{
  "best_metric": 10.33694076538086,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.25157232704402516,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012578616352201257,
      "grad_norm": 0.0676870122551918,
      "learning_rate": 1e-05,
      "loss": 10.3781,
      "step": 1
    },
    {
      "epoch": 0.0012578616352201257,
      "eval_loss": 10.373727798461914,
      "eval_runtime": 2.8214,
      "eval_samples_per_second": 474.581,
      "eval_steps_per_second": 118.734,
      "step": 1
    },
    {
      "epoch": 0.0025157232704402514,
      "grad_norm": 0.053749579936265945,
      "learning_rate": 2e-05,
      "loss": 10.3781,
      "step": 2
    },
    {
      "epoch": 0.0037735849056603774,
      "grad_norm": 0.05700600892305374,
      "learning_rate": 3e-05,
      "loss": 10.3763,
      "step": 3
    },
    {
      "epoch": 0.005031446540880503,
      "grad_norm": 0.05451948195695877,
      "learning_rate": 4e-05,
      "loss": 10.376,
      "step": 4
    },
    {
      "epoch": 0.006289308176100629,
      "grad_norm": 0.05333434417843819,
      "learning_rate": 5e-05,
      "loss": 10.3767,
      "step": 5
    },
    {
      "epoch": 0.007547169811320755,
      "grad_norm": 0.053336936980485916,
      "learning_rate": 6e-05,
      "loss": 10.3776,
      "step": 6
    },
    {
      "epoch": 0.00880503144654088,
      "grad_norm": 0.050664711743593216,
      "learning_rate": 7e-05,
      "loss": 10.3781,
      "step": 7
    },
    {
      "epoch": 0.010062893081761006,
      "grad_norm": 0.053908322006464005,
      "learning_rate": 8e-05,
      "loss": 10.3772,
      "step": 8
    },
    {
      "epoch": 0.011320754716981131,
      "grad_norm": 0.05347241088747978,
      "learning_rate": 9e-05,
      "loss": 10.3755,
      "step": 9
    },
    {
      "epoch": 0.012578616352201259,
      "grad_norm": 0.06627130508422852,
      "learning_rate": 0.0001,
      "loss": 10.376,
      "step": 10
    },
    {
      "epoch": 0.013836477987421384,
      "grad_norm": 0.0658232793211937,
      "learning_rate": 9.999316524962345e-05,
      "loss": 10.3757,
      "step": 11
    },
    {
      "epoch": 0.01509433962264151,
      "grad_norm": 0.07336028665304184,
      "learning_rate": 9.997266286704631e-05,
      "loss": 10.3731,
      "step": 12
    },
    {
      "epoch": 0.016352201257861635,
      "grad_norm": 0.07335679978132248,
      "learning_rate": 9.993849845741524e-05,
      "loss": 10.3721,
      "step": 13
    },
    {
      "epoch": 0.01761006289308176,
      "grad_norm": 0.07778532058000565,
      "learning_rate": 9.989068136093873e-05,
      "loss": 10.3727,
      "step": 14
    },
    {
      "epoch": 0.018867924528301886,
      "grad_norm": 0.08464192599058151,
      "learning_rate": 9.98292246503335e-05,
      "loss": 10.3715,
      "step": 15
    },
    {
      "epoch": 0.02012578616352201,
      "grad_norm": 0.07666515558958054,
      "learning_rate": 9.975414512725057e-05,
      "loss": 10.3705,
      "step": 16
    },
    {
      "epoch": 0.021383647798742137,
      "grad_norm": 0.08507933467626572,
      "learning_rate": 9.966546331768191e-05,
      "loss": 10.3713,
      "step": 17
    },
    {
      "epoch": 0.022641509433962263,
      "grad_norm": 0.08501887321472168,
      "learning_rate": 9.956320346634876e-05,
      "loss": 10.3707,
      "step": 18
    },
    {
      "epoch": 0.02389937106918239,
      "grad_norm": 0.09447915107011795,
      "learning_rate": 9.944739353007344e-05,
      "loss": 10.3723,
      "step": 19
    },
    {
      "epoch": 0.025157232704402517,
      "grad_norm": 0.09398620575666428,
      "learning_rate": 9.931806517013612e-05,
      "loss": 10.3687,
      "step": 20
    },
    {
      "epoch": 0.026415094339622643,
      "grad_norm": 0.10066643357276917,
      "learning_rate": 9.917525374361912e-05,
      "loss": 10.3696,
      "step": 21
    },
    {
      "epoch": 0.027672955974842768,
      "grad_norm": 0.10919738560914993,
      "learning_rate": 9.901899829374047e-05,
      "loss": 10.3668,
      "step": 22
    },
    {
      "epoch": 0.028930817610062894,
      "grad_norm": 0.12229104340076447,
      "learning_rate": 9.884934153917997e-05,
      "loss": 10.3678,
      "step": 23
    },
    {
      "epoch": 0.03018867924528302,
      "grad_norm": 0.11512572318315506,
      "learning_rate": 9.86663298624003e-05,
      "loss": 10.3675,
      "step": 24
    },
    {
      "epoch": 0.031446540880503145,
