{
  "best_metric": 0.7010467052459717,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.3840830449826989,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01384083044982699,
      "grad_norm": 40.9892692565918,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 30.7293,
      "step": 1
    },
    {
      "epoch": 0.01384083044982699,
      "eval_loss": 7.911479949951172,
      "eval_runtime": 5.1322,
      "eval_samples_per_second": 9.742,
      "eval_steps_per_second": 1.364,
      "step": 1
    },
    {
      "epoch": 0.02768166089965398,
      "grad_norm": 44.54869079589844,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 31.553,
      "step": 2
    },
    {
      "epoch": 0.04152249134948097,
      "grad_norm": 46.91074752807617,
      "learning_rate": 8.999999999999999e-05,
      "loss": 30.4963,
      "step": 3
    },
    {
      "epoch": 0.05536332179930796,
      "grad_norm": 49.72462844848633,
      "learning_rate": 0.00011999999999999999,
      "loss": 28.3763,
      "step": 4
    },
    {
      "epoch": 0.06920415224913495,
      "grad_norm": 50.18564224243164,
      "learning_rate": 0.00015,
      "loss": 22.6685,
      "step": 5
    },
    {
      "epoch": 0.08304498269896193,
      "grad_norm": 44.5780143737793,
      "learning_rate": 0.00017999999999999998,
      "loss": 14.5096,
      "step": 6
    },
    {
      "epoch": 0.09688581314878893,
      "grad_norm": 30.434995651245117,
      "learning_rate": 0.00020999999999999998,
      "loss": 7.348,
      "step": 7
    },
    {
      "epoch": 0.11072664359861592,
      "grad_norm": 15.010186195373535,
      "learning_rate": 0.00023999999999999998,
      "loss": 4.1836,
      "step": 8
    },
    {
      "epoch": 0.1245674740484429,
      "grad_norm": 8.79946231842041,
      "learning_rate": 0.00027,
      "loss": 3.2994,
      "step": 9
    },
    {
      "epoch": 0.1384083044982699,
      "grad_norm": 3.8603556156158447,
      "learning_rate": 0.0003,
      "loss": 2.8264,
      "step": 10
    },
    {
      "epoch": 0.1522491349480969,
      "grad_norm": 10.656445503234863,
      "learning_rate": 0.0002999593861769192,
      "loss": 3.1222,
      "step": 11
    },
    {
      "epoch": 0.16608996539792387,
      "grad_norm": 5.157639980316162,
      "learning_rate": 0.00029983756670077865,
      "loss": 2.9336,
      "step": 12
    },
    {
      "epoch": 0.17993079584775087,
      "grad_norm": 3.850473165512085,
      "learning_rate": 0.0002996346075389736,
      "loss": 2.8686,
      "step": 13
    },
    {
      "epoch": 0.19377162629757785,
      "grad_norm": 8.165860176086426,
      "learning_rate": 0.00029935061859747065,
      "loss": 2.9763,
      "step": 14
    },
    {
      "epoch": 0.20761245674740483,
      "grad_norm": 6.534956455230713,
      "learning_rate": 0.00029898575366129145,
      "loss": 3.1093,
      "step": 15
    },
    {
      "epoch": 0.22145328719723184,
      "grad_norm": 5.248986721038818,
      "learning_rate": 0.0002985402103112355,
      "loss": 2.896,
      "step": 16
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 3.770387887954712,
      "learning_rate": 0.00029801422981688686,
      "loss": 2.7932,
      "step": 17
    },
    {
      "epoch": 0.2491349480968858,
      "grad_norm": 9.586681365966797,
      "learning_rate": 0.000297408097005962,
      "loss": 2.9843,
      "step": 18
    },
    {
      "epoch": 0.2629757785467128,
      "grad_norm": 5.363808631896973,
      "learning_rate": 0.0002967221401100708,
      "loss": 2.9857,
      "step": 19
    },
    {
      "epoch": 0.2768166089965398,
      "grad_norm": 3.2338597774505615,
      "learning_rate": 0.00029595673058697357,
