epoch": 0.012808269198359644,
      "grad_norm": 0.2192939966917038,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 41.2115,
      "step": 114
    },
    {
      "epoch": 0.012920622436941745,
      "grad_norm": 0.2397969663143158,
      "learning_rate": 4.17702704859633e-05,
      "loss": 41.2128,
      "step": 115
    },
    {
      "epoch": 0.013032975675523847,
      "grad_norm": 0.33919790387153625,
      "learning_rate": 4.095597328339452e-05,
      "loss": 41.2121,
      "step": 116
    },
    {
      "epoch": 0.013145328914105948,
      "grad_norm": 0.21591807901859283,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 41.2223,
      "step": 117
    },
    {
      "epoch": 0.013257682152688051,
      "grad_norm": 0.2794930934906006,
      "learning_rate": 3.933501846281267e-05,
      "loss": 41.2133,
      "step": 118
    },
    {
      "epoch": 0.013370035391270154,
      "grad_norm": 0.2230224609375,
      "learning_rate": 3.852880399766243e-05,
      "loss": 41.2282,
      "step": 119
    },
    {
      "epoch": 0.013482388629852255,
      "grad_norm": 0.2297627478837967,
      "learning_rate": 3.772572564296005e-05,
      "loss": 41.2177,
      "step": 120
    },
    {
      "epoch": 0.013594741868434358,
      "grad_norm": 0.26342302560806274,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 41.2122,
      "step": 121
    },
    {
      "epoch": 0.013707095107016459,
      "grad_norm": 0.2136620134115219,
      "learning_rate": 3.612985456190778e-05,
      "loss": 41.2163,
      "step": 122
    },
    {
      "epoch": 0.013819448345598562,
      "grad_norm": 0.25090110301971436,
      "learning_rate": 3.533749813077677e-05,
      "loss": 41.2091,
      "step": 123
    },
    {
      "epoch": 0.013931801584180665,
      "grad_norm": 0.20302414894104004,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 41.2225,
      "step": 124
    },
    {
      "epoch": 0.014044154822762766,
      "grad_norm": 0.15653355419635773,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 41.1986,
      "step": 125
    },
    {
      "epoch": 0.014156508061344868,
      "grad_norm": 0.23139993846416473,
      "learning_rate": 3.298534127791785e-05,
      "loss": 41.2188,
      "step": 126
    },
    {
      "epoch": 0.014268861299926971,
      "grad_norm": 0.23362991213798523,
      "learning_rate": 3.221030765387417e-05,
      "loss": 41.2245,
      "step": 127
    },
    {
      "epoch": 0.014381214538509072,
      "grad_norm": 0.28792744874954224,
      "learning_rate": 3.144013755408895e-05,
      "loss": 41.2254,
      "step": 128
    },
    {
      "epoch": 0.014493567777091175,
      "grad_norm": 0.21903224289417267,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 41.2128,
      "step": 129
    },
    {
      "epoch": 0.014605921015673276,
      "grad_norm": 0.2267473340034485,
      "learning_rate": 2.991522876735154e-05,
      "loss": 41.2227,
      "step": 130
    },
    {
      "epoch": 0.014718274254255379,
      "grad_norm": 0.26865267753601074,
      "learning_rate": 2.916090697523549e-05,
      "loss": 41.2062,
      "step": 131
    },
    {
      "epoch": 0.014830627492837482,
      "grad_norm": 0.24797743558883667,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 41.2019,
      "step": 132
    },
    {
      "epoch": 0.014942980731419583,
      "grad_norm": 0.2965383231639862,
      "learning_rate": 2.766955965735968e-05,
      "loss": 41.2102,
      "step": 133
    },
    {
      "epoch": 0.015055333970001685,
      "grad_norm": 0.21794797480106354,
      "learning_rate": 2.693294185106562e-05,
      "loss": 41.2194,
      "step": 134
    },
    {
      "epoch": 0.015167687208583788,
      "grad_norm": 0.25002628564834595,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 41.2146,
      "step": 135
    },
    {
      "epoch": 0.01528004044716589,
      "grad_norm": 0.3150271773338318,