      "grad_norm": 0.1288090944290161,
      "learning_rate": 9.847001329696653e-05,
      "loss": 10.3658,
      "step": 25
    },
    {
      "epoch": 0.03270440251572327,
      "grad_norm": 0.1288468837738037,
      "learning_rate": 9.826044551386744e-05,
      "loss": 10.3638,
      "step": 26
    },
    {
      "epoch": 0.033962264150943396,
      "grad_norm": 0.15287871658802032,
      "learning_rate": 9.803768380684242e-05,
      "loss": 10.3627,
      "step": 27
    },
    {
      "epoch": 0.03522012578616352,
      "grad_norm": 0.14995208382606506,
      "learning_rate": 9.780178907671789e-05,
      "loss": 10.3658,
      "step": 28
    },
    {
      "epoch": 0.03647798742138365,
      "grad_norm": 0.16352064907550812,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.363,
      "step": 29
    },
    {
      "epoch": 0.03773584905660377,
      "grad_norm": 0.1616298109292984,
      "learning_rate": 9.729086208503174e-05,
      "loss": 10.362,
      "step": 30
    },
    {
      "epoch": 0.0389937106918239,
      "grad_norm": 0.18207941949367523,
      "learning_rate": 9.701596950580806e-05,
      "loss": 10.3582,
      "step": 31
    },
    {
      "epoch": 0.04025157232704402,
      "grad_norm": 0.17258626222610474,
      "learning_rate": 9.672822322997305e-05,
      "loss": 10.3591,
      "step": 32
    },
    {
      "epoch": 0.04150943396226415,
      "grad_norm": 0.1723157912492752,
      "learning_rate": 9.642770192448536e-05,
      "loss": 10.3575,
      "step": 33
    },
    {
      "epoch": 0.042767295597484274,
      "grad_norm": 0.1635301411151886,
      "learning_rate": 9.611448774886924e-05,
      "loss": 10.3578,
      "step": 34
    },
    {
      "epoch": 0.0440251572327044,
      "grad_norm": 0.18812069296836853,
      "learning_rate": 9.578866633275288e-05,
      "loss": 10.3569,
      "step": 35
    },
    {
      "epoch": 0.045283018867924525,
      "grad_norm": 0.17699386179447174,
      "learning_rate": 9.545032675245813e-05,
      "loss": 10.3525,
      "step": 36
    },
    {
      "epoch": 0.04654088050314465,
      "grad_norm": 0.17810064554214478,
      "learning_rate": 9.509956150664796e-05,
      "loss": 10.3524,
      "step": 37
    },
    {
      "epoch": 0.04779874213836478,
      "grad_norm": 0.1659187227487564,
      "learning_rate": 9.473646649103818e-05,
      "loss": 10.3481,
      "step": 38
    },
    {
      "epoch": 0.04905660377358491,
      "grad_norm": 0.15193907916545868,
      "learning_rate": 9.43611409721806e-05,
      "loss": 10.3503,
      "step": 39
    },
    {
      "epoch": 0.050314465408805034,
      "grad_norm": 0.16581708192825317,
      "learning_rate": 9.397368756032445e-05,
      "loss": 10.3489,
      "step": 40
    },
    {
      "epoch": 0.05157232704402516,
      "grad_norm": 0.14731748402118683,
      "learning_rate": 9.357421218136386e-05,
      "loss": 10.3484,
      "step": 41
    },
    {
      "epoch": 0.052830188679245285,
      "grad_norm": 0.12889303267002106,
      "learning_rate": 9.316282404787871e-05,
      "loss": 10.3448,
      "step": 42
    },
    {
      "epoch": 0.05408805031446541,
      "grad_norm": 0.14560353755950928,
      "learning_rate": 9.273963562927695e-05,
      "loss": 10.3448,
      "step": 43
    },
    {
      "epoch": 0.055345911949685536,
      "grad_norm": 0.12265373766422272,
      "learning_rate": 9.230476262104677e-05,
      "loss": 10.3433,
      "step": 44
    },
    {
      "epoch": 0.05660377358490566,
      "grad_norm": 0.13917139172554016,
      "learning_rate": 9.185832391312644e-05,
      "loss": 10.34,
      "step": 45
    },
    {
      "epoch": 0.05786163522012579,
      "grad_norm": 0.10753589868545532,
      "learning_rate": 9.140044155740101e-05,
      "loss": 10.3415,
      "step": 46
    },
    {
      "epoch": 0.05911949685534591,
      "grad_norm": 0.0811968594789505,
      "learning_rate": 9.093124073433463e-05,
      "loss": 10.3417,
      "step": 47
    },
    {
      "epoch": 0.06037735849056604,
      "grad_norm": 0.11372454464435577,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3455,
      "step": 48
    },
    {
      "epoch": 0.061635220125786164,
      "grad_norm": 0.1224861592054367,
      "learning_rate": 8.995939984474624e-05,
      "loss": 10.3371,
      "step": 49
    },
    {
      "epoch": 0.06289308176100629,
      "grad_norm": 0.15765050053596497,
      "learning_rate": 8.945702546981969e-05,
      "loss": 10.3347,
      "step": 50
    },
