{
  "best_metric": 1.4234563112258911,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.24848578971890045,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0024848578971890046,
      "grad_norm": 2.213345527648926,
      "learning_rate": 2e-05,
      "loss": 1.3872,
      "step": 1
    },
    {
      "epoch": 0.0024848578971890046,
      "eval_loss": 2.3529415130615234,
      "eval_runtime": 0.5026,
      "eval_samples_per_second": 99.48,
      "eval_steps_per_second": 25.865,
      "step": 1
    },
    {
      "epoch": 0.004969715794378009,
      "grad_norm": 2.8364529609680176,
      "learning_rate": 4e-05,
      "loss": 1.4444,
      "step": 2
    },
    {
      "epoch": 0.007454573691567014,
      "grad_norm": 1.7703208923339844,
      "learning_rate": 6e-05,
      "loss": 1.5407,
      "step": 3
    },
    {
      "epoch": 0.009939431588756018,
      "grad_norm": 0.7865042686462402,
      "learning_rate": 8e-05,
      "loss": 1.5653,
      "step": 4
    },
    {
      "epoch": 0.012424289485945022,
      "grad_norm": 0.8928652405738831,
      "learning_rate": 0.0001,
      "loss": 1.6448,
      "step": 5
    },
    {
      "epoch": 0.014909147383134027,
      "grad_norm": 1.403510332107544,
      "learning_rate": 9.997539658034168e-05,
      "loss": 1.8179,
      "step": 6
    },
    {
      "epoch": 0.017394005280323033,
      "grad_norm": 1.432464599609375,
      "learning_rate": 9.990161322484486e-05,
      "loss": 1.8834,
      "step": 7
    },
    {
      "epoch": 0.019878863177512036,
      "grad_norm": 1.4054795503616333,
      "learning_rate": 9.977873061452552e-05,
      "loss": 1.9963,
      "step": 8
    },
    {
      "epoch": 0.02236372107470104,
      "grad_norm": 2.726348876953125,
      "learning_rate": 9.96068831197139e-05,
      "loss": 2.3706,
      "step": 9
    },
    {
      "epoch": 0.024848578971890044,
      "grad_norm": 2.5260682106018066,
      "learning_rate": 9.938625865312251e-05,
      "loss": 2.4257,
      "step": 10
    },
    {
      "epoch": 0.02733343686907905,
      "grad_norm": 2.9714224338531494,
      "learning_rate": 9.911709846436641e-05,
      "loss": 2.4314,
      "step": 11
    },
    {
      "epoch": 0.029818294766268055,
      "grad_norm": 4.160161972045898,
      "learning_rate": 9.879969687616027e-05,
      "loss": 2.7894,
      "step": 12
    },
    {
      "epoch": 0.03230315266345706,
      "grad_norm": 0.6694028973579407,
      "learning_rate": 9.84344009624807e-05,
      "loss": 1.2134,
      "step": 13
    },
    {
      "epoch": 0.034788010560646065,
      "grad_norm": 0.585831344127655,
      "learning_rate": 9.80216101690461e-05,
      "loss": 1.3008,
      "step": 14
    },
    {
      "epoch": 0.03727286845783507,
      "grad_norm": 0.44409918785095215,
      "learning_rate": 9.756177587652856e-05,
      "loss": 1.2994,
      "step": 15
    },
    {
      "epoch": 0.03975772635502407,
      "grad_norm": 0.47101661562919617,
      "learning_rate": 9.705540090697575e-05,
      "loss": 1.3609,
      "step": 16
    },
    {
      "epoch": 0.042242584252213077,
      "grad_norm": 0.366786926984787,
      "learning_rate": 9.650303897398232e-05,
      "loss": 1.3769,
      "step": 17
    },
    {
      "epoch": 0.04472744214940208,
      "grad_norm": 0.4264712333679199,
      "learning_rate": 9.590529407721231e-05,
      "loss": 1.4,
      "step": 18
    },
    {
      "epoch": 0.047212300046591084,
      "grad_norm": 0.48432719707489014,
      "learning_rate": 9.526281984193436e-05,
      "loss": 1.4577,
      "step": 19
    },
    {
      "epoch": 0.04969715794378009,
      "grad_norm": 0.5458565354347229,
      "learning_rate": 9.4576318804292e-05,
      "loss": 1.5155,
