{
  "best_metric": 1.296454668045044,
  "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": 0.19135846197605133,
      "learning_rate": 2e-05,
      "loss": 1.1205,
      "step": 1
    },
    {
      "epoch": 0.0024848578971890046,
      "eval_loss": 1.5502378940582275,
      "eval_runtime": 1.1969,
      "eval_samples_per_second": 41.775,
      "eval_steps_per_second": 10.861,
      "step": 1
    },
    {
      "epoch": 0.004969715794378009,
      "grad_norm": 0.20889164507389069,
      "learning_rate": 4e-05,
      "loss": 1.1432,
      "step": 2
    },
    {
      "epoch": 0.007454573691567014,
      "grad_norm": 0.23940329253673553,
      "learning_rate": 6e-05,
      "loss": 1.1905,
      "step": 3
    },
    {
      "epoch": 0.009939431588756018,
      "grad_norm": 0.270460307598114,
      "learning_rate": 8e-05,
      "loss": 1.2135,
      "step": 4
    },
    {
      "epoch": 0.012424289485945022,
      "grad_norm": 0.2930460274219513,
      "learning_rate": 0.0001,
      "loss": 1.2384,
      "step": 5
    },
    {
      "epoch": 0.014909147383134027,
      "grad_norm": 0.33367636799812317,
      "learning_rate": 9.997539658034168e-05,
      "loss": 1.3348,
      "step": 6
    },
    {
      "epoch": 0.017394005280323033,
      "grad_norm": 0.39504995942115784,
      "learning_rate": 9.990161322484486e-05,
      "loss": 1.3978,
      "step": 7
    },
    {
      "epoch": 0.019878863177512036,
      "grad_norm": 0.5078551769256592,
      "learning_rate": 9.977873061452552e-05,
      "loss": 1.4639,
      "step": 8
    },
    {
      "epoch": 0.02236372107470104,
      "grad_norm": 0.7216916084289551,
      "learning_rate": 9.96068831197139e-05,
      "loss": 1.626,
      "step": 9
    },
    {
      "epoch": 0.024848578971890044,
      "grad_norm": 0.9594578742980957,
      "learning_rate": 9.938625865312251e-05,
      "loss": 1.6584,
      "step": 10
    },
    {
      "epoch": 0.02733343686907905,
      "grad_norm": 1.2051019668579102,
      "learning_rate": 9.911709846436641e-05,
      "loss": 1.7222,
      "step": 11
    },
    {
      "epoch": 0.029818294766268055,
      "grad_norm": 1.6941516399383545,
      "learning_rate": 9.879969687616027e-05,
      "loss": 1.9584,
      "step": 12
    },
    {
      "epoch": 0.03230315266345706,
      "grad_norm": 0.5741978883743286,
      "learning_rate": 9.84344009624807e-05,
      "loss": 1.0769,
      "step": 13
    },
    {
      "epoch": 0.034788010560646065,
      "grad_norm": 0.7483494281768799,
      "learning_rate": 9.80216101690461e-05,
      "loss": 1.1724,
      "step": 14
    },
    {
      "epoch": 0.03727286845783507,
      "grad_norm": 0.6988890767097473,
      "learning_rate": 9.756177587652856e-05,
      "loss": 1.1815,
      "step": 15
    },
    {
      "epoch": 0.03975772635502407,
      "grad_norm": 0.6390421986579895,
      "learning_rate": 9.705540090697575e-05,
      "loss": 1.2393,
      "step": 16
    },
    {
      "epoch": 0.042242584252213077,
      "grad_norm": 0.5592739582061768,
      "learning_rate": 9.650303897398232e-05,
      "loss": 1.237,
      "step": 17
    },
    {
      "epoch": 0.04472744214940208,
      "grad_norm": 0.4472772479057312,
      "learning_rate": 9.590529407721231e-05,
      "loss": 1.225,
      "step": 18
    },
    {
      "epoch": 0.047212300046591084,
      "grad_norm": 0.381583034992218,
      "learning_rate": 9.526281984193436e-05,
      "loss": 1.2886,
      "step": 19
    },
    {
      "epoch": 0.04969715794378009,
      "grad_norm": 0.896741509437561,
      "learning_rate": 9.4576318804292e-05,
      "loss": 1.3218,
      "step": 20
    },
    {
      "epoch": 0.05218201584096909,