    {
      "epoch": 0.06289308176100629,
      "eval_loss": 10.346579551696777,
      "eval_runtime": 2.8076,
      "eval_samples_per_second": 476.923,
      "eval_steps_per_second": 119.32,
      "step": 50
    },
    {
      "epoch": 0.06415094339622641,
      "grad_norm": 0.20373915135860443,
      "learning_rate": 8.894386393810563e-05,
      "loss": 10.357,
      "step": 51
    },
    {
      "epoch": 0.06540880503144654,
      "grad_norm": 0.13907502591609955,
      "learning_rate": 8.842005554284296e-05,
      "loss": 10.3547,
      "step": 52
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 0.10302690416574478,
      "learning_rate": 8.788574348801675e-05,
      "loss": 10.3524,
      "step": 53
    },
    {
      "epoch": 0.06792452830188679,
      "grad_norm": 0.09686433523893356,
      "learning_rate": 8.73410738492077e-05,
      "loss": 10.3531,
      "step": 54
    },
    {
      "epoch": 0.06918238993710692,
      "grad_norm": 0.09991912543773651,
      "learning_rate": 8.678619553365659e-05,
      "loss": 10.351,
      "step": 55
    },
    {
      "epoch": 0.07044025157232704,
      "grad_norm": 0.09921389818191528,
      "learning_rate": 8.622126023955446e-05,
      "loss": 10.3535,
      "step": 56
    },
    {
      "epoch": 0.07169811320754717,
      "grad_norm": 0.08701566606760025,
      "learning_rate": 8.564642241456986e-05,
      "loss": 10.3542,
      "step": 57
    },
    {
      "epoch": 0.0729559748427673,
      "grad_norm": 0.10219220072031021,
      "learning_rate": 8.506183921362443e-05,
      "loss": 10.3552,
      "step": 58
    },
    {
      "epoch": 0.07421383647798742,
      "grad_norm": 0.10533212870359421,
      "learning_rate": 8.44676704559283e-05,
      "loss": 10.3532,
      "step": 59
    },
    {
      "epoch": 0.07547169811320754,
      "grad_norm": 0.09530836343765259,
      "learning_rate": 8.386407858128706e-05,
      "loss": 10.3532,
      "step": 60
    },
    {
      "epoch": 0.07672955974842767,
      "grad_norm": 0.10432213544845581,
      "learning_rate": 8.32512286056924e-05,
      "loss": 10.3523,
      "step": 61
    },
    {
      "epoch": 0.0779874213836478,
      "grad_norm": 0.0899193212389946,
      "learning_rate": 8.262928807620843e-05,
      "loss": 10.3501,
      "step": 62
    },
    {
      "epoch": 0.07924528301886792,
      "grad_norm": 0.093780517578125,
      "learning_rate": 8.199842702516583e-05,
      "loss": 10.3494,
      "step": 63
    },
    {
      "epoch": 0.08050314465408805,
      "grad_norm": 0.07790330797433853,
      "learning_rate": 8.135881792367686e-05,
      "loss": 10.3472,
      "step": 64
    },
    {
      "epoch": 0.08176100628930817,
      "grad_norm": 0.07598777115345001,
      "learning_rate": 8.07106356344834e-05,
      "loss": 10.346,
      "step": 65
    },
    {
      "epoch": 0.0830188679245283,
      "grad_norm": 0.07190755009651184,
      "learning_rate": 8.005405736415126e-05,
      "loss": 10.3466,
      "step": 66
    },
    {
      "epoch": 0.08427672955974842,
      "grad_norm": 0.06125994399189949,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3462,
      "step": 67
    },
    {
      "epoch": 0.08553459119496855,
      "grad_norm": 0.07972890883684158,
      "learning_rate": 7.871643313414718e-05,
      "loss": 10.3468,
      "step": 68
    },
    {
      "epoch": 0.08679245283018867,
      "grad_norm": 0.06964690238237381,
      "learning_rate": 7.803575286758364e-05,
      "loss": 10.3459,
      "step": 69
    },
    {
      "epoch": 0.0880503144654088,
      "grad_norm": 0.08247006684541702,
      "learning_rate": 7.734740790612136e-05,
      "loss": 10.3456,
      "step": 70
    },
    {
      "epoch": 0.08930817610062892,
      "grad_norm": 0.07849586009979248,
      "learning_rate": 7.66515864363997e-05,
      "loss": 10.3472,
      "step": 71
    },
    {
      "epoch": 0.09056603773584905,
      "grad_norm": 0.08514388650655746,
      "learning_rate": 7.594847868906076e-05,
      "loss": 10.3455,
      "step": 72
    },
    {
      "epoch": 0.09182389937106918,
      "grad_norm": 0.06918893754482269,
      "learning_rate": 7.52382768867422e-05,
      "loss": 10.3477,
      "step": 73
    },
    {
      "epoch": 0.0930817610062893,
      "grad_norm": 0.07320869714021683,
      "learning_rate": 7.452117519152542e-05,
      "loss": 10.3464,
      "step": 74
    },
    {
      "epoch": 0.09433962264150944,
      "grad_norm": 0.053462397307157516,
