{
  "best_metric": 1.4269131422042847,
  "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": 2.300088882446289,
      "learning_rate": 2e-05,
      "loss": 1.3872,
      "step": 1
    },
    {
      "epoch": 0.0024848578971890046,
      "eval_loss": 2.3529415130615234,
      "eval_runtime": 0.5013,
      "eval_samples_per_second": 99.744,
      "eval_steps_per_second": 25.933,
      "step": 1
    },
    {
      "epoch": 0.004969715794378009,
      "grad_norm": 2.9502623081207275,
      "learning_rate": 4e-05,
      "loss": 1.4444,
      "step": 2
    },
    {
      "epoch": 0.007454573691567014,
      "grad_norm": 1.8946784734725952,
      "learning_rate": 6e-05,
      "loss": 1.5412,
      "step": 3
    },
    {
      "epoch": 0.009939431588756018,
      "grad_norm": 0.7780651450157166,
      "learning_rate": 8e-05,
      "loss": 1.565,
      "step": 4
    },
    {
      "epoch": 0.012424289485945022,
      "grad_norm": 0.865875780582428,
      "learning_rate": 0.0001,
      "loss": 1.6449,
      "step": 5
    },
    {
      "epoch": 0.014909147383134027,
      "grad_norm": 1.3217724561691284,
      "learning_rate": 9.997539658034168e-05,
      "loss": 1.82,
      "step": 6
    },
    {
      "epoch": 0.017394005280323033,
      "grad_norm": 1.3737115859985352,
      "learning_rate": 9.990161322484486e-05,
      "loss": 1.8865,
      "step": 7
    },
    {
      "epoch": 0.019878863177512036,
      "grad_norm": 1.384137749671936,
      "learning_rate": 9.977873061452552e-05,
      "loss": 2.0011,
      "step": 8
    },
    {
      "epoch": 0.02236372107470104,
      "grad_norm": 2.2917892932891846,
      "learning_rate": 9.96068831197139e-05,
      "loss": 2.386,
      "step": 9
    },
    {
      "epoch": 0.024848578971890044,
      "grad_norm": 2.604100227355957,
      "learning_rate": 9.938625865312251e-05,
      "loss": 2.4431,
      "step": 10
    },
    {
      "epoch": 0.02733343686907905,
      "grad_norm": 3.0263943672180176,
      "learning_rate": 9.911709846436641e-05,
      "loss": 2.4512,
      "step": 11
    },
    {
      "epoch": 0.029818294766268055,
      "grad_norm": 4.259069919586182,
      "learning_rate": 9.879969687616027e-05,
      "loss": 2.8096,
      "step": 12
    },
    {
      "epoch": 0.03230315266345706,
      "grad_norm": 0.6636050343513489,
      "learning_rate": 9.84344009624807e-05,
      "loss": 1.2143,
      "step": 13
    },
    {
      "epoch": 0.034788010560646065,
      "grad_norm": 0.5798764824867249,
      "learning_rate": 9.80216101690461e-05,
      "loss": 1.3011,
      "step": 14
    },
    {
      "epoch": 0.03727286845783507,
      "grad_norm": 0.4180930554866791,
      "learning_rate": 9.756177587652856e-05,
      "loss": 1.3003,
      "step": 15
    },
    {
      "epoch": 0.03975772635502407,
      "grad_norm": 0.4222364127635956,
      "learning_rate": 9.705540090697575e-05,
      "loss": 1.3608,
      "step": 16
    },
    {
      "epoch": 0.042242584252213077,
      "grad_norm": 0.35597240924835205,
      "learning_rate": 9.650303897398232e-05,
      "loss": 1.3774,
      "step": 17
    },
    {
      "epoch": 0.04472744214940208,
      "grad_norm": 0.44517314434051514,
      "learning_rate": 9.590529407721231e-05,
      "loss": 1.4007,
      "step": 18
    },
    {
      "epoch": 0.047212300046591084,
      "grad_norm": 0.48741888999938965,
      "learning_rate": 9.526281984193436e-05,
      "loss": 1.46,
      "step": 19
    },
    {
      "epoch": 0.04969715794378009,
      "grad_norm": 0.5775387287139893,
      "learning_rate": 9.4576318804292e-05,
      "loss": 1.5176,
      "step": 20
    },
    {
      "epoch": 0.05218201584096909,