      "loss": 2.8622,
      "step": 20
    },
    {
      "epoch": 0.2906574394463668,
      "grad_norm": 3.012906312942505,
      "learning_rate": 0.0002951122829194295,
      "loss": 2.6277,
      "step": 21
    },
    {
      "epoch": 0.3044982698961938,
      "grad_norm": 6.697887420654297,
      "learning_rate": 0.0002941892543907478,
      "loss": 3.0416,
      "step": 22
    },
    {
      "epoch": 0.31833910034602075,
      "grad_norm": 2.6583356857299805,
      "learning_rate": 0.0002931881448371598,
      "loss": 2.6767,
      "step": 23
    },
    {
      "epoch": 0.33217993079584773,
      "grad_norm": 1.7108440399169922,
      "learning_rate": 0.0002921094963771494,
      "loss": 2.7423,
      "step": 24
    },
    {
      "epoch": 0.3460207612456747,
      "grad_norm": 2.377303123474121,
      "learning_rate": 0.0002909538931178862,
      "loss": 2.811,
      "step": 25
    },
    {
      "epoch": 0.3460207612456747,
      "eval_loss": 0.6890237331390381,
      "eval_runtime": 5.2521,
      "eval_samples_per_second": 9.52,
      "eval_steps_per_second": 1.333,
      "step": 25
    },
    {
      "epoch": 0.35986159169550175,
      "grad_norm": 2.390648603439331,
      "learning_rate": 0.00028972196083892134,
      "loss": 2.7977,
      "step": 26
    },
    {
      "epoch": 0.3737024221453287,
      "grad_norm": 2.9108152389526367,
      "learning_rate": 0.00028841436665331634,
      "loss": 2.9092,
      "step": 27
    },
    {
      "epoch": 0.3875432525951557,
      "grad_norm": 2.952723979949951,
      "learning_rate": 0.0002870318186463901,
      "loss": 2.7992,
      "step": 28
    },
    {
      "epoch": 0.4013840830449827,
      "grad_norm": 2.9674861431121826,
      "learning_rate": 0.00028557506549227804,
      "loss": 2.8412,
      "step": 29
    },
    {
      "epoch": 0.41522491349480967,
      "grad_norm": 1.8786237239837646,
      "learning_rate": 0.0002840448960485118,
      "loss": 2.7702,
      "step": 30
    },
    {
      "epoch": 0.4290657439446367,
      "grad_norm": 3.3518176078796387,
      "learning_rate": 0.000282442138928839,
      "loss": 2.8484,
      "step": 31
    },
    {
      "epoch": 0.4429065743944637,
      "grad_norm": 1.953736662864685,
      "learning_rate": 0.0002807676620545143,
      "loss": 2.5684,
      "step": 32
    },
    {
      "epoch": 0.45674740484429066,
      "grad_norm": 8.230539321899414,
      "learning_rate": 0.00027902237218430483,
      "loss": 3.2569,
      "step": 33
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 7.019381046295166,
      "learning_rate": 0.00027720721442346387,
      "loss": 3.1625,
      "step": 34
    },
    {
      "epoch": 0.4844290657439446,
      "grad_norm": 5.099842071533203,
      "learning_rate": 0.00027532317171194046,
      "loss": 3.0486,
      "step": 35
    },
    {
      "epoch": 0.4982698961937716,
      "grad_norm": 2.0828545093536377,
      "learning_rate": 0.00027337126429209934,
      "loss": 2.832,
      "step": 36
    },
    {
      "epoch": 0.5121107266435986,
      "grad_norm": 1.9583015441894531,
      "learning_rate": 0.0002713525491562421,
      "loss": 2.8298,
      "step": 37
    },
    {
      "epoch": 0.5259515570934256,
      "grad_norm": 2.480612277984619,
      "learning_rate": 0.00026926811947422714,
      "loss": 2.7638,
      "step": 38
    },
    {
      "epoch": 0.5397923875432526,
      "grad_norm": 2.304385185241699,
      "learning_rate": 0.0002671191040014989,
      "loss": 2.7757,
      "step": 39
    },
    {
      "epoch": 0.5536332179930796,
      "grad_norm": 3.724012851715088,
      "learning_rate": 0.00026490666646784665,
      "loss": 2.8564,
      "step": 40
    },