      "learning_rate": 7.379736965185368e-05,
      "loss": 10.3457,
      "step": 75
    },
    {
      "epoch": 0.09559748427672957,
      "grad_norm": 0.06765273213386536,
      "learning_rate": 7.30670581489344e-05,
      "loss": 10.3437,
      "step": 76
    },
    {
      "epoch": 0.09685534591194969,
      "grad_norm": 0.07632695883512497,
      "learning_rate": 7.233044034264034e-05,
      "loss": 10.3469,
      "step": 77
    },
    {
      "epoch": 0.09811320754716982,
      "grad_norm": 0.05615519359707832,
      "learning_rate": 7.158771761692464e-05,
      "loss": 10.3409,
      "step": 78
    },
    {
      "epoch": 0.09937106918238994,
      "grad_norm": 0.06486508250236511,
      "learning_rate": 7.083909302476453e-05,
      "loss": 10.3425,
      "step": 79
    },
    {
      "epoch": 0.10062893081761007,
      "grad_norm": 0.06389287114143372,
      "learning_rate": 7.008477123264848e-05,
      "loss": 10.3419,
      "step": 80
    },
    {
      "epoch": 0.1018867924528302,
      "grad_norm": 0.06854084879159927,
      "learning_rate": 6.932495846462261e-05,
      "loss": 10.3437,
      "step": 81
    },
    {
      "epoch": 0.10314465408805032,
      "grad_norm": 0.06664920598268509,
      "learning_rate": 6.855986244591104e-05,
      "loss": 10.3447,
      "step": 82
    },
    {
      "epoch": 0.10440251572327044,
      "grad_norm": 0.06491422653198242,
      "learning_rate": 6.778969234612584e-05,
      "loss": 10.3418,
      "step": 83
    },
    {
      "epoch": 0.10566037735849057,
      "grad_norm": 0.0585564523935318,
      "learning_rate": 6.701465872208216e-05,
      "loss": 10.3426,
      "step": 84
    },
    {
      "epoch": 0.1069182389937107,
      "grad_norm": 0.08702181279659271,
      "learning_rate": 6.623497346023418e-05,
      "loss": 10.3394,
      "step": 85
    },
    {
      "epoch": 0.10817610062893082,
      "grad_norm": 0.06520400196313858,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3412,
      "step": 86
    },
    {
      "epoch": 0.10943396226415095,
      "grad_norm": 0.0648193359375,
      "learning_rate": 6.466250186922325e-05,
      "loss": 10.3417,
      "step": 87
    },
    {
      "epoch": 0.11069182389937107,
      "grad_norm": 0.06995167583227158,
      "learning_rate": 6.387014543809223e-05,
      "loss": 10.3416,
      "step": 88
    },
    {
      "epoch": 0.1119496855345912,
      "grad_norm": 0.06437996029853821,
      "learning_rate": 6.307399704769099e-05,
      "loss": 10.339,
      "step": 89
    },
    {
      "epoch": 0.11320754716981132,
      "grad_norm": 0.08533439040184021,
      "learning_rate": 6.227427435703997e-05,
      "loss": 10.3401,
      "step": 90
    },
    {
      "epoch": 0.11446540880503145,
      "grad_norm": 0.07717045396566391,
      "learning_rate": 6.147119600233758e-05,
      "loss": 10.3393,
      "step": 91
    },
    {
      "epoch": 0.11572327044025157,
      "grad_norm": 0.08750893175601959,
      "learning_rate": 6.066498153718735e-05,
      "loss": 10.3357,
      "step": 92
    },
    {
      "epoch": 0.1169811320754717,
      "grad_norm": 0.08522073179483414,
      "learning_rate": 5.985585137257401e-05,
      "loss": 10.3403,
      "step": 93
    },
    {
      "epoch": 0.11823899371069183,
      "grad_norm": 0.10059858113527298,
      "learning_rate": 5.90440267166055e-05,
      "loss": 10.3349,
      "step": 94
    },
    {
      "epoch": 0.11949685534591195,
      "grad_norm": 0.05769551917910576,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 10.3365,
      "step": 95
    },
    {
      "epoch": 0.12075471698113208,
      "grad_norm": 0.06903026252985,
      "learning_rate": 5.74131823855921e-05,
      "loss": 10.3344,
      "step": 96
    },
    {
      "epoch": 0.1220125786163522,
      "grad_norm": 0.0842885971069336,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 10.3354,
      "step": 97
    },
    {
      "epoch": 0.12327044025157233,
      "grad_norm": 0.05861712247133255,
      "learning_rate": 5.577423184847932e-05,
      "loss": 10.3342,
      "step": 98
    },
    {
      "epoch": 0.12452830188679245,
      "grad_norm": 0.07835382968187332,
      "learning_rate": 5.495227651252315e-05,
      "loss": 10.3324,
      "step": 99
    },
    {
      "epoch": 0.12578616352201258,
      "grad_norm": 0.13683158159255981,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 10.3287,
      "step": 100
    },
    {
      "epoch": 0.12578616352201258,