      "grad_norm": 0.46586254239082336,
      "learning_rate": 9.384654164309083e-05,
      "loss": 1.5014,
      "step": 21
    },
    {
      "epoch": 0.0546668737381581,
      "grad_norm": 0.635338544845581,
      "learning_rate": 9.30742863589421e-05,
      "loss": 1.546,
      "step": 22
    },
    {
      "epoch": 0.057151731635347106,
      "grad_norm": 0.8390082716941833,
      "learning_rate": 9.226039740166091e-05,
      "loss": 1.5184,
      "step": 23
    },
    {
      "epoch": 0.05963658953253611,
      "grad_norm": 1.1133440732955933,
      "learning_rate": 9.140576474687264e-05,
      "loss": 1.878,
      "step": 24
    },
    {
      "epoch": 0.06212144742972511,
      "grad_norm": 2.014930009841919,
      "learning_rate": 9.051132292283771e-05,
      "loss": 2.3234,
      "step": 25
    },
    {
      "epoch": 0.06212144742972511,
      "eval_loss": 1.351180911064148,
      "eval_runtime": 1.1673,
      "eval_samples_per_second": 42.834,
      "eval_steps_per_second": 11.137,
      "step": 25
    },
    {
      "epoch": 0.06460630532691412,
      "grad_norm": 0.13552242517471313,
      "learning_rate": 8.957804998855866e-05,
      "loss": 1.03,
      "step": 26
    },
    {
      "epoch": 0.06709116322410312,
      "grad_norm": 0.14115220308303833,
      "learning_rate": 8.860696646428693e-05,
      "loss": 1.106,
      "step": 27
    },
    {
      "epoch": 0.06957602112129213,
      "grad_norm": 0.16067887842655182,
      "learning_rate": 8.759913421559902e-05,
      "loss": 1.1242,
      "step": 28
    },
    {
      "epoch": 0.07206087901848113,
      "grad_norm": 0.16710247099399567,
      "learning_rate": 8.655565529226198e-05,
      "loss": 1.1861,
      "step": 29
    },
    {
      "epoch": 0.07454573691567014,
      "grad_norm": 0.1886073648929596,
      "learning_rate": 8.547767072315835e-05,
      "loss": 1.1936,
      "step": 30
    },
    {
      "epoch": 0.07703059481285914,
      "grad_norm": 0.2157226949930191,
      "learning_rate": 8.436635926858759e-05,
      "loss": 1.2286,
      "step": 31
    },
    {
      "epoch": 0.07951545271004815,
      "grad_norm": 0.2546946406364441,
      "learning_rate": 8.322293613130917e-05,
      "loss": 1.2942,
      "step": 32
    },
    {
      "epoch": 0.08200031060723714,
      "grad_norm": 0.34159988164901733,
      "learning_rate": 8.204865162773613e-05,
      "loss": 1.3495,
      "step": 33
    },
    {
      "epoch": 0.08448516850442615,
      "grad_norm": 0.44573602080345154,
      "learning_rate": 8.084478982073247e-05,
      "loss": 1.4677,
      "step": 34
    },
    {
      "epoch": 0.08697002640161516,
      "grad_norm": 0.5484282970428467,
      "learning_rate": 7.961266711550922e-05,
      "loss": 1.4124,
      "step": 35
    },
    {
      "epoch": 0.08945488429880416,
      "grad_norm": 0.7390031218528748,
      "learning_rate": 7.835363082015468e-05,
      "loss": 1.6858,
      "step": 36
    },
    {
      "epoch": 0.09193974219599317,
      "grad_norm": 1.0373011827468872,
      "learning_rate": 7.706905767237288e-05,
      "loss": 1.7112,
      "step": 37
    },
    {
      "epoch": 0.09442460009318217,
      "grad_norm": 0.17684373259544373,
      "learning_rate": 7.576035233404096e-05,
      "loss": 1.0075,
      "step": 38
    },
    {
      "epoch": 0.09690945799037118,
      "grad_norm": 0.13694511353969574,
      "learning_rate": 7.442894585523218e-05,
      "loss": 1.1016,
      "step": 39
    },
    {
      "epoch": 0.09939431588756018,
      "grad_norm": 0.13813506066799164,
      "learning_rate": 7.307629410938363e-05,
      "loss": 1.0873,
      "step": 40
    },
    {
      "epoch": 0.10187917378474919,