      "learning_rate": 2.547882480847461e-05,
      "loss": 41.218,
      "step": 136
    },
    {
      "epoch": 0.015392393685747992,
      "grad_norm": 0.2121894508600235,
      "learning_rate": 2.476172311325783e-05,
      "loss": 41.2235,
      "step": 137
    },
    {
      "epoch": 0.015504746924330093,
      "grad_norm": 0.26923856139183044,
      "learning_rate": 2.405152131093926e-05,
      "loss": 41.2132,
      "step": 138
    },
    {
      "epoch": 0.015617100162912196,
      "grad_norm": 0.2581329345703125,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 41.2266,
      "step": 139
    },
    {
      "epoch": 0.015729453401494297,
      "grad_norm": 0.2612220346927643,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 41.2147,
      "step": 140
    },
    {
      "epoch": 0.0158418066400764,
      "grad_norm": 0.2495860606431961,
      "learning_rate": 2.196424713241637e-05,
      "loss": 41.2264,
      "step": 141
    },
    {
      "epoch": 0.015954159878658503,
      "grad_norm": 0.267837256193161,
      "learning_rate": 2.128356686585282e-05,
      "loss": 41.2224,
      "step": 142
    },
    {
      "epoch": 0.016066513117240604,
      "grad_norm": 0.34399616718292236,
      "learning_rate": 2.061073738537635e-05,
      "loss": 41.2354,
      "step": 143
    },
    {
      "epoch": 0.016178866355822708,
      "grad_norm": 0.2811826765537262,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 41.2332,
      "step": 144
    },
    {
      "epoch": 0.01629121959440481,
      "grad_norm": 0.2815895676612854,
      "learning_rate": 1.928936436551661e-05,
      "loss": 41.2062,
      "step": 145
    },
    {
      "epoch": 0.01640357283298691,
      "grad_norm": 0.2869739234447479,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 41.2212,
      "step": 146
    },
    {
      "epoch": 0.01651592607156901,
      "grad_norm": 0.3401114046573639,
      "learning_rate": 1.800157297483417e-05,
      "loss": 41.2258,
      "step": 147
    },
    {
      "epoch": 0.016628279310151116,
      "grad_norm": 0.3535214364528656,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 41.222,
      "step": 148
    },
    {
      "epoch": 0.016740632548733217,
      "grad_norm": 0.3539586067199707,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 41.2279,
      "step": 149
    },
    {
      "epoch": 0.016852985787315318,
      "grad_norm": 0.40270936489105225,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 41.2384,
      "step": 150
    },
    {
      "epoch": 0.016852985787315318,
      "eval_loss": 10.303377151489258,
      "eval_runtime": 34.1119,
      "eval_samples_per_second": 439.436,
      "eval_steps_per_second": 109.874,
      "step": 150
    },
    {
      "epoch": 0.016965339025897423,
      "grad_norm": 0.5998801589012146,
      "learning_rate": 1.553232954407171e-05,
      "loss": 41.228,
      "step": 151
    },
    {
      "epoch": 0.017077692264479524,
      "grad_norm": 0.8729236125946045,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 41.2058,
      "step": 152
    },
    {
      "epoch": 0.017190045503061625,
      "grad_norm": 0.3832565248012543,
      "learning_rate": 1.435357758543015e-05,
      "loss": 41.2104,
      "step": 153
    },
    {
      "epoch": 0.01730239874164373,
      "grad_norm": 0.37122440338134766,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 41.2097,
      "step": 154
    },
    {
      "epoch": 0.01741475198022583,
      "grad_norm": 0.19617068767547607,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 41.2071,
      "step": 155
    },
    {
      "epoch": 0.01752710521880793,
      "grad_norm": 0.2588755786418915,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 41.2111,
      "step": 156
    },
    {
      "epoch": 0.017639458457390036,
      "grad_norm": 0.27696478366851807,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 41.2196,