      "eval_loss": 10.342180252075195,
      "eval_runtime": 2.8083,
      "eval_samples_per_second": 476.796,
      "eval_steps_per_second": 119.288,
      "step": 100
    },
    {
      "epoch": 0.1270440251572327,
      "grad_norm": 0.16829006373882294,
      "learning_rate": 5.330452921628497e-05,
      "loss": 10.35,
      "step": 101
    },
    {
      "epoch": 0.12830188679245283,
      "grad_norm": 0.10214440524578094,
      "learning_rate": 5.247918773366112e-05,
      "loss": 10.3491,
      "step": 102
    },
    {
      "epoch": 0.12955974842767295,
      "grad_norm": 0.08292871713638306,
      "learning_rate": 5.165316846586541e-05,
      "loss": 10.3482,
      "step": 103
    },
    {
      "epoch": 0.13081761006289308,
      "grad_norm": 0.071856290102005,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 10.3474,
      "step": 104
    },
    {
      "epoch": 0.1320754716981132,
      "grad_norm": 0.07028871774673462,
      "learning_rate": 5e-05,
      "loss": 10.3497,
      "step": 105
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 0.07992203533649445,
      "learning_rate": 4.917330276168208e-05,
      "loss": 10.3471,
      "step": 106
    },
    {
      "epoch": 0.13459119496855346,
      "grad_norm": 0.07728118449449539,
      "learning_rate": 4.834683153413459e-05,
      "loss": 10.3506,
      "step": 107
    },
    {
      "epoch": 0.13584905660377358,
      "grad_norm": 0.08815820515155792,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 10.3481,
      "step": 108
    },
    {
      "epoch": 0.1371069182389937,
      "grad_norm": 0.09084111452102661,
      "learning_rate": 4.669547078371504e-05,
      "loss": 10.3504,
      "step": 109
    },
    {
      "epoch": 0.13836477987421383,
      "grad_norm": 0.09387490153312683,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 10.3465,
      "step": 110
    },
    {
      "epoch": 0.13962264150943396,
      "grad_norm": 0.09231863915920258,
      "learning_rate": 4.504772348747687e-05,
      "loss": 10.3462,
      "step": 111
    },
    {
      "epoch": 0.14088050314465408,
      "grad_norm": 0.09010244160890579,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 10.3449,
      "step": 112
    },
    {
      "epoch": 0.1421383647798742,
      "grad_norm": 0.0757468119263649,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 10.3406,
      "step": 113
    },
    {
      "epoch": 0.14339622641509434,
      "grad_norm": 0.06914759427309036,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 10.3429,
      "step": 114
    },
    {
      "epoch": 0.14465408805031446,
      "grad_norm": 0.06821081787347794,
      "learning_rate": 4.17702704859633e-05,
      "loss": 10.3403,
      "step": 115
    },
    {
      "epoch": 0.1459119496855346,
      "grad_norm": 0.0743262767791748,
      "learning_rate": 4.095597328339452e-05,
      "loss": 10.3445,
      "step": 116
    },
    {
      "epoch": 0.1471698113207547,
      "grad_norm": 0.07690567523241043,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 10.3432,
      "step": 117
    },
    {
      "epoch": 0.14842767295597484,
      "grad_norm": 0.062463872134685516,
      "learning_rate": 3.933501846281267e-05,
      "loss": 10.3418,
      "step": 118
    },
    {
      "epoch": 0.14968553459119496,
      "grad_norm": 0.06534265726804733,
      "learning_rate": 3.852880399766243e-05,
      "loss": 10.3406,
      "step": 119
    },
    {
      "epoch": 0.1509433962264151,
      "grad_norm": 0.06799394637346268,
      "learning_rate": 3.772572564296005e-05,
      "loss": 10.3435,
      "step": 120
    },
    {
      "epoch": 0.15220125786163521,
      "grad_norm": 0.07413194328546524,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 10.3407,
      "step": 121
    },
    {
      "epoch": 0.15345911949685534,
      "grad_norm": 0.06097736954689026,
      "learning_rate": 3.612985456190778e-05,
      "loss": 10.3412,
      "step": 122
    },
    {
      "epoch": 0.15471698113207547,
      "grad_norm": 0.07089071720838547,
      "learning_rate": 3.533749813077677e-05,
      "loss": 10.3405,
      "step": 123
    },
    {
      "epoch": 0.1559748427672956,
      "grad_norm": 0.07079850137233734,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.3408,
      "step": 124
    },
    {
      "epoch": 0.15723270440251572,
      "grad_norm": 0.0693952664732933,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 10.3398,
      "step": 125
    },
    {