      "grad_norm": 0.15622101724147797,
      "learning_rate": 7.170387620131993e-05,
      "loss": 1.1538,
      "step": 41
    },
    {
      "epoch": 0.10436403168193818,
      "grad_norm": 0.17008064687252045,
      "learning_rate": 7.031319284987394e-05,
      "loss": 1.2087,
      "step": 42
    },
    {
      "epoch": 0.1068488895791272,
      "grad_norm": 0.1911894828081131,
      "learning_rate": 6.890576474687263e-05,
      "loss": 1.2157,
      "step": 43
    },
    {
      "epoch": 0.1093337474763162,
      "grad_norm": 0.22054672241210938,
      "learning_rate": 6.7483130894283e-05,
      "loss": 1.263,
      "step": 44
    },
    {
      "epoch": 0.1118186053735052,
      "grad_norm": 0.2807726562023163,
      "learning_rate": 6.604684692133597e-05,
      "loss": 1.3281,
      "step": 45
    },
    {
      "epoch": 0.11430346327069421,
      "grad_norm": 0.3638734221458435,
      "learning_rate": 6.459848338346861e-05,
      "loss": 1.3941,
      "step": 46
    },
    {
      "epoch": 0.11678832116788321,
      "grad_norm": 0.5523617267608643,
      "learning_rate": 6.313962404494496e-05,
      "loss": 1.4622,
      "step": 47
    },
    {
      "epoch": 0.11927317906507222,
      "grad_norm": 0.6990809440612793,
      "learning_rate": 6.167186414703289e-05,
      "loss": 1.4193,
      "step": 48
    },
    {
      "epoch": 0.12175803696226122,
      "grad_norm": 1.1496556997299194,
      "learning_rate": 6.019680866363139e-05,
      "loss": 1.7219,
      "step": 49
    },
    {
      "epoch": 0.12424289485945023,
      "grad_norm": 2.33288836479187,
      "learning_rate": 5.8716070546254966e-05,
      "loss": 2.1245,
      "step": 50
    },
    {
      "epoch": 0.12424289485945023,
      "eval_loss": 1.3092597723007202,
      "eval_runtime": 1.1847,
      "eval_samples_per_second": 42.206,
      "eval_steps_per_second": 10.974,
      "step": 50
    },
    {
      "epoch": 0.12672775275663922,
      "grad_norm": 0.13320881128311157,
      "learning_rate": 5.7231268960295e-05,
      "loss": 1.0636,
      "step": 51
    },
    {
      "epoch": 0.12921261065382825,
      "grad_norm": 0.14497292041778564,
      "learning_rate": 5.574402751448614e-05,
      "loss": 1.135,
      "step": 52
    },
    {
      "epoch": 0.13169746855101724,
      "grad_norm": 0.16492624580860138,
      "learning_rate": 5.425597248551387e-05,
      "loss": 1.0798,
      "step": 53
    },
    {
      "epoch": 0.13418232644820624,
      "grad_norm": 0.18326567113399506,
      "learning_rate": 5.2768731039705e-05,
      "loss": 1.1425,
      "step": 54
    },
    {
      "epoch": 0.13666718434539524,
      "grad_norm": 0.2107713520526886,
      "learning_rate": 5.128392945374505e-05,
      "loss": 1.2191,
      "step": 55
    },
    {
      "epoch": 0.13915204224258426,
      "grad_norm": 0.2540586292743683,
      "learning_rate": 4.980319133636863e-05,
      "loss": 1.2378,
      "step": 56
    },
    {
      "epoch": 0.14163690013977326,
      "grad_norm": 0.2890605628490448,
      "learning_rate": 4.83281358529671e-05,
      "loss": 1.2228,
      "step": 57
    },
    {
      "epoch": 0.14412175803696226,
      "grad_norm": 0.3913767635822296,
      "learning_rate": 4.686037595505507e-05,
      "loss": 1.468,
      "step": 58
    },
    {
      "epoch": 0.14660661593415125,
      "grad_norm": 0.44723743200302124,
      "learning_rate": 4.54015166165314e-05,
      "loss": 1.3898,
      "step": 59
    },
    {
      "epoch": 0.14909147383134028,
      "grad_norm": 0.5722945332527161,
      "learning_rate": 4.395315307866405e-05,
      "loss": 1.4764,
      "step": 60
    },
    {
      "epoch": 0.15157633172852927,