      "step": 157
    },
    {
      "epoch": 0.017751811695972137,
      "grad_norm": 0.23367959260940552,
      "learning_rate": 1.157994445715706e-05,
      "loss": 41.2278,
      "step": 158
    },
    {
      "epoch": 0.017864164934554238,
      "grad_norm": 0.3423803150653839,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 41.2091,
      "step": 159
    },
    {
      "epoch": 0.01797651817313634,
      "grad_norm": 0.3560184836387634,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 41.2053,
      "step": 160
    },
    {
      "epoch": 0.018088871411718443,
      "grad_norm": 0.28921639919281006,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 41.2093,
      "step": 161
    },
    {
      "epoch": 0.018201224650300545,
      "grad_norm": 0.2694426476955414,
      "learning_rate": 9.549150281252633e-06,
      "loss": 41.2099,
      "step": 162
    },
    {
      "epoch": 0.018313577888882646,
      "grad_norm": 0.22039711475372314,
      "learning_rate": 9.068759265665384e-06,
      "loss": 41.2149,
      "step": 163
    },
    {
      "epoch": 0.01842593112746475,
      "grad_norm": 0.19488602876663208,
      "learning_rate": 8.599558442598998e-06,
      "loss": 41.2094,
      "step": 164
    },
    {
      "epoch": 0.01853828436604685,
      "grad_norm": 0.2423410564661026,
      "learning_rate": 8.141676086873572e-06,
      "loss": 41.205,
      "step": 165
    },
    {
      "epoch": 0.018650637604628952,
      "grad_norm": 0.1848248392343521,
      "learning_rate": 7.695237378953223e-06,
      "loss": 41.2096,
      "step": 166
    },
    {
      "epoch": 0.018762990843211057,
      "grad_norm": 0.3004802167415619,
      "learning_rate": 7.260364370723044e-06,
      "loss": 41.2266,
      "step": 167
    },
    {
      "epoch": 0.018875344081793158,
      "grad_norm": 0.2908780574798584,
      "learning_rate": 6.837175952121306e-06,
      "loss": 41.1881,
      "step": 168
    },
    {
      "epoch": 0.01898769732037526,
      "grad_norm": 0.17987942695617676,
      "learning_rate": 6.425787818636131e-06,
      "loss": 41.2055,
      "step": 169
    },
    {
      "epoch": 0.019100050558957363,
      "grad_norm": 0.2570153772830963,
      "learning_rate": 6.026312439675552e-06,
      "loss": 41.2074,
      "step": 170
    },
    {
      "epoch": 0.019212403797539464,
      "grad_norm": 0.24911056458950043,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 41.2172,
      "step": 171
    },
    {
      "epoch": 0.019324757036121566,
      "grad_norm": 0.1543077528476715,
      "learning_rate": 5.263533508961827e-06,
      "loss": 41.2063,
      "step": 172
    },
    {
      "epoch": 0.01943711027470367,
      "grad_norm": 0.2991461455821991,
      "learning_rate": 4.900438493352055e-06,
      "loss": 41.1928,
      "step": 173
    },
    {
      "epoch": 0.01954946351328577,
      "grad_norm": 0.2257542461156845,
      "learning_rate": 4.549673247541875e-06,
      "loss": 41.1979,
      "step": 174
    },
    {
      "epoch": 0.019661816751867872,
      "grad_norm": 0.2865986227989197,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 41.181,
      "step": 175
    },
    {
      "epoch": 0.019774169990449973,
      "grad_norm": 0.35200926661491394,
      "learning_rate": 3.885512251130763e-06,
      "loss": 41.1888,
      "step": 176
    },
    {
      "epoch": 0.019886523229032078,
      "grad_norm": 0.20003312826156616,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 41.2024,
      "step": 177
    },
    {
      "epoch": 0.01999887646761418,
      "grad_norm": 0.24820686876773834,
      "learning_rate": 3.271776770026963e-06,
      "loss": 41.2017,
      "step": 178
    },
    {
      "epoch": 0.02011122970619628,
      "grad_norm": 0.23656213283538818,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 41.2039,
      "step": 179
    },
    {
      "epoch": 0.020223582944778384,