      "epoch": 0.15849056603773584,
      "grad_norm": 0.0659995824098587,
      "learning_rate": 3.298534127791785e-05,
      "loss": 10.3411,
      "step": 126
    },
    {
      "epoch": 0.15974842767295597,
      "grad_norm": 0.06219927966594696,
      "learning_rate": 3.221030765387417e-05,
      "loss": 10.3386,
      "step": 127
    },
    {
      "epoch": 0.1610062893081761,
      "grad_norm": 0.07468194514513016,
      "learning_rate": 3.144013755408895e-05,
      "loss": 10.3363,
      "step": 128
    },
    {
      "epoch": 0.16226415094339622,
      "grad_norm": 0.07858281582593918,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 10.3408,
      "step": 129
    },
    {
      "epoch": 0.16352201257861634,
      "grad_norm": 0.08168749511241913,
      "learning_rate": 2.991522876735154e-05,
      "loss": 10.3399,
      "step": 130
    },
    {
      "epoch": 0.16477987421383647,
      "grad_norm": 0.07804001122713089,
      "learning_rate": 2.916090697523549e-05,
      "loss": 10.339,
      "step": 131
    },
    {
      "epoch": 0.1660377358490566,
      "grad_norm": 0.0697825625538826,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 10.3375,
      "step": 132
    },
    {
      "epoch": 0.16729559748427672,
      "grad_norm": 0.06571916490793228,
      "learning_rate": 2.766955965735968e-05,
      "loss": 10.3361,
      "step": 133
    },
    {
      "epoch": 0.16855345911949685,
      "grad_norm": 0.06645193696022034,
      "learning_rate": 2.693294185106562e-05,
      "loss": 10.3366,
      "step": 134
    },
    {
      "epoch": 0.16981132075471697,
      "grad_norm": 0.06530148535966873,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 10.337,
      "step": 135
    },
    {
      "epoch": 0.1710691823899371,
      "grad_norm": 0.07109314203262329,
      "learning_rate": 2.547882480847461e-05,
      "loss": 10.3328,
      "step": 136
    },
    {
      "epoch": 0.17232704402515722,
      "grad_norm": 0.0944875180721283,
      "learning_rate": 2.476172311325783e-05,
      "loss": 10.3338,
      "step": 137
    },
    {
      "epoch": 0.17358490566037735,
      "grad_norm": 0.0718129575252533,
      "learning_rate": 2.405152131093926e-05,
      "loss": 10.3356,
      "step": 138
    },
    {
      "epoch": 0.17484276729559747,
      "grad_norm": 0.076311856508255,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 10.3356,
      "step": 139
    },
    {
      "epoch": 0.1761006289308176,
      "grad_norm": 0.07428840547800064,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 10.3343,
      "step": 140
    },
    {
      "epoch": 0.17735849056603772,
      "grad_norm": 0.07271865755319595,
      "learning_rate": 2.196424713241637e-05,
      "loss": 10.3349,
      "step": 141
    },
    {
      "epoch": 0.17861635220125785,
      "grad_norm": 0.07106521725654602,
      "learning_rate": 2.128356686585282e-05,
      "loss": 10.3327,
      "step": 142
    },
    {
      "epoch": 0.17987421383647798,
      "grad_norm": 0.094117172062397,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3336,
      "step": 143
    },
    {
      "epoch": 0.1811320754716981,
      "grad_norm": 0.06027039885520935,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 10.3339,
      "step": 144
    },
    {
      "epoch": 0.18238993710691823,
      "grad_norm": 0.1071876809000969,
      "learning_rate": 1.928936436551661e-05,
      "loss": 10.331,
      "step": 145
    },
    {
      "epoch": 0.18364779874213835,
      "grad_norm": 0.08291321247816086,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 10.3309,
      "step": 146
    },
    {
      "epoch": 0.18490566037735848,
      "grad_norm": 0.08659283071756363,
      "learning_rate": 1.800157297483417e-05,
      "loss": 10.329,
      "step": 147
    },
    {
      "epoch": 0.1861635220125786,
      "grad_norm": 0.07780143618583679,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 10.329,
      "step": 148
    },
    {
      "epoch": 0.18742138364779873,
      "grad_norm": 0.09116362035274506,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 10.3259,
      "step": 149
    },
    {
      "epoch": 0.18867924528301888,
      "grad_norm": 0.15961508452892303,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 10.3215,
      "step": 150
    },
    {
      "epoch": 0.18867924528301888,
      "eval_loss": 10.337943077087402,
      "eval_runtime": 2.8074,
      "eval_samples_per_second": 476.954,
      "eval_steps_per_second": 119.328,