      "grad_norm": 0.6735637784004211,
      "learning_rate": 4.2516869105717004e-05,
      "loss": 1.5408,
      "step": 61
    },
    {
      "epoch": 0.15406118962571827,
      "grad_norm": 0.9894400238990784,
      "learning_rate": 4.109423525312738e-05,
      "loss": 1.7832,
      "step": 62
    },
    {
      "epoch": 0.1565460475229073,
      "grad_norm": 0.14697420597076416,
      "learning_rate": 3.968680715012606e-05,
      "loss": 1.0738,
      "step": 63
    },
    {
      "epoch": 0.1590309054200963,
      "grad_norm": 0.12737371027469635,
      "learning_rate": 3.829612379868006e-05,
      "loss": 1.0667,
      "step": 64
    },
    {
      "epoch": 0.1615157633172853,
      "grad_norm": 0.14219443500041962,
      "learning_rate": 3.692370589061639e-05,
      "loss": 1.0997,
      "step": 65
    },
    {
      "epoch": 0.16400062121447428,
      "grad_norm": 0.15139789879322052,
      "learning_rate": 3.557105414476782e-05,
      "loss": 1.1539,
      "step": 66
    },
    {
      "epoch": 0.1664854791116633,
      "grad_norm": 0.15827913582324982,
      "learning_rate": 3.423964766595906e-05,
      "loss": 1.1753,
      "step": 67
    },
    {
      "epoch": 0.1689703370088523,
      "grad_norm": 0.19669124484062195,
      "learning_rate": 3.293094232762715e-05,
      "loss": 1.2182,
      "step": 68
    },
    {
      "epoch": 0.1714551949060413,
      "grad_norm": 0.2270824909210205,
      "learning_rate": 3.164636917984534e-05,
      "loss": 1.2668,
      "step": 69
    },
    {
      "epoch": 0.17394005280323033,
      "grad_norm": 0.2890926003456116,
      "learning_rate": 3.0387332884490805e-05,
      "loss": 1.3265,
      "step": 70
    },
    {
      "epoch": 0.17642491070041932,
      "grad_norm": 0.3860069811344147,
      "learning_rate": 2.9155210179267546e-05,
      "loss": 1.4004,
      "step": 71
    },
    {
      "epoch": 0.17890976859760832,
      "grad_norm": 0.4971885085105896,
      "learning_rate": 2.7951348372263875e-05,
      "loss": 1.4714,
      "step": 72
    },
    {
      "epoch": 0.18139462649479732,
      "grad_norm": 0.6487317681312561,
      "learning_rate": 2.677706386869083e-05,
      "loss": 1.5419,
      "step": 73
    },
    {
      "epoch": 0.18387948439198634,
      "grad_norm": 0.8211824893951416,
      "learning_rate": 2.5633640731412412e-05,
      "loss": 1.5489,
      "step": 74
    },
    {
      "epoch": 0.18636434228917534,
      "grad_norm": 1.7613846063613892,
      "learning_rate": 2.4522329276841663e-05,
      "loss": 2.1532,
      "step": 75
    },
    {
      "epoch": 0.18636434228917534,
      "eval_loss": 1.3022475242614746,
      "eval_runtime": 1.1687,
      "eval_samples_per_second": 42.783,
      "eval_steps_per_second": 11.124,
      "step": 75
    },
    {
      "epoch": 0.18884920018636434,
      "grad_norm": 0.11220304667949677,
      "learning_rate": 2.3444344707738015e-05,
      "loss": 1.047,
      "step": 76
    },
    {
      "epoch": 0.19133405808355336,
      "grad_norm": 0.1274535059928894,
      "learning_rate": 2.2400865784401e-05,
      "loss": 1.1196,
      "step": 77
    },
    {
      "epoch": 0.19381891598074236,
      "grad_norm": 0.13804402947425842,
      "learning_rate": 2.1393033535713093e-05,
      "loss": 1.1235,
      "step": 78
    },
    {
      "epoch": 0.19630377387793135,
      "grad_norm": 0.14971572160720825,
      "learning_rate": 2.0421950011441354e-05,
      "loss": 1.1777,
      "step": 79
    },
    {
      "epoch": 0.19878863177512035,
      "grad_norm": 0.18402217328548431,
      "learning_rate": 1.9488677077162295e-05,
      "loss": 1.179,
      "step": 80
    },
    {
      "epoch": 0.20127348967230937,