    {
      "epoch": 0.5674740484429066,
      "grad_norm": 6.570769309997559,
      "learning_rate": 0.00026263200494722487,
      "loss": 3.0332,
      "step": 41
    },
    {
      "epoch": 0.5813148788927336,
      "grad_norm": 3.7891201972961426,
      "learning_rate": 0.0002602963512089743,
      "loss": 2.8577,
      "step": 42
    },
    {
      "epoch": 0.5951557093425606,
      "grad_norm": 3.1248676776885986,
      "learning_rate": 0.00025790097005079764,
      "loss": 2.8053,
      "step": 43
    },
    {
      "epoch": 0.6089965397923875,
      "grad_norm": 2.767016649246216,
      "learning_rate": 0.0002554471586138493,
      "loss": 2.7561,
      "step": 44
    },
    {
      "epoch": 0.6228373702422145,
      "grad_norm": 3.91235089302063,
      "learning_rate": 0.00025293624568031,
      "loss": 2.9683,
      "step": 45
    },
    {
      "epoch": 0.6366782006920415,
      "grad_norm": 3.9107556343078613,
      "learning_rate": 0.0002503695909538287,
      "loss": 2.9184,
      "step": 46
    },
    {
      "epoch": 0.6505190311418685,
      "grad_norm": 3.6938490867614746,
      "learning_rate": 0.0002477485843232183,
      "loss": 2.7981,
      "step": 47
    },
    {
      "epoch": 0.6643598615916955,
      "grad_norm": 1.329195499420166,
      "learning_rate": 0.0002450746451098065,
      "loss": 2.7712,
      "step": 48
    },
    {
      "epoch": 0.6782006920415224,
      "grad_norm": 1.1611841917037964,
      "learning_rate": 0.0002423492212988487,
      "loss": 2.778,
      "step": 49
    },
    {
      "epoch": 0.6920415224913494,
      "grad_norm": 2.376075506210327,
      "learning_rate": 0.00023957378875541792,
      "loss": 2.6997,
      "step": 50
    },
    {
      "epoch": 0.6920415224913494,
      "eval_loss": 0.7010467052459717,
      "eval_runtime": 5.2581,
      "eval_samples_per_second": 9.509,
      "eval_steps_per_second": 1.331,
      "step": 50
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 9.266826629638672,
      "learning_rate": 0.00023674985042519795,
      "loss": 3.4074,
      "step": 51
    },
    {
      "epoch": 0.7197231833910035,
      "grad_norm": 2.7682924270629883,
      "learning_rate": 0.00023387893552061199,
      "loss": 2.6934,
      "step": 52
    },
    {
      "epoch": 0.7335640138408305,
      "grad_norm": 1.135008454322815,
      "learning_rate": 0.00023096259869272693,
      "loss": 2.7218,
      "step": 53
    },
    {
      "epoch": 0.7474048442906575,
      "grad_norm": 3.1696879863739014,
      "learning_rate": 0.00022800241918938228,
      "loss": 2.8763,
      "step": 54
    },
    {
      "epoch": 0.7612456747404844,
      "grad_norm": 3.2597336769104004,
      "learning_rate": 0.000225,
      "loss": 2.794,
      "step": 55
    },
    {
      "epoch": 0.7750865051903114,
      "grad_norm": 2.9772768020629883,
      "learning_rate": 0.00022195696698753693,
      "loss": 2.9002,
      "step": 56
    },
    {
      "epoch": 0.7889273356401384,
      "grad_norm": 2.6768057346343994,
      "learning_rate": 0.00021887496800805173,
      "loss": 2.8117,
      "step": 57
    },
    {
      "epoch": 0.8027681660899654,
      "grad_norm": 1.5049817562103271,
      "learning_rate": 0.0002157556720183616,
      "loss": 2.8173,
      "step": 58
    },
    {
      "epoch": 0.8166089965397924,
      "grad_norm": 1.5916688442230225,
      "learning_rate": 0.00021260076817227266,
      "loss": 2.7637,
      "step": 59
    },
    {
      "epoch": 0.8304498269896193,
      "grad_norm": 2.124816656112671,
      "learning_rate": 0.0002094119649058735,
      "loss": 2.7946,
      "step": 60
    },
    {
      "epoch": 0.8442906574394463,