      "step": 150
    },
    {
      "epoch": 0.189937106918239,
      "grad_norm": 0.1443028301000595,
      "learning_rate": 1.553232954407171e-05,
      "loss": 10.3469,
      "step": 151
    },
    {
      "epoch": 0.19119496855345913,
      "grad_norm": 0.1174471378326416,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 10.3457,
      "step": 152
    },
    {
      "epoch": 0.19245283018867926,
      "grad_norm": 0.060474835336208344,
      "learning_rate": 1.435357758543015e-05,
      "loss": 10.345,
      "step": 153
    },
    {
      "epoch": 0.19371069182389938,
      "grad_norm": 0.06148985028266907,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 10.3475,
      "step": 154
    },
    {
      "epoch": 0.1949685534591195,
      "grad_norm": 0.06383097916841507,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 10.3447,
      "step": 155
    },
    {
      "epoch": 0.19622641509433963,
      "grad_norm": 0.06898840516805649,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 10.3441,
      "step": 156
    },
    {
      "epoch": 0.19748427672955976,
      "grad_norm": 0.06910186260938644,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 10.3477,
      "step": 157
    },
    {
      "epoch": 0.19874213836477989,
      "grad_norm": 0.07637208700180054,
      "learning_rate": 1.157994445715706e-05,
      "loss": 10.3459,
      "step": 158
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.08541613817214966,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 10.3446,
      "step": 159
    },
    {
      "epoch": 0.20125786163522014,
      "grad_norm": 0.07373882830142975,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 10.3437,
      "step": 160
    },
    {
      "epoch": 0.20251572327044026,
      "grad_norm": 0.07668569684028625,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 10.3426,
      "step": 161
    },
    {
      "epoch": 0.2037735849056604,
      "grad_norm": 0.07920914143323898,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.3405,
      "step": 162
    },
    {
      "epoch": 0.2050314465408805,
      "grad_norm": 0.07557826489210129,
      "learning_rate": 9.068759265665384e-06,
      "loss": 10.338,
      "step": 163
    },
    {
      "epoch": 0.20628930817610064,
      "grad_norm": 0.060079172253608704,
      "learning_rate": 8.599558442598998e-06,
      "loss": 10.3402,
      "step": 164
    },
    {
      "epoch": 0.20754716981132076,
      "grad_norm": 0.07464677095413208,
      "learning_rate": 8.141676086873572e-06,
      "loss": 10.3411,
      "step": 165
    },
    {
      "epoch": 0.2088050314465409,
      "grad_norm": 0.06779949367046356,
      "learning_rate": 7.695237378953223e-06,
      "loss": 10.3417,
      "step": 166
    },
    {
      "epoch": 0.21006289308176102,
      "grad_norm": 0.06503839790821075,
      "learning_rate": 7.260364370723044e-06,
      "loss": 10.3416,
      "step": 167
    },
    {
      "epoch": 0.21132075471698114,
      "grad_norm": 0.06535510718822479,
      "learning_rate": 6.837175952121306e-06,
      "loss": 10.3424,
      "step": 168
    },
    {
      "epoch": 0.21257861635220127,
      "grad_norm": 0.06771840155124664,
      "learning_rate": 6.425787818636131e-06,
      "loss": 10.341,
      "step": 169
    },
    {
      "epoch": 0.2138364779874214,
      "grad_norm": 0.07385121285915375,
      "learning_rate": 6.026312439675552e-06,
      "loss": 10.3386,
      "step": 170
    },
    {
      "epoch": 0.21509433962264152,
      "grad_norm": 0.05837663263082504,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 10.3408,
      "step": 171
    },
    {
      "epoch": 0.21635220125786164,
      "grad_norm": 0.06223186478018761,
      "learning_rate": 5.263533508961827e-06,
      "loss": 10.3391,
      "step": 172
    },
    {
      "epoch": 0.21761006289308177,
      "grad_norm": 0.053905993700027466,
      "learning_rate": 4.900438493352055e-06,
      "loss": 10.3362,
      "step": 173
    },
    {
      "epoch": 0.2188679245283019,
      "grad_norm": 0.07273418456315994,
      "learning_rate": 4.549673247541875e-06,
      "loss": 10.3347,
      "step": 174
    },
    {
      "epoch": 0.22012578616352202,
      "grad_norm": 0.07494191080331802,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 10.3351,
      "step": 175
    },
    {
      "epoch": 0.22138364779874214,
      "grad_norm": 0.07365655153989792,
      "learning_rate": 3.885512251130763e-06,
      "loss": 10.34,