      "step": 20
    },
    {
      "epoch": 0.05218201584096909,
      "grad_norm": 0.7800182104110718,
      "learning_rate": 9.384654164309083e-05,
      "loss": 1.7264,
      "step": 21
    },
    {
      "epoch": 0.0546668737381581,
      "grad_norm": 1.0161879062652588,
      "learning_rate": 9.30742863589421e-05,
      "loss": 1.8173,
      "step": 22
    },
    {
      "epoch": 0.057151731635347106,
      "grad_norm": 1.664415955543518,
      "learning_rate": 9.226039740166091e-05,
      "loss": 1.8517,
      "step": 23
    },
    {
      "epoch": 0.05963658953253611,
      "grad_norm": 1.7926095724105835,
      "learning_rate": 9.140576474687264e-05,
      "loss": 2.2677,
      "step": 24
    },
    {
      "epoch": 0.06212144742972511,
      "grad_norm": 2.9434328079223633,
      "learning_rate": 9.051132292283771e-05,
      "loss": 2.7369,
      "step": 25
    },
    {
      "epoch": 0.06212144742972511,
      "eval_loss": 1.5853602886199951,
      "eval_runtime": 0.5018,
      "eval_samples_per_second": 99.639,
      "eval_steps_per_second": 25.906,
      "step": 25
    },
    {
      "epoch": 0.06460630532691412,
      "grad_norm": 0.4380030035972595,
      "learning_rate": 8.957804998855866e-05,
      "loss": 1.1567,
      "step": 26
    },
    {
      "epoch": 0.06709116322410312,
      "grad_norm": 0.5094096064567566,
      "learning_rate": 8.860696646428693e-05,
      "loss": 1.2427,
      "step": 27
    },
    {
      "epoch": 0.06957602112129213,
      "grad_norm": 0.472796231508255,
      "learning_rate": 8.759913421559902e-05,
      "loss": 1.2684,
      "step": 28
    },
    {
      "epoch": 0.07206087901848113,
      "grad_norm": 0.48177894949913025,
      "learning_rate": 8.655565529226198e-05,
      "loss": 1.3198,
      "step": 29
    },
    {
      "epoch": 0.07454573691567014,
      "grad_norm": 0.4852677285671234,
      "learning_rate": 8.547767072315835e-05,
      "loss": 1.3428,
      "step": 30
    },
    {
      "epoch": 0.07703059481285914,
      "grad_norm": 0.43640175461769104,
      "learning_rate": 8.436635926858759e-05,
      "loss": 1.3659,
      "step": 31
    },
    {
      "epoch": 0.07951545271004815,
      "grad_norm": 0.4880797564983368,
      "learning_rate": 8.322293613130917e-05,
      "loss": 1.4387,
      "step": 32
    },
    {
      "epoch": 0.08200031060723714,
      "grad_norm": 0.5233495235443115,
      "learning_rate": 8.204865162773613e-05,
      "loss": 1.4945,
      "step": 33
    },
    {
      "epoch": 0.08448516850442615,
      "grad_norm": 0.8668330311775208,
      "learning_rate": 8.084478982073247e-05,
      "loss": 1.6462,
      "step": 34
    },
    {
      "epoch": 0.08697002640161516,
      "grad_norm": 1.2236716747283936,
      "learning_rate": 7.961266711550922e-05,
      "loss": 1.659,
      "step": 35
    },
    {
      "epoch": 0.08945488429880416,
      "grad_norm": 1.5685863494873047,
      "learning_rate": 7.835363082015468e-05,
      "loss": 1.9596,
      "step": 36
    },
    {
      "epoch": 0.09193974219599317,
      "grad_norm": 2.142998456954956,
      "learning_rate": 7.706905767237288e-05,
      "loss": 2.016,
      "step": 37
    },
    {
      "epoch": 0.09442460009318217,
      "grad_norm": 0.28065016865730286,
      "learning_rate": 7.576035233404096e-05,
      "loss": 1.1157,
      "step": 38
    },
    {
      "epoch": 0.09690945799037118,
      "grad_norm": 0.2927067279815674,
      "learning_rate": 7.442894585523218e-05,
      "loss": 1.2051,
      "step": 39
    },
    {
      "epoch": 0.09939431588756018,
      "grad_norm": 0.24963538348674774,
      "learning_rate": 7.307629410938363e-05,
      "loss": 1.2006,
      "step": 40
    },
    {
