{
  "best_metric": 11.898860931396484,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 0.11705814401232191,
  "eval_steps": 25,
  "global_step": 95,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012321909896033886,
      "grad_norm": 0.060775503516197205,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 11.9363,
      "step": 1
    },
    {
      "epoch": 0.0012321909896033886,
      "eval_loss": 11.935738563537598,
      "eval_runtime": 0.4452,
      "eval_samples_per_second": 112.307,
      "eval_steps_per_second": 29.2,
      "step": 1
    },
    {
      "epoch": 0.002464381979206777,
      "grad_norm": 0.07343389838933945,
      "learning_rate": 6.666666666666667e-05,
      "loss": 11.9365,
      "step": 2
    },
    {
      "epoch": 0.0036965729688101657,
      "grad_norm": 0.06411717087030411,
      "learning_rate": 0.0001,
      "loss": 11.9362,
      "step": 3
    },
    {
      "epoch": 0.004928763958413554,
      "grad_norm": 0.05968811735510826,
      "learning_rate": 9.997376600647783e-05,
      "loss": 11.9373,
      "step": 4
    },
    {
      "epoch": 0.0061609549480169425,
      "grad_norm": 0.06928801536560059,
      "learning_rate": 9.989509461357426e-05,
      "loss": 11.9376,
      "step": 5
    },
    {
      "epoch": 0.0073931459376203315,
      "grad_norm": 0.07378507405519485,
      "learning_rate": 9.976407754861426e-05,
      "loss": 11.9355,
      "step": 6
    },
    {
      "epoch": 0.00862533692722372,
      "grad_norm": 0.07377367466688156,
      "learning_rate": 9.958086757163489e-05,
      "loss": 11.9339,
      "step": 7
    },
    {
      "epoch": 0.009857527916827109,
      "grad_norm": 0.08905545622110367,
      "learning_rate": 9.934567829727386e-05,
      "loss": 11.9327,
      "step": 8
    },
    {
      "epoch": 0.011089718906430497,
      "grad_norm": 0.08033275604248047,
      "learning_rate": 9.905878394570453e-05,
      "loss": 11.9319,
      "step": 9
    },
    {
      "epoch": 0.012321909896033885,
      "grad_norm": 0.10465037077665329,
      "learning_rate": 9.872051902290737e-05,
      "loss": 11.9335,
      "step": 10
    },
    {
      "epoch": 0.013554100885637273,
      "grad_norm": 0.15654270350933075,
      "learning_rate": 9.833127793065098e-05,
      "loss": 11.9313,
      "step": 11
    },
    {
      "epoch": 0.014786291875240663,
      "grad_norm": 0.16284310817718506,
      "learning_rate": 9.789151450663723e-05,
      "loss": 11.9295,
      "step": 12
    },
    {
      "epoch": 0.01601848286484405,
      "grad_norm": 0.09769000113010406,
      "learning_rate": 9.740174149534693e-05,
      "loss": 11.9327,
      "step": 13
    },
    {
      "epoch": 0.01725067385444744,
      "grad_norm": 0.08060012757778168,
      "learning_rate": 9.686252995020249e-05,
      "loss": 11.9325,
      "step": 14
    },
    {
      "epoch": 0.018482864844050827,
      "grad_norm": 0.0939093828201294,
      "learning_rate": 9.627450856774539e-05,
      "loss": 11.9323,
      "step": 15
    },
    {
      "epoch": 0.019715055833654217,
      "grad_norm": 0.09729772806167603,
      "learning_rate": 9.563836295460398e-05,
      "loss": 11.934,
      "step": 16
    },
    {
      "epoch": 0.020947246823257604,
      "grad_norm": 0.10164664685726166,
      "learning_rate": 9.495483482810688e-05,
      "loss": 11.9317,
      "step": 17
    },
    {
      "epoch": 0.022179437812860994,
      "grad_norm": 0.11222667992115021,
      "learning_rate": 9.422472115147382e-05,
      "loss": 11.9313,
      "step": 18
    },
    {