      "grad_norm": 0.21275171637535095,
      "learning_rate": 1.8594235253127375e-05,
      "loss": 1.2864,
      "step": 81
    },
    {
      "epoch": 0.20375834756949837,
      "grad_norm": 0.2665954530239105,
      "learning_rate": 1.77396025983391e-05,
      "loss": 1.2847,
      "step": 82
    },
    {
      "epoch": 0.20624320546668737,
      "grad_norm": 0.3545299768447876,
      "learning_rate": 1.6925713641057904e-05,
      "loss": 1.4364,
      "step": 83
    },
    {
      "epoch": 0.20872806336387636,
      "grad_norm": 0.44620993733406067,
      "learning_rate": 1.6153458356909176e-05,
      "loss": 1.4322,
      "step": 84
    },
    {
      "epoch": 0.2112129212610654,
      "grad_norm": 0.5365117788314819,
      "learning_rate": 1.5423681195707997e-05,
      "loss": 1.3801,
      "step": 85
    },
    {
      "epoch": 0.2136977791582544,
      "grad_norm": 0.6859667897224426,
      "learning_rate": 1.4737180158065644e-05,
      "loss": 1.5157,
      "step": 86
    },
    {
      "epoch": 0.21618263705544338,
      "grad_norm": 1.0796610116958618,
      "learning_rate": 1.4094705922787687e-05,
      "loss": 1.8931,
      "step": 87
    },
    {
      "epoch": 0.2186674949526324,
      "grad_norm": 0.15191839635372162,
      "learning_rate": 1.3496961026017687e-05,
      "loss": 1.0785,
      "step": 88
    },
    {
      "epoch": 0.2211523528498214,
      "grad_norm": 0.12437998503446579,
      "learning_rate": 1.2944599093024267e-05,
      "loss": 1.0752,
      "step": 89
    },
    {
      "epoch": 0.2236372107470104,
      "grad_norm": 0.12759096920490265,
      "learning_rate": 1.2438224123471442e-05,
      "loss": 1.0812,
      "step": 90
    },
    {
      "epoch": 0.2261220686441994,
      "grad_norm": 0.14436273276805878,
      "learning_rate": 1.1978389830953907e-05,
      "loss": 1.1591,
      "step": 91
    },
    {
      "epoch": 0.22860692654138842,
      "grad_norm": 0.1650199145078659,
      "learning_rate": 1.1565599037519316e-05,
      "loss": 1.1473,
      "step": 92
    },
    {
      "epoch": 0.23109178443857742,
      "grad_norm": 0.1937108039855957,
      "learning_rate": 1.1200303123839742e-05,
      "loss": 1.2184,
      "step": 93
    },
    {
      "epoch": 0.23357664233576642,
      "grad_norm": 0.2247273474931717,
      "learning_rate": 1.088290153563358e-05,
      "loss": 1.3174,
      "step": 94
    },
    {
      "epoch": 0.23606150023295544,
      "grad_norm": 0.2764604687690735,
      "learning_rate": 1.0613741346877497e-05,
      "loss": 1.3146,
      "step": 95
    },
    {
      "epoch": 0.23854635813014444,
      "grad_norm": 0.359423965215683,
      "learning_rate": 1.0393116880286118e-05,
      "loss": 1.4263,
      "step": 96
    },
    {
      "epoch": 0.24103121602733343,
      "grad_norm": 0.4706696569919586,
      "learning_rate": 1.0221269385474488e-05,
      "loss": 1.3916,
      "step": 97
    },
    {
      "epoch": 0.24351607392452243,
      "grad_norm": 0.598770797252655,
      "learning_rate": 1.0098386775155147e-05,
      "loss": 1.575,
      "step": 98
    },
    {
      "epoch": 0.24600093182171145,
      "grad_norm": 0.7586723566055298,
      "learning_rate": 1.0024603419658329e-05,
      "loss": 1.5519,
      "step": 99
    },
    {
      "epoch": 0.24848578971890045,
      "grad_norm": 1.7414568662643433,
      "learning_rate": 1e-05,
      "loss": 2.0062,
      "step": 100
    },
    {
      "epoch": 0.24848578971890045,
      "eval_loss": 1.296454668045044,
      "eval_runtime": 1.1762,
      "eval_samples_per_second": 42.511,
      "eval_steps_per_second": 11.053,
      "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
}