      "epoch": 0.10187917378474919,
      "grad_norm": 0.2745957374572754,
      "learning_rate": 7.170387620131993e-05,
      "loss": 1.264,
      "step": 41
    },
    {
      "epoch": 0.10436403168193818,
      "grad_norm": 0.2527835965156555,
      "learning_rate": 7.031319284987394e-05,
      "loss": 1.3202,
      "step": 42
    },
    {
      "epoch": 0.1068488895791272,
      "grad_norm": 0.2923299968242645,
      "learning_rate": 6.890576474687263e-05,
      "loss": 1.3144,
      "step": 43
    },
    {
      "epoch": 0.1093337474763162,
      "grad_norm": 0.35846221446990967,
      "learning_rate": 6.7483130894283e-05,
      "loss": 1.3669,
      "step": 44
    },
    {
      "epoch": 0.1118186053735052,
      "grad_norm": 0.39263513684272766,
      "learning_rate": 6.604684692133597e-05,
      "loss": 1.4608,
      "step": 45
    },
    {
      "epoch": 0.11430346327069421,
      "grad_norm": 0.53093022108078,
      "learning_rate": 6.459848338346861e-05,
      "loss": 1.531,
      "step": 46
    },
    {
      "epoch": 0.11678832116788321,
      "grad_norm": 0.750128984451294,
      "learning_rate": 6.313962404494496e-05,
      "loss": 1.6268,
      "step": 47
    },
    {
      "epoch": 0.11927317906507222,
      "grad_norm": 1.1228125095367432,
      "learning_rate": 6.167186414703289e-05,
      "loss": 1.6107,
      "step": 48
    },
    {
      "epoch": 0.12175803696226122,
      "grad_norm": 1.3567590713500977,
      "learning_rate": 6.019680866363139e-05,
      "loss": 1.932,
      "step": 49
    },
    {
      "epoch": 0.12424289485945023,
      "grad_norm": 2.1906304359436035,
      "learning_rate": 5.8716070546254966e-05,
      "loss": 2.4177,
      "step": 50
    },
    {
      "epoch": 0.12424289485945023,
      "eval_loss": 1.4773844480514526,
      "eval_runtime": 0.5015,
      "eval_samples_per_second": 99.704,
      "eval_steps_per_second": 25.923,
      "step": 50
    },
    {
      "epoch": 0.12672775275663922,
      "grad_norm": 0.20560088753700256,
      "learning_rate": 5.7231268960295e-05,
      "loss": 1.1799,
      "step": 51
    },
    {
      "epoch": 0.12921261065382825,
      "grad_norm": 0.23120570182800293,
      "learning_rate": 5.574402751448614e-05,
      "loss": 1.2372,
      "step": 52
    },
    {
      "epoch": 0.13169746855101724,
      "grad_norm": 0.23276279866695404,
      "learning_rate": 5.425597248551387e-05,
      "loss": 1.1809,
      "step": 53
    },
    {
      "epoch": 0.13418232644820624,
      "grad_norm": 0.24758167564868927,
      "learning_rate": 5.2768731039705e-05,
      "loss": 1.2471,
      "step": 54
    },
    {
      "epoch": 0.13666718434539524,
      "grad_norm": 0.27665722370147705,
      "learning_rate": 5.128392945374505e-05,
      "loss": 1.3109,
      "step": 55
    },
    {
      "epoch": 0.13915204224258426,
      "grad_norm": 0.3292866051197052,
      "learning_rate": 4.980319133636863e-05,
      "loss": 1.3299,
      "step": 56
    },
    {
      "epoch": 0.14163690013977326,
      "grad_norm": 0.33890780806541443,
      "learning_rate": 4.83281358529671e-05,
      "loss": 1.3129,
      "step": 57
    },
    {
      "epoch": 0.14412175803696226,
      "grad_norm": 0.4250866174697876,
      "learning_rate": 4.686037595505507e-05,
      "loss": 1.5612,
      "step": 58
    },
    {
      "epoch": 0.14660661593415125,
      "grad_norm": 0.624860942363739,
      "learning_rate": 4.54015166165314e-05,
      "loss": 1.5192,
      "step": 59
    },
    {
      "epoch": 0.14909147383134028,
      "grad_norm": 0.8327329754829407,
      "learning_rate": 4.395315307866405e-05,
      "loss": 1.5965,
      "step": 60
    },
    {
      "epoch": 0.15157633172852927,