      "epoch": 0.023411628802464383,
      "grad_norm": 0.11252212524414062,
      "learning_rate": 9.3448873204592e-05,
      "loss": 11.931,
      "step": 19
    },
    {
      "epoch": 0.02464381979206777,
      "grad_norm": 0.13546523451805115,
      "learning_rate": 9.2628195591462e-05,
      "loss": 11.9307,
      "step": 20
    },
    {
      "epoch": 0.02587601078167116,
      "grad_norm": 0.14520035684108734,
      "learning_rate": 9.176364518546989e-05,
      "loss": 11.9278,
      "step": 21
    },
    {
      "epoch": 0.027108201771274546,
      "grad_norm": 0.1726980060338974,
      "learning_rate": 9.08562300137157e-05,
      "loss": 11.9236,
      "step": 22
    },
    {
      "epoch": 0.028340392760877936,
      "grad_norm": 0.1935577541589737,
      "learning_rate": 8.990700808169889e-05,
      "loss": 11.9236,
      "step": 23
    },
    {
      "epoch": 0.029572583750481326,
      "grad_norm": 0.208387091755867,
      "learning_rate": 8.891708613973126e-05,
      "loss": 11.9201,
      "step": 24
    },
    {
      "epoch": 0.030804774740084712,
      "grad_norm": 0.25750771164894104,
      "learning_rate": 8.788761839251559e-05,
      "loss": 11.9189,
      "step": 25
    },
    {
      "epoch": 0.030804774740084712,
      "eval_loss": 11.921143531799316,
      "eval_runtime": 0.4097,
      "eval_samples_per_second": 122.041,
      "eval_steps_per_second": 31.731,
      "step": 25
    },
    {
      "epoch": 0.0320369657296881,
      "grad_norm": 0.1562894582748413,
      "learning_rate": 8.681980515339464e-05,
      "loss": 11.9259,
      "step": 26
    },
    {
      "epoch": 0.03326915671929149,
      "grad_norm": 0.16972583532333374,
      "learning_rate": 8.571489144483944e-05,
      "loss": 11.9242,
      "step": 27
    },
    {
      "epoch": 0.03450134770889488,
      "grad_norm": 0.1763102412223816,
      "learning_rate": 8.457416554680877e-05,
      "loss": 11.9227,
      "step": 28
    },
    {
      "epoch": 0.03573353869849827,
      "grad_norm": 0.18980900943279266,
      "learning_rate": 8.339895749467238e-05,
      "loss": 11.923,
      "step": 29
    },
    {
      "epoch": 0.036965729688101655,
      "grad_norm": 0.18117795884609222,
      "learning_rate": 8.219063752844926e-05,
      "loss": 11.9203,
      "step": 30
    },
    {
      "epoch": 0.03819792067770504,
      "grad_norm": 0.15770718455314636,
      "learning_rate": 8.095061449516903e-05,
      "loss": 11.9228,
      "step": 31
    },
    {
      "epoch": 0.039430111667308435,
      "grad_norm": 0.21280968189239502,
      "learning_rate": 7.968033420621935e-05,
      "loss": 11.9144,
      "step": 32
    },
    {
      "epoch": 0.04066230265691182,
      "grad_norm": 0.16655640304088593,
      "learning_rate": 7.838127775159452e-05,
      "loss": 11.9188,
      "step": 33
    },
    {
      "epoch": 0.04189449364651521,
      "grad_norm": 0.18396218121051788,
      "learning_rate": 7.705495977301078e-05,
      "loss": 11.9168,
      "step": 34
    },
    {
      "epoch": 0.0431266846361186,
      "grad_norm": 0.19807805120944977,
      "learning_rate": 7.570292669790186e-05,
      "loss": 11.9119,
      "step": 35
    },
    {
      "epoch": 0.04435887562572199,
      "grad_norm": 0.24202106893062592,
      "learning_rate": 7.43267549363537e-05,
      "loss": 11.9091,
      "step": 36
    },
    {
      "epoch": 0.045591066615325374,
      "grad_norm": 0.22782112658023834,
      "learning_rate": 7.292804904308087e-05,
      "loss": 11.9144,
      "step": 37
    },
    {
      "epoch": 0.04682325760492877,