      "grad_norm": 0.8612766861915588,
      "learning_rate": 9.384654164309083e-05,
      "loss": 1.7313,
      "step": 21
    },
    {
      "epoch": 0.0546668737381581,
      "grad_norm": 1.0877819061279297,
      "learning_rate": 9.30742863589421e-05,
      "loss": 1.8189,
      "step": 22
    },
    {
      "epoch": 0.057151731635347106,
      "grad_norm": 1.5835909843444824,
      "learning_rate": 9.226039740166091e-05,
      "loss": 1.8616,
      "step": 23
    },
    {
      "epoch": 0.05963658953253611,
      "grad_norm": 1.821236252784729,
      "learning_rate": 9.140576474687264e-05,
      "loss": 2.2753,
      "step": 24
    },
    {
      "epoch": 0.06212144742972511,
      "grad_norm": 3.0897128582000732,
      "learning_rate": 9.051132292283771e-05,
      "loss": 2.7458,
      "step": 25
    },
    {
      "epoch": 0.06212144742972511,
      "eval_loss": 1.5924893617630005,
      "eval_runtime": 0.5029,
      "eval_samples_per_second": 99.426,
      "eval_steps_per_second": 25.851,
      "step": 25
    },
    {
      "epoch": 0.06460630532691412,
      "grad_norm": 0.6046158671379089,
      "learning_rate": 8.957804998855866e-05,
      "loss": 1.1591,
      "step": 26
    },
    {
      "epoch": 0.06709116322410312,
      "grad_norm": 0.5957551002502441,
      "learning_rate": 8.860696646428693e-05,
      "loss": 1.245,
      "step": 27
    },
    {
      "epoch": 0.06957602112129213,
      "grad_norm": 0.5139787793159485,
      "learning_rate": 8.759913421559902e-05,
      "loss": 1.2712,
      "step": 28
    },
    {
      "epoch": 0.07206087901848113,
      "grad_norm": 0.5479816794395447,
      "learning_rate": 8.655565529226198e-05,
      "loss": 1.323,
      "step": 29
    },
    {
      "epoch": 0.07454573691567014,
      "grad_norm": 0.5366622805595398,
      "learning_rate": 8.547767072315835e-05,
      "loss": 1.3463,
      "step": 30
    },
    {
      "epoch": 0.07703059481285914,
      "grad_norm": 0.45999062061309814,
      "learning_rate": 8.436635926858759e-05,
      "loss": 1.3698,
      "step": 31
    },
    {
      "epoch": 0.07951545271004815,
      "grad_norm": 0.503322422504425,
      "learning_rate": 8.322293613130917e-05,
      "loss": 1.4421,
      "step": 32
    },
    {
      "epoch": 0.08200031060723714,
      "grad_norm": 0.5098061561584473,
      "learning_rate": 8.204865162773613e-05,
      "loss": 1.4987,
      "step": 33
    },
    {
      "epoch": 0.08448516850442615,
      "grad_norm": 0.8290462493896484,
      "learning_rate": 8.084478982073247e-05,
      "loss": 1.6499,
      "step": 34
    },
    {
      "epoch": 0.08697002640161516,
      "grad_norm": 1.1299933195114136,
      "learning_rate": 7.961266711550922e-05,
      "loss": 1.6645,
      "step": 35
    },
    {
      "epoch": 0.08945488429880416,
      "grad_norm": 1.509699821472168,
      "learning_rate": 7.835363082015468e-05,
      "loss": 1.9601,
      "step": 36
    },
    {
      "epoch": 0.09193974219599317,
      "grad_norm": 2.031057357788086,
      "learning_rate": 7.706905767237288e-05,
      "loss": 2.0144,
      "step": 37
    },
    {
      "epoch": 0.09442460009318217,
      "grad_norm": 0.2664984166622162,
      "learning_rate": 7.576035233404096e-05,
      "loss": 1.1166,
      "step": 38
    },
    {
      "epoch": 0.09690945799037118,
      "grad_norm": 0.3003743886947632,
      "learning_rate": 7.442894585523218e-05,
      "loss": 1.2056,
      "step": 39
    },
    {
      "epoch": 0.09939431588756018,
      "grad_norm": 0.2394295483827591,
      "learning_rate": 7.307629410938363e-05,
      "loss": 1.2017,
      "step": 40
    },
    {
      "epoch": 0.10187917378474919,