      "step": 176
    },
    {
      "epoch": 0.22264150943396227,
      "grad_norm": 0.07057920843362808,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 10.3376,
      "step": 177
    },
    {
      "epoch": 0.2238993710691824,
      "grad_norm": 0.07610414177179337,
      "learning_rate": 3.271776770026963e-06,
      "loss": 10.3353,
      "step": 178
    },
    {
      "epoch": 0.22515723270440252,
      "grad_norm": 0.0696873590350151,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 10.3371,
      "step": 179
    },
    {
      "epoch": 0.22641509433962265,
      "grad_norm": 0.07698570191860199,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 10.3369,
      "step": 180
    },
    {
      "epoch": 0.22767295597484277,
      "grad_norm": 0.07439422607421875,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.3366,
      "step": 181
    },
    {
      "epoch": 0.2289308176100629,
      "grad_norm": 0.06881588697433472,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 10.3302,
      "step": 182
    },
    {
      "epoch": 0.23018867924528302,
      "grad_norm": 0.07513081282377243,
      "learning_rate": 1.962316193157593e-06,
      "loss": 10.3322,
      "step": 183
    },
    {
      "epoch": 0.23144654088050315,
      "grad_norm": 0.06894870847463608,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 10.3348,
      "step": 184
    },
    {
      "epoch": 0.23270440251572327,
      "grad_norm": 0.0848296731710434,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 10.3322,
      "step": 185
    },
    {
      "epoch": 0.2339622641509434,
      "grad_norm": 0.06908418238162994,
      "learning_rate": 1.333670137599713e-06,
      "loss": 10.3334,
      "step": 186
    },
    {
      "epoch": 0.23522012578616353,
      "grad_norm": 0.06873072683811188,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 10.3327,
      "step": 187
    },
    {
      "epoch": 0.23647798742138365,
      "grad_norm": 0.08577898144721985,
      "learning_rate": 9.810017062595322e-07,
      "loss": 10.3285,
      "step": 188
    },
    {
      "epoch": 0.23773584905660378,
      "grad_norm": 0.08834285289049149,
      "learning_rate": 8.247462563808817e-07,
      "loss": 10.3326,
      "step": 189
    },
    {
      "epoch": 0.2389937106918239,
      "grad_norm": 0.07424641400575638,
      "learning_rate": 6.819348298638839e-07,
      "loss": 10.3318,
      "step": 190
    },
    {
      "epoch": 0.24025157232704403,
      "grad_norm": 0.06382283568382263,
      "learning_rate": 5.526064699265753e-07,
      "loss": 10.3344,
      "step": 191
    },
    {
      "epoch": 0.24150943396226415,
      "grad_norm": 0.08855995535850525,
      "learning_rate": 4.367965336512403e-07,
      "loss": 10.3314,
      "step": 192
    },
    {
      "epoch": 0.24276729559748428,
      "grad_norm": 0.08993738889694214,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 10.3304,
      "step": 193
    },
    {
      "epoch": 0.2440251572327044,
      "grad_norm": 0.08923917263746262,
      "learning_rate": 2.458548727494292e-07,
      "loss": 10.3319,
      "step": 194
    },
    {
      "epoch": 0.24528301886792453,
      "grad_norm": 0.07801834493875504,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 10.3285,
      "step": 195
    },
    {
      "epoch": 0.24654088050314465,
      "grad_norm": 0.08305680751800537,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 10.3333,
      "step": 196
    },
    {
      "epoch": 0.24779874213836478,
      "grad_norm": 0.08010074496269226,
      "learning_rate": 6.150154258476315e-08,
      "loss": 10.3277,
      "step": 197
    },
    {
      "epoch": 0.2490566037735849,
      "grad_norm": 0.08962223678827286,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 10.3303,
      "step": 198
    },
    {
      "epoch": 0.25031446540880503,
      "grad_norm": 0.10381283611059189,
      "learning_rate": 6.834750376549792e-09,
      "loss": 10.3316,
      "step": 199
    },
    {
      "epoch": 0.25157232704402516,
      "grad_norm": 0.1311977058649063,
      "learning_rate": 0.0,
      "loss": 10.3252,
      "step": 200
    },
    {
      "epoch": 0.25157232704402516,
      "eval_loss": 10.33694076538086,
      "eval_runtime": 2.8077,
      "eval_samples_per_second": 476.91,
      "eval_steps_per_second": 119.317,
      "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": 22421682782208.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}