      "grad_norm": 1.0322227478027344,
      "learning_rate": 4.2516869105717004e-05,
      "loss": 1.7066,
      "step": 61
    },
    {
      "epoch": 0.15406118962571827,
      "grad_norm": 1.6692428588867188,
      "learning_rate": 4.109423525312738e-05,
      "loss": 1.9786,
      "step": 62
    },
    {
      "epoch": 0.1565460475229073,
      "grad_norm": 0.21098101139068604,
      "learning_rate": 3.968680715012606e-05,
      "loss": 1.1647,
      "step": 63
    },
    {
      "epoch": 0.1590309054200963,
      "grad_norm": 0.19633238017559052,
      "learning_rate": 3.829612379868006e-05,
      "loss": 1.1685,
      "step": 64
    },
    {
      "epoch": 0.1615157633172853,
      "grad_norm": 0.2040661871433258,
      "learning_rate": 3.692370589061639e-05,
      "loss": 1.1929,
      "step": 65
    },
    {
      "epoch": 0.16400062121447428,
      "grad_norm": 0.2036914974451065,
      "learning_rate": 3.557105414476782e-05,
      "loss": 1.2412,
      "step": 66
    },
    {
      "epoch": 0.1664854791116633,
      "grad_norm": 0.21338950097560883,
      "learning_rate": 3.423964766595906e-05,
      "loss": 1.273,
      "step": 67
    },
    {
      "epoch": 0.1689703370088523,
      "grad_norm": 0.26673391461372375,
      "learning_rate": 3.293094232762715e-05,
      "loss": 1.3177,
      "step": 68
    },
    {
      "epoch": 0.1714551949060413,
      "grad_norm": 0.3049785792827606,
      "learning_rate": 3.164636917984534e-05,
      "loss": 1.3569,
      "step": 69
    },
    {
      "epoch": 0.17394005280323033,
      "grad_norm": 0.3914351463317871,
      "learning_rate": 3.0387332884490805e-05,
      "loss": 1.4214,
      "step": 70
    },
    {
      "epoch": 0.17642491070041932,
      "grad_norm": 0.4944564998149872,
      "learning_rate": 2.9155210179267546e-05,
      "loss": 1.4842,
      "step": 71
    },
    {
      "epoch": 0.17890976859760832,
      "grad_norm": 0.7299094200134277,
      "learning_rate": 2.7951348372263875e-05,
      "loss": 1.607,
      "step": 72
    },
    {
      "epoch": 0.18139462649479732,
      "grad_norm": 0.9269328713417053,
      "learning_rate": 2.677706386869083e-05,
      "loss": 1.7074,
      "step": 73
    },
    {
      "epoch": 0.18387948439198634,
      "grad_norm": 1.1799345016479492,
      "learning_rate": 2.5633640731412412e-05,
      "loss": 1.6967,
      "step": 74
    },
    {
      "epoch": 0.18636434228917534,
      "grad_norm": 2.2998039722442627,
      "learning_rate": 2.4522329276841663e-05,
      "loss": 2.2813,
      "step": 75
    },
    {
      "epoch": 0.18636434228917534,
      "eval_loss": 1.4348056316375732,
      "eval_runtime": 0.5016,
      "eval_samples_per_second": 99.679,
      "eval_steps_per_second": 25.917,
      "step": 75
    },
    {
      "epoch": 0.18884920018636434,
      "grad_norm": 0.15302395820617676,
      "learning_rate": 2.3444344707738015e-05,
      "loss": 1.1401,
      "step": 76
    },
    {
      "epoch": 0.19133405808355336,
      "grad_norm": 0.17382937669754028,
      "learning_rate": 2.2400865784401e-05,
      "loss": 1.2122,
      "step": 77
    },
    {
      "epoch": 0.19381891598074236,
      "grad_norm": 0.19359153509140015,
      "learning_rate": 2.1393033535713093e-05,
      "loss": 1.2059,
      "step": 78
    },
    {
      "epoch": 0.19630377387793135,
      "grad_norm": 0.20696574449539185,
      "learning_rate": 2.0421950011441354e-05,
      "loss": 1.2563,
      "step": 79
    },
    {
      "epoch": 0.19878863177512035,
      "grad_norm": 0.25555720925331116,
      "learning_rate": 1.9488677077162295e-05,
      "loss": 1.2519,
      "step": 80
    },
    {
      "epoch": 0.20127348967230937,
      "grad_norm": 0.29984888434410095,