      "grad_norm": 0.2574416697025299,
      "learning_rate": 7.170387620131993e-05,
      "loss": 1.2667,
      "step": 41
    },
    {
      "epoch": 0.10436403168193818,
      "grad_norm": 0.27160924673080444,
      "learning_rate": 7.031319284987394e-05,
      "loss": 1.3229,
      "step": 42
    },
    {
      "epoch": 0.1068488895791272,
      "grad_norm": 0.2959175705909729,
      "learning_rate": 6.890576474687263e-05,
      "loss": 1.317,
      "step": 43
    },
    {
      "epoch": 0.1093337474763162,
      "grad_norm": 0.37090274691581726,
      "learning_rate": 6.7483130894283e-05,
      "loss": 1.3696,
      "step": 44
    },
    {
      "epoch": 0.1118186053735052,
      "grad_norm": 0.3861182928085327,
      "learning_rate": 6.604684692133597e-05,
      "loss": 1.4644,
      "step": 45
    },
    {
      "epoch": 0.11430346327069421,
      "grad_norm": 0.5286714434623718,
      "learning_rate": 6.459848338346861e-05,
      "loss": 1.5335,
      "step": 46
    },
    {
      "epoch": 0.11678832116788321,
      "grad_norm": 0.7814580798149109,
      "learning_rate": 6.313962404494496e-05,
      "loss": 1.6303,
      "step": 47
    },
    {
      "epoch": 0.11927317906507222,
      "grad_norm": 0.9398607611656189,
      "learning_rate": 6.167186414703289e-05,
      "loss": 1.618,
      "step": 48
    },
    {
      "epoch": 0.12175803696226122,
      "grad_norm": 1.396071195602417,
      "learning_rate": 6.019680866363139e-05,
      "loss": 1.9406,
      "step": 49
    },
    {
      "epoch": 0.12424289485945023,
      "grad_norm": 2.228092670440674,
      "learning_rate": 5.8716070546254966e-05,
      "loss": 2.4273,
      "step": 50
    },
    {
      "epoch": 0.12424289485945023,
      "eval_loss": 1.4828438758850098,
      "eval_runtime": 0.5009,
      "eval_samples_per_second": 99.821,
      "eval_steps_per_second": 25.953,
      "step": 50
    },
    {
      "epoch": 0.12672775275663922,
      "grad_norm": 0.502906322479248,
      "learning_rate": 5.7231268960295e-05,
      "loss": 1.1817,
      "step": 51
    },
    {
      "epoch": 0.12921261065382825,
      "grad_norm": 0.24773943424224854,
      "learning_rate": 5.574402751448614e-05,
      "loss": 1.2391,
      "step": 52
    },
    {
      "epoch": 0.13169746855101724,
      "grad_norm": 0.2371302992105484,
      "learning_rate": 5.425597248551387e-05,
      "loss": 1.1822,
      "step": 53
    },
    {
      "epoch": 0.13418232644820624,
      "grad_norm": 0.25085148215293884,
      "learning_rate": 5.2768731039705e-05,
      "loss": 1.2478,
      "step": 54
    },
    {
      "epoch": 0.13666718434539524,
      "grad_norm": 0.2836790084838867,
      "learning_rate": 5.128392945374505e-05,
      "loss": 1.3121,
      "step": 55
    },
    {
      "epoch": 0.13915204224258426,
      "grad_norm": 0.33297136425971985,
      "learning_rate": 4.980319133636863e-05,
      "loss": 1.3318,
      "step": 56
    },
    {
      "epoch": 0.14163690013977326,
      "grad_norm": 0.34877943992614746,
      "learning_rate": 4.83281358529671e-05,
      "loss": 1.3158,
      "step": 57
    },
    {
      "epoch": 0.14412175803696226,
      "grad_norm": 0.4253171980381012,
      "learning_rate": 4.686037595505507e-05,
      "loss": 1.5633,
      "step": 58
    },
    {
      "epoch": 0.14660661593415125,
      "grad_norm": 0.6319759488105774,
      "learning_rate": 4.54015166165314e-05,
      "loss": 1.5243,
      "step": 59
    },
    {
      "epoch": 0.14909147383134028,
      "grad_norm": 0.8073891997337341,
      "learning_rate": 4.395315307866405e-05,
      "loss": 1.5936,
      "step": 60
    },
    {
      "epoch": 0.15157633172852927,