      "grad_norm": 0.1838875114917755,
      "learning_rate": 7.150843984658754e-05,
      "loss": 11.9138,
      "step": 38
    },
    {
      "epoch": 0.04805544859453215,
      "grad_norm": 0.1562553346157074,
      "learning_rate": 7.006958254769438e-05,
      "loss": 11.9152,
      "step": 39
    },
    {
      "epoch": 0.04928763958413554,
      "grad_norm": 0.16204679012298584,
      "learning_rate": 6.861315478964841e-05,
      "loss": 11.9147,
      "step": 40
    },
    {
      "epoch": 0.050519830573738926,
      "grad_norm": 0.17445921897888184,
      "learning_rate": 6.714085470206609e-05,
      "loss": 11.9121,
      "step": 41
    },
    {
      "epoch": 0.05175202156334232,
      "grad_norm": 0.17594383656978607,
      "learning_rate": 6.56543989209901e-05,
      "loss": 11.911,
      "step": 42
    },
    {
      "epoch": 0.052984212552945706,
      "grad_norm": 0.15127213299274445,
      "learning_rate": 6.415552058736854e-05,
      "loss": 11.9129,
      "step": 43
    },
    {
      "epoch": 0.05421640354254909,
      "grad_norm": 0.1726858913898468,
      "learning_rate": 6.264596732629e-05,
      "loss": 11.9105,
      "step": 44
    },
    {
      "epoch": 0.055448594532152486,
      "grad_norm": 0.16555853188037872,
      "learning_rate": 6.112749920933111e-05,
      "loss": 11.9067,
      "step": 45
    },
    {
      "epoch": 0.05668078552175587,
      "grad_norm": 0.15048764646053314,
      "learning_rate": 5.960188670239154e-05,
      "loss": 11.9086,
      "step": 46
    },
    {
      "epoch": 0.05791297651135926,
      "grad_norm": 0.1858365684747696,
      "learning_rate": 5.80709086014102e-05,
      "loss": 11.9065,
      "step": 47
    },
    {
      "epoch": 0.05914516750096265,
      "grad_norm": 0.1863349974155426,
      "learning_rate": 5.653634995836856e-05,
      "loss": 11.9058,
      "step": 48
    },
    {
      "epoch": 0.06037735849056604,
      "grad_norm": 0.21114401519298553,
      "learning_rate": 5.500000000000001e-05,
      "loss": 11.8964,
      "step": 49
    },
    {
      "epoch": 0.061609549480169425,
      "grad_norm": 0.26575568318367004,
      "learning_rate": 5.346365004163145e-05,
      "loss": 11.8979,
      "step": 50
    },
    {
      "epoch": 0.061609549480169425,
      "eval_loss": 11.904302597045898,
      "eval_runtime": 0.4424,
      "eval_samples_per_second": 113.019,
      "eval_steps_per_second": 29.385,
      "step": 50
    },
    {
      "epoch": 0.06284174046977281,
      "grad_norm": 0.14176851511001587,
      "learning_rate": 5.192909139858981e-05,
      "loss": 11.9077,
      "step": 51
    },
    {
      "epoch": 0.0640739314593762,
      "grad_norm": 0.14125069975852966,
      "learning_rate": 5.0398113297608465e-05,
      "loss": 11.9084,
      "step": 52
    },
    {
      "epoch": 0.0653061224489796,
      "grad_norm": 0.13022831082344055,
      "learning_rate": 4.887250079066892e-05,
      "loss": 11.9067,
      "step": 53
    },
    {
      "epoch": 0.06653831343858298,
      "grad_norm": 0.1437574028968811,
      "learning_rate": 4.7354032673710005e-05,
      "loss": 11.905,
      "step": 54
    },
    {
      "epoch": 0.06777050442818637,
      "grad_norm": 0.12500199675559998,
      "learning_rate": 4.584447941263149e-05,
      "loss": 11.9048,
      "step": 55
    },
    {
      "epoch": 0.06900269541778976,
      "grad_norm": 0.15741832554340363,
      "learning_rate": 4.43456010790099e-05,
      "loss": 11.9049,
      "step": 56
    },
    {
      "epoch": 0.07023488640739314,