      "grad_norm": 1.6769332885742188,
      "learning_rate": 0.0002061909890123868,
      "loss": 2.7702,
      "step": 61
    },
    {
      "epoch": 0.8581314878892734,
      "grad_norm": 3.2984721660614014,
      "learning_rate": 0.0002029395847070803,
      "loss": 2.7117,
      "step": 62
    },
    {
      "epoch": 0.8719723183391004,
      "grad_norm": 1.5877281427383423,
      "learning_rate": 0.0001996595126827437,
      "loss": 2.705,
      "step": 63
    },
    {
      "epoch": 0.8858131487889274,
      "grad_norm": 3.0824265480041504,
      "learning_rate": 0.0001963525491562421,
      "loss": 2.8567,
      "step": 64
    },
    {
      "epoch": 0.8996539792387543,
      "grad_norm": 3.194683313369751,
      "learning_rate": 0.00019302048490666353,
      "loss": 2.8681,
      "step": 65
    },
    {
      "epoch": 0.9134948096885813,
      "grad_norm": 2.6802637577056885,
      "learning_rate": 0.00018966512430558034,
      "loss": 2.8496,
      "step": 66
    },
    {
      "epoch": 0.9273356401384083,
      "grad_norm": 3.094783067703247,
      "learning_rate": 0.00018628828433995013,
      "loss": 2.8264,
      "step": 67
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 1.2324931621551514,
      "learning_rate": 0.00018289179362818546,
      "loss": 2.7473,
      "step": 68
    },
    {
      "epoch": 0.9550173010380623,
      "grad_norm": 2.415250778198242,
      "learning_rate": 0.0001794774914299245,
      "loss": 2.835,
      "step": 69
    },
    {
      "epoch": 0.9688581314878892,
      "grad_norm": 2.9529473781585693,
      "learning_rate": 0.00017604722665003956,
      "loss": 2.958,
      "step": 70
    },
    {
      "epoch": 0.9826989619377162,
      "grad_norm": 1.7587758302688599,
      "learning_rate": 0.00017260285683742246,
      "loss": 2.8396,
      "step": 71
    },
    {
      "epoch": 0.9965397923875432,
      "grad_norm": 1.809816598892212,
      "learning_rate": 0.00016914624717908922,
      "loss": 2.8112,
      "step": 72
    },
    {
      "epoch": 1.0103806228373702,
      "grad_norm": 1.430889368057251,
      "learning_rate": 0.000165679269490148,
      "loss": 2.7052,
      "step": 73
    },
    {
      "epoch": 1.0242214532871972,
      "grad_norm": 2.520479440689087,
      "learning_rate": 0.00016220380120017872,
      "loss": 2.7617,
      "step": 74
    },
    {
      "epoch": 1.0380622837370241,
      "grad_norm": 1.8224382400512695,
      "learning_rate": 0.00015872172433657134,
      "loss": 2.7747,
      "step": 75
    },
    {
      "epoch": 1.0380622837370241,
      "eval_loss": 0.6992730498313904,
      "eval_runtime": 5.2527,
      "eval_samples_per_second": 9.519,
      "eval_steps_per_second": 1.333,
      "step": 75
    },
    {
      "epoch": 1.0519031141868511,
      "grad_norm": 1.3448646068572998,
      "learning_rate": 0.00015523492450537517,
      "loss": 2.763,
      "step": 76
    },
    {
      "epoch": 1.065743944636678,
      "grad_norm": 1.085045576095581,
      "learning_rate": 0.00015174528987020957,
      "loss": 2.7388,
      "step": 77
    },
    {
      "epoch": 1.0795847750865053,
      "grad_norm": 1.328552007675171,
      "learning_rate": 0.00014825471012979045,
      "loss": 2.7668,
      "step": 78
    },
    {
      "epoch": 1.0934256055363323,
      "grad_norm": 1.4537187814712524,
      "learning_rate": 0.0001447650754946249,
      "loss": 2.7073,
      "step": 79
    },
    {
      "epoch": 1.1072664359861593,
      "grad_norm": 1.3335843086242676,
      "learning_rate": 0.00014127827566342863,
      "loss": 2.796,
      "step": 80
    },
    {
      "epoch": 1.1211072664359862,
      "grad_norm": 2.351191997528076,