      "grad_norm": 0.9894248247146606,
      "learning_rate": 4.2516869105717004e-05,
      "loss": 1.7098,
      "step": 61
    },
    {
      "epoch": 0.15406118962571827,
      "grad_norm": 1.6078970432281494,
      "learning_rate": 4.109423525312738e-05,
      "loss": 1.9748,
      "step": 62
    },
    {
      "epoch": 0.1565460475229073,
      "grad_norm": 0.22679314017295837,
      "learning_rate": 3.968680715012606e-05,
      "loss": 1.1667,
      "step": 63
    },
    {
      "epoch": 0.1590309054200963,
      "grad_norm": 0.2222493439912796,
      "learning_rate": 3.829612379868006e-05,
      "loss": 1.1709,
      "step": 64
    },
    {
      "epoch": 0.1615157633172853,
      "grad_norm": 0.21688520908355713,
      "learning_rate": 3.692370589061639e-05,
      "loss": 1.1943,
      "step": 65
    },
    {
      "epoch": 0.16400062121447428,
      "grad_norm": 0.20430833101272583,
      "learning_rate": 3.557105414476782e-05,
      "loss": 1.2414,
      "step": 66
    },
    {
      "epoch": 0.1664854791116633,
      "grad_norm": 0.2140100747346878,
      "learning_rate": 3.423964766595906e-05,
      "loss": 1.2744,
      "step": 67
    },
    {
      "epoch": 0.1689703370088523,
      "grad_norm": 0.2611446678638458,
      "learning_rate": 3.293094232762715e-05,
      "loss": 1.3186,
      "step": 68
    },
    {
      "epoch": 0.1714551949060413,
      "grad_norm": 0.3044528663158417,
      "learning_rate": 3.164636917984534e-05,
      "loss": 1.3571,
      "step": 69
    },
    {
      "epoch": 0.17394005280323033,
      "grad_norm": 0.38728901743888855,
      "learning_rate": 3.0387332884490805e-05,
      "loss": 1.4208,
      "step": 70
    },
    {
      "epoch": 0.17642491070041932,
      "grad_norm": 0.4820074737071991,
      "learning_rate": 2.9155210179267546e-05,
      "loss": 1.4856,
      "step": 71
    },
    {
      "epoch": 0.17890976859760832,
      "grad_norm": 0.7685176730155945,
      "learning_rate": 2.7951348372263875e-05,
      "loss": 1.6077,
      "step": 72
    },
    {
      "epoch": 0.18139462649479732,
      "grad_norm": 0.9084189534187317,
      "learning_rate": 2.677706386869083e-05,
      "loss": 1.7115,
      "step": 73
    },
    {
      "epoch": 0.18387948439198634,
      "grad_norm": 1.1682430505752563,
      "learning_rate": 2.5633640731412412e-05,
      "loss": 1.7022,
      "step": 74
    },
    {
      "epoch": 0.18636434228917534,
      "grad_norm": 2.3014986515045166,
      "learning_rate": 2.4522329276841663e-05,
      "loss": 2.2833,
      "step": 75
    },
    {
      "epoch": 0.18636434228917534,
      "eval_loss": 1.4402331113815308,
      "eval_runtime": 0.5011,
      "eval_samples_per_second": 99.773,
      "eval_steps_per_second": 25.941,
      "step": 75
    },
    {
      "epoch": 0.18884920018636434,
      "grad_norm": 0.1660635769367218,
      "learning_rate": 2.3444344707738015e-05,
      "loss": 1.142,
      "step": 76
    },
    {
      "epoch": 0.19133405808355336,
      "grad_norm": 0.18352839350700378,
      "learning_rate": 2.2400865784401e-05,
      "loss": 1.2142,
      "step": 77
    },
    {
      "epoch": 0.19381891598074236,
      "grad_norm": 0.20116844773292542,
      "learning_rate": 2.1393033535713093e-05,
      "loss": 1.2073,
      "step": 78
    },
    {
      "epoch": 0.19630377387793135,
      "grad_norm": 0.21657872200012207,
      "learning_rate": 2.0421950011441354e-05,
      "loss": 1.2575,
      "step": 79
    },
    {
      "epoch": 0.19878863177512035,
      "grad_norm": 0.2673671841621399,
      "learning_rate": 1.9488677077162295e-05,
      "loss": 1.2537,
      "step": 80
    },
    {
      "epoch": 0.20127348967230937,