      "grad_norm": 0.1377156525850296,
      "learning_rate": 4.285914529793391e-05,
      "loss": 11.9036,
      "step": 57
    },
    {
      "epoch": 0.07146707739699654,
      "grad_norm": 0.14599944651126862,
      "learning_rate": 4.13868452103516e-05,
      "loss": 11.9023,
      "step": 58
    },
    {
      "epoch": 0.07269926838659992,
      "grad_norm": 0.14348281919956207,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 11.9015,
      "step": 59
    },
    {
      "epoch": 0.07393145937620331,
      "grad_norm": 0.1534987986087799,
      "learning_rate": 3.8491560153412466e-05,
      "loss": 11.9031,
      "step": 60
    },
    {
      "epoch": 0.0751636503658067,
      "grad_norm": 0.20068278908729553,
      "learning_rate": 3.707195095691913e-05,
      "loss": 11.9012,
      "step": 61
    },
    {
      "epoch": 0.07639584135541008,
      "grad_norm": 0.23697830736637115,
      "learning_rate": 3.567324506364632e-05,
      "loss": 11.8982,
      "step": 62
    },
    {
      "epoch": 0.07762803234501348,
      "grad_norm": 0.12292071431875229,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 11.9056,
      "step": 63
    },
    {
      "epoch": 0.07886022333461687,
      "grad_norm": 0.10782992094755173,
      "learning_rate": 3.2945040226989244e-05,
      "loss": 11.9042,
      "step": 64
    },
    {
      "epoch": 0.08009241432422025,
      "grad_norm": 0.12751153111457825,
      "learning_rate": 3.16187222484055e-05,
      "loss": 11.9046,
      "step": 65
    },
    {
      "epoch": 0.08132460531382364,
      "grad_norm": 0.11147710680961609,
      "learning_rate": 3.0319665793780648e-05,
      "loss": 11.9034,
      "step": 66
    },
    {
      "epoch": 0.08255679630342704,
      "grad_norm": 0.10850214958190918,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 11.9019,
      "step": 67
    },
    {
      "epoch": 0.08378898729303041,
      "grad_norm": 0.12796252965927124,
      "learning_rate": 2.7809362471550748e-05,
      "loss": 11.9035,
      "step": 68
    },
    {
      "epoch": 0.08502117828263381,
      "grad_norm": 0.11640307307243347,
      "learning_rate": 2.660104250532764e-05,
      "loss": 11.8993,
      "step": 69
    },
    {
      "epoch": 0.0862533692722372,
      "grad_norm": 0.14162230491638184,
      "learning_rate": 2.5425834453191232e-05,
      "loss": 11.9038,
      "step": 70
    },
    {
      "epoch": 0.08748556026184058,
      "grad_norm": 0.12289347499608994,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 11.9017,
      "step": 71
    },
    {
      "epoch": 0.08871775125144397,
      "grad_norm": 0.14467501640319824,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 11.9031,
      "step": 72
    },
    {
      "epoch": 0.08994994224104737,
      "grad_norm": 0.21114110946655273,
      "learning_rate": 2.2112381607484417e-05,
      "loss": 11.8997,
      "step": 73
    },
    {
      "epoch": 0.09118213323065075,
      "grad_norm": 0.20919640362262726,
      "learning_rate": 2.1082913860268765e-05,
      "loss": 11.8962,
      "step": 74
    },
    {
      "epoch": 0.09241432422025414,
      "grad_norm": 0.2882833480834961,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 11.8899,
      "step": 75
    },
    {
      "epoch": 0.09241432422025414,
      "eval_loss": 11.898860931396484,
      "eval_runtime": 0.4413,
      "eval_samples_per_second": 113.302,
      "eval_steps_per_second": 29.459,
      "step": 75
    },
    {
      "epoch": 0.09364651520985753,
      "grad_norm": 0.11339965462684631,