      "learning_rate": 1.8594235253127375e-05,
      "loss": 1.3702,
      "step": 81
    },
    {
      "epoch": 0.20375834756949837,
      "grad_norm": 0.38583916425704956,
      "learning_rate": 1.77396025983391e-05,
      "loss": 1.3688,
      "step": 82
    },
    {
      "epoch": 0.20624320546668737,
      "grad_norm": 0.5157633423805237,
      "learning_rate": 1.6925713641057904e-05,
      "loss": 1.5393,
      "step": 83
    },
    {
      "epoch": 0.20872806336387636,
      "grad_norm": 0.6191871762275696,
      "learning_rate": 1.6153458356909176e-05,
      "loss": 1.5415,
      "step": 84
    },
    {
      "epoch": 0.2112129212610654,
      "grad_norm": 0.7850320935249329,
      "learning_rate": 1.5423681195707997e-05,
      "loss": 1.5217,
      "step": 85
    },
    {
      "epoch": 0.2136977791582544,
      "grad_norm": 0.952873945236206,
      "learning_rate": 1.4737180158065644e-05,
      "loss": 1.6336,
      "step": 86
    },
    {
      "epoch": 0.21618263705544338,
      "grad_norm": 1.69228196144104,
      "learning_rate": 1.4094705922787687e-05,
      "loss": 2.0211,
      "step": 87
    },
    {
      "epoch": 0.2186674949526324,
      "grad_norm": 0.20387884974479675,
      "learning_rate": 1.3496961026017687e-05,
      "loss": 1.1658,
      "step": 88
    },
    {
      "epoch": 0.2211523528498214,
      "grad_norm": 0.1599428653717041,
      "learning_rate": 1.2944599093024267e-05,
      "loss": 1.1664,
      "step": 89
    },
    {
      "epoch": 0.2236372107470104,
      "grad_norm": 0.16834738850593567,
      "learning_rate": 1.2438224123471442e-05,
      "loss": 1.1621,
      "step": 90
    },
    {
      "epoch": 0.2261220686441994,
      "grad_norm": 0.18566007912158966,
      "learning_rate": 1.1978389830953907e-05,
      "loss": 1.2394,
      "step": 91
    },
    {
      "epoch": 0.22860692654138842,
      "grad_norm": 0.20164741575717926,
      "learning_rate": 1.1565599037519316e-05,
      "loss": 1.2335,
      "step": 92
    },
    {
      "epoch": 0.23109178443857742,
      "grad_norm": 0.25663846731185913,
      "learning_rate": 1.1200303123839742e-05,
      "loss": 1.2925,
      "step": 93
    },
    {
      "epoch": 0.23357664233576642,
      "grad_norm": 0.2900138795375824,
      "learning_rate": 1.088290153563358e-05,
      "loss": 1.397,
      "step": 94
    },
    {
      "epoch": 0.23606150023295544,
      "grad_norm": 0.3564670979976654,
      "learning_rate": 1.0613741346877497e-05,
      "loss": 1.3999,
      "step": 95
    },
    {
      "epoch": 0.23854635813014444,
      "grad_norm": 0.4753359854221344,
      "learning_rate": 1.0393116880286118e-05,
      "loss": 1.5083,
      "step": 96
    },
    {
      "epoch": 0.24103121602733343,
      "grad_norm": 0.8535330891609192,
      "learning_rate": 1.0221269385474488e-05,
      "loss": 1.508,
      "step": 97
    },
    {
      "epoch": 0.24351607392452243,
      "grad_norm": 0.8620418906211853,
      "learning_rate": 1.0098386775155147e-05,
      "loss": 1.6986,
      "step": 98
    },
    {
      "epoch": 0.24600093182171145,
      "grad_norm": 1.0517289638519287,
      "learning_rate": 1.0024603419658329e-05,
      "loss": 1.6832,
      "step": 99
    },
    {
      "epoch": 0.24848578971890045,
      "grad_norm": 2.3589024543762207,
      "learning_rate": 1e-05,
      "loss": 2.163,
      "step": 100
    },
    {
      "epoch": 0.24848578971890045,
      "eval_loss": 1.4234563112258911,
      "eval_runtime": 0.5013,
      "eval_samples_per_second": 99.743,
      "eval_steps_per_second": 25.933,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 1.666832784162816e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}