      "grad_norm": 0.2948070168495178,
      "learning_rate": 1.8594235253127375e-05,
      "loss": 1.3705,
      "step": 81
    },
    {
      "epoch": 0.20375834756949837,
      "grad_norm": 0.39712944626808167,
      "learning_rate": 1.77396025983391e-05,
      "loss": 1.3718,
      "step": 82
    },
    {
      "epoch": 0.20624320546668737,
      "grad_norm": 0.534000813961029,
      "learning_rate": 1.6925713641057904e-05,
      "loss": 1.541,
      "step": 83
    },
    {
      "epoch": 0.20872806336387636,
      "grad_norm": 0.6204800009727478,
      "learning_rate": 1.6153458356909176e-05,
      "loss": 1.5432,
      "step": 84
    },
    {
      "epoch": 0.2112129212610654,
      "grad_norm": 0.7464126944541931,
      "learning_rate": 1.5423681195707997e-05,
      "loss": 1.5205,
      "step": 85
    },
    {
      "epoch": 0.2136977791582544,
      "grad_norm": 0.9733933806419373,
      "learning_rate": 1.4737180158065644e-05,
      "loss": 1.6361,
      "step": 86
    },
    {
      "epoch": 0.21618263705544338,
      "grad_norm": 1.6869643926620483,
      "learning_rate": 1.4094705922787687e-05,
      "loss": 2.0192,
      "step": 87
    },
    {
      "epoch": 0.2186674949526324,
      "grad_norm": 0.19440440833568573,
      "learning_rate": 1.3496961026017687e-05,
      "loss": 1.1668,
      "step": 88
    },
    {
      "epoch": 0.2211523528498214,
      "grad_norm": 0.15947960317134857,
      "learning_rate": 1.2944599093024267e-05,
      "loss": 1.1674,
      "step": 89
    },
    {
      "epoch": 0.2236372107470104,
      "grad_norm": 0.16794700920581818,
      "learning_rate": 1.2438224123471442e-05,
      "loss": 1.1625,
      "step": 90
    },
    {
      "epoch": 0.2261220686441994,
      "grad_norm": 0.1928674876689911,
      "learning_rate": 1.1978389830953907e-05,
      "loss": 1.2395,
      "step": 91
    },
    {
      "epoch": 0.22860692654138842,
      "grad_norm": 0.20329076051712036,
      "learning_rate": 1.1565599037519316e-05,
      "loss": 1.2341,
      "step": 92
    },
    {
      "epoch": 0.23109178443857742,
      "grad_norm": 0.24812369048595428,
      "learning_rate": 1.1200303123839742e-05,
      "loss": 1.2939,
      "step": 93
    },
    {
      "epoch": 0.23357664233576642,
      "grad_norm": 0.31037917733192444,
      "learning_rate": 1.088290153563358e-05,
      "loss": 1.3984,
      "step": 94
    },
    {
      "epoch": 0.23606150023295544,
      "grad_norm": 0.36285361647605896,
      "learning_rate": 1.0613741346877497e-05,
      "loss": 1.4013,
      "step": 95
    },
    {
      "epoch": 0.23854635813014444,
      "grad_norm": 0.47147876024246216,
      "learning_rate": 1.0393116880286118e-05,
      "loss": 1.5091,
      "step": 96
    },
    {
      "epoch": 0.24103121602733343,
      "grad_norm": 0.6406936645507812,
      "learning_rate": 1.0221269385474488e-05,
      "loss": 1.508,
      "step": 97
    },
    {
      "epoch": 0.24351607392452243,
      "grad_norm": 0.8809720277786255,
      "learning_rate": 1.0098386775155147e-05,
      "loss": 1.7012,
      "step": 98
    },
    {
      "epoch": 0.24600093182171145,
      "grad_norm": 1.0965121984481812,
      "learning_rate": 1.0024603419658329e-05,
      "loss": 1.6873,
      "step": 99
    },
    {
      "epoch": 0.24848578971890045,
      "grad_norm": 2.3786566257476807,
      "learning_rate": 1e-05,
      "loss": 2.1749,
      "step": 100
    },
    {
      "epoch": 0.24848578971890045,
      "eval_loss": 1.4269131422042847,
      "eval_runtime": 0.5018,
      "eval_samples_per_second": 99.643,
      "eval_steps_per_second": 25.907,
      "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
}