      "learning_rate": 1.91437699862843e-05,
      "loss": 11.9061,
      "step": 76
    },
    {
      "epoch": 0.09487870619946091,
      "grad_norm": 0.0967002585530281,
      "learning_rate": 1.8236354814530112e-05,
      "loss": 11.9045,
      "step": 77
    },
    {
      "epoch": 0.0961108971890643,
      "grad_norm": 0.10335846245288849,
      "learning_rate": 1.7371804408538024e-05,
      "loss": 11.9027,
      "step": 78
    },
    {
      "epoch": 0.0973430881786677,
      "grad_norm": 0.10277073085308075,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 11.9032,
      "step": 79
    },
    {
      "epoch": 0.09857527916827108,
      "grad_norm": 0.09848005324602127,
      "learning_rate": 1.577527884852619e-05,
      "loss": 11.8994,
      "step": 80
    },
    {
      "epoch": 0.09980747015787447,
      "grad_norm": 0.10161633044481277,
      "learning_rate": 1.5045165171893116e-05,
      "loss": 11.8994,
      "step": 81
    },
    {
      "epoch": 0.10103966114747785,
      "grad_norm": 0.09697967022657394,
      "learning_rate": 1.4361637045396029e-05,
      "loss": 11.9027,
      "step": 82
    },
    {
      "epoch": 0.10227185213708125,
      "grad_norm": 0.10200096666812897,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 11.9003,
      "step": 83
    },
    {
      "epoch": 0.10350404312668464,
      "grad_norm": 0.13053254783153534,
      "learning_rate": 1.313747004979751e-05,
      "loss": 11.8971,
      "step": 84
    },
    {
      "epoch": 0.10473623411628802,
      "grad_norm": 0.1328170746564865,
      "learning_rate": 1.2598258504653081e-05,
      "loss": 11.8973,
      "step": 85
    },
    {
      "epoch": 0.10596842510589141,
      "grad_norm": 0.19934439659118652,
      "learning_rate": 1.2108485493362765e-05,
      "loss": 11.8961,
      "step": 86
    },
    {
      "epoch": 0.1072006160954948,
      "grad_norm": 0.26894065737724304,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 11.8933,
      "step": 87
    },
    {
      "epoch": 0.10843280708509818,
      "grad_norm": 0.10815577208995819,
      "learning_rate": 1.1279480977092635e-05,
      "loss": 11.9066,
      "step": 88
    },
    {
      "epoch": 0.10966499807470158,
      "grad_norm": 0.10114790499210358,
      "learning_rate": 1.094121605429547e-05,
      "loss": 11.9022,
      "step": 89
    },
    {
      "epoch": 0.11089718906430497,
      "grad_norm": 0.0996105894446373,
      "learning_rate": 1.0654321702726141e-05,
      "loss": 11.9031,
      "step": 90
    },
    {
      "epoch": 0.11212938005390835,
      "grad_norm": 0.11002374440431595,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 11.9013,
      "step": 91
    },
    {
      "epoch": 0.11336157104351174,
      "grad_norm": 0.1089978888630867,
      "learning_rate": 1.0235922451385733e-05,
      "loss": 11.8994,
      "step": 92
    },
    {
      "epoch": 0.11459376203311514,
      "grad_norm": 0.10552305728197098,
      "learning_rate": 1.0104905386425733e-05,
      "loss": 11.9014,
      "step": 93
    },
    {
      "epoch": 0.11582595302271852,
      "grad_norm": 0.11430001258850098,
      "learning_rate": 1.002623399352217e-05,
      "loss": 11.8997,
      "step": 94
    },
    {
      "epoch": 0.11705814401232191,
      "grad_norm": 0.11952391266822815,
      "learning_rate": 1e-05,
      "loss": 11.8955,
      "step": 95
    }
  ],
  "logging_steps": 1,
  "max_steps": 95,
  "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": 793696618414080.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}