      "learning_rate": 0.00013779619879982126,
      "loss": 2.8494,
      "step": 81
    },
    {
      "epoch": 1.1349480968858132,
      "grad_norm": 2.260059118270874,
      "learning_rate": 0.000134320730509852,
      "loss": 2.7993,
      "step": 82
    },
    {
      "epoch": 1.1487889273356402,
      "grad_norm": 2.7046008110046387,
      "learning_rate": 0.00013085375282091078,
      "loss": 2.837,
      "step": 83
    },
    {
      "epoch": 1.1626297577854672,
      "grad_norm": 1.4147647619247437,
      "learning_rate": 0.0001273971431625775,
      "loss": 2.7192,
      "step": 84
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 2.916611909866333,
      "learning_rate": 0.00012395277334996044,
      "loss": 2.8989,
      "step": 85
    },
    {
      "epoch": 1.1903114186851211,
      "grad_norm": 3.9687960147857666,
      "learning_rate": 0.00012052250857007545,
      "loss": 2.728,
      "step": 86
    },
    {
      "epoch": 1.2041522491349481,
      "grad_norm": 1.5941438674926758,
      "learning_rate": 0.00011710820637181447,
      "loss": 2.7109,
      "step": 87
    },
    {
      "epoch": 1.217993079584775,
      "grad_norm": 1.5909277200698853,
      "learning_rate": 0.00011371171566004985,
      "loss": 2.78,
      "step": 88
    },
    {
      "epoch": 1.231833910034602,
      "grad_norm": 3.141655206680298,
      "learning_rate": 0.0001103348756944197,
      "loss": 2.7588,
      "step": 89
    },
    {
      "epoch": 1.245674740484429,
      "grad_norm": 2.018080234527588,
      "learning_rate": 0.0001069795150933365,
      "loss": 2.7771,
      "step": 90
    },
    {
      "epoch": 1.259515570934256,
      "grad_norm": 1.5090923309326172,
      "learning_rate": 0.0001036474508437579,
      "loss": 2.7333,
      "step": 91
    },
    {
      "epoch": 1.273356401384083,
      "grad_norm": 1.451968789100647,
      "learning_rate": 0.0001003404873172563,
      "loss": 2.7345,
      "step": 92
    },
    {
      "epoch": 1.28719723183391,
      "grad_norm": 2.1932549476623535,
      "learning_rate": 9.706041529291968e-05,
      "loss": 2.7071,
      "step": 93
    },
    {
      "epoch": 1.301038062283737,
      "grad_norm": 2.9638872146606445,
      "learning_rate": 9.380901098761319e-05,
      "loss": 2.8978,
      "step": 94
    },
    {
      "epoch": 1.314878892733564,
      "grad_norm": 2.9430599212646484,
      "learning_rate": 9.058803509412646e-05,
      "loss": 2.8598,
      "step": 95
    },
    {
      "epoch": 1.328719723183391,
      "grad_norm": 2.1553397178649902,
      "learning_rate": 8.739923182772731e-05,
      "loss": 2.6598,
      "step": 96
    },
    {
      "epoch": 1.342560553633218,
      "grad_norm": 1.4002549648284912,
      "learning_rate": 8.424432798163836e-05,
      "loss": 2.7373,
      "step": 97
    },
    {
      "epoch": 1.356401384083045,
      "grad_norm": 2.587266206741333,
      "learning_rate": 8.112503199194821e-05,
      "loss": 2.785,
      "step": 98
    },
    {
      "epoch": 1.370242214532872,
      "grad_norm": 1.669758915901184,
      "learning_rate": 7.804303301246311e-05,
      "loss": 2.6785,
      "step": 99
    },
    {
      "epoch": 1.3840830449826989,
      "grad_norm": 3.042837381362915,
      "learning_rate": 7.500000000000002e-05,
      "loss": 2.858,
      "step": 100
    },
    {
      "epoch": 1.3840830449826989,
      "eval_loss": 0.7048866748809814,
      "eval_runtime": 5.2514,
      "eval_samples_per_second": 9.521,
      "eval_steps_per_second": 1.333,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 145,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3877308048696934e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}