      "grad_norm": 0.24723601341247559,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 41.2189,
      "step": 180
    },
    {
      "epoch": 0.020335936183360485,
      "grad_norm": 0.22884495556354523,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 41.2215,
      "step": 181
    },
    {
      "epoch": 0.020448289421942586,
      "grad_norm": 0.26854977011680603,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 41.2044,
      "step": 182
    },
    {
      "epoch": 0.02056064266052469,
      "grad_norm": 0.24930109083652496,
      "learning_rate": 1.962316193157593e-06,
      "loss": 41.2203,
      "step": 183
    },
    {
      "epoch": 0.020672995899106792,
      "grad_norm": 0.29127103090286255,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 41.2077,
      "step": 184
    },
    {
      "epoch": 0.020785349137688893,
      "grad_norm": 0.2198585718870163,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 41.2201,
      "step": 185
    },
    {
      "epoch": 0.020897702376270998,
      "grad_norm": 0.19509965181350708,
      "learning_rate": 1.333670137599713e-06,
      "loss": 41.2021,
      "step": 186
    },
    {
      "epoch": 0.0210100556148531,
      "grad_norm": 0.3104880750179291,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 41.2023,
      "step": 187
    },
    {
      "epoch": 0.0211224088534352,
      "grad_norm": 0.22649165987968445,
      "learning_rate": 9.810017062595322e-07,
      "loss": 41.2069,
      "step": 188
    },
    {
      "epoch": 0.0212347620920173,
      "grad_norm": 0.25516071915626526,
      "learning_rate": 8.247462563808817e-07,
      "loss": 41.2207,
      "step": 189
    },
    {
      "epoch": 0.021347115330599405,
      "grad_norm": 0.236747145652771,
      "learning_rate": 6.819348298638839e-07,
      "loss": 41.2038,
      "step": 190
    },
    {
      "epoch": 0.021459468569181506,
      "grad_norm": 0.28271225094795227,
      "learning_rate": 5.526064699265753e-07,
      "loss": 41.2206,
      "step": 191
    },
    {
      "epoch": 0.021571821807763607,
      "grad_norm": 0.27172738313674927,
      "learning_rate": 4.367965336512403e-07,
      "loss": 41.2355,
      "step": 192
    },
    {
      "epoch": 0.021684175046345712,
      "grad_norm": 0.22428080439567566,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 41.2018,
      "step": 193
    },
    {
      "epoch": 0.021796528284927813,
      "grad_norm": 0.2830086052417755,
      "learning_rate": 2.458548727494292e-07,
      "loss": 41.198,
      "step": 194
    },
    {
      "epoch": 0.021908881523509914,
      "grad_norm": 0.3113277554512024,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 41.2261,
      "step": 195
    },
    {
      "epoch": 0.02202123476209202,
      "grad_norm": 0.2997662127017975,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 41.2421,
      "step": 196
    },
    {
      "epoch": 0.02213358800067412,
      "grad_norm": 0.366565465927124,
      "learning_rate": 6.150154258476315e-08,
      "loss": 41.2134,
      "step": 197
    },
    {
      "epoch": 0.02224594123925622,
      "grad_norm": 0.3228812515735626,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 41.2271,
      "step": 198
    },
    {
      "epoch": 0.022358294477838325,
      "grad_norm": 0.37816309928894043,
      "learning_rate": 6.834750376549792e-09,
      "loss": 41.2303,
      "step": 199
    },
    {
      "epoch": 0.022470647716420426,
      "grad_norm": 0.4088732600212097,
      "learning_rate": 0.0,
      "loss": 41.2581,
      "step": 200
    },
    {
      "epoch": 0.022470647716420426,
      "eval_loss": 10.303131103515625,
      "eval_runtime": 34.1122,
      "eval_samples_per_second": 439.432,
      "eval_steps_per_second": 109.873,
      "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": 44841416785920.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}