{
  "best_metric": 0.28790074586868286,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 0.5239572561185798,
  "eval_steps": 25,
  "global_step": 95,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005515339538090314,
      "grad_norm": 92.3752670288086,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 14.1418,
      "step": 1
    },
    {
      "epoch": 0.005515339538090314,
      "eval_loss": 18.986474990844727,
      "eval_runtime": 2.072,
      "eval_samples_per_second": 24.132,
      "eval_steps_per_second": 6.274,
      "step": 1
    },
    {
      "epoch": 0.011030679076180628,
      "grad_norm": 92.41960144042969,
      "learning_rate": 6.666666666666667e-05,
      "loss": 14.1418,
      "step": 2
    },
    {
      "epoch": 0.016546018614270942,
      "grad_norm": 91.83131408691406,
      "learning_rate": 0.0001,
      "loss": 9.4242,
      "step": 3
    },
    {
      "epoch": 0.022061358152361255,
      "grad_norm": 17.633739471435547,
      "learning_rate": 9.997376600647783e-05,
      "loss": 5.9923,
      "step": 4
    },
    {
      "epoch": 0.027576697690451568,
      "grad_norm": 9.156025886535645,
      "learning_rate": 9.989509461357426e-05,
      "loss": 4.2342,
      "step": 5
    },
    {
      "epoch": 0.033092037228541885,
      "grad_norm": 14.200757026672363,
      "learning_rate": 9.976407754861426e-05,
      "loss": 5.1585,
      "step": 6
    },
    {
      "epoch": 0.038607376766632194,
      "grad_norm": 11.900317192077637,
      "learning_rate": 9.958086757163489e-05,
      "loss": 6.826,
      "step": 7
    },
    {
      "epoch": 0.04412271630472251,
      "grad_norm": 12.914311408996582,
      "learning_rate": 9.934567829727386e-05,
      "loss": 6.2055,
      "step": 8
    },
    {
      "epoch": 0.04963805584281282,
      "grad_norm": 14.33440113067627,
      "learning_rate": 9.905878394570453e-05,
      "loss": 5.3226,
      "step": 9
    },
    {
      "epoch": 0.055153395380903136,
      "grad_norm": 16.229171752929688,
      "learning_rate": 9.872051902290737e-05,
      "loss": 4.2126,
      "step": 10
    },
    {
      "epoch": 0.06066873491899345,
      "grad_norm": 18.343318939208984,
      "learning_rate": 9.833127793065098e-05,
      "loss": 2.8094,
      "step": 11
    },
    {
      "epoch": 0.06618407445708377,
      "grad_norm": 20.21609878540039,
      "learning_rate": 9.789151450663723e-05,
      "loss": 1.1322,
      "step": 12
    },
    {
      "epoch": 0.07169941399517407,
      "grad_norm": 8.667510986328125,
      "learning_rate": 9.740174149534693e-05,
      "loss": 1.199,
      "step": 13
    },
    {
      "epoch": 0.07721475353326439,
      "grad_norm": 16.896587371826172,
      "learning_rate": 9.686252995020249e-05,
      "loss": 2.4148,
      "step": 14
    },
    {
      "epoch": 0.0827300930713547,
      "grad_norm": 17.433048248291016,
      "learning_rate": 9.627450856774539e-05,
      "loss": 2.4726,
      "step": 15
    },
    {
      "epoch": 0.08824543260944502,
      "grad_norm": 18.047983169555664,
      "learning_rate": 9.563836295460398e-05,
      "loss": 2.1929,
      "step": 16
    },
    {
      "epoch": 0.09376077214753534,
      "grad_norm": 18.881397247314453,
      "learning_rate": 9.495483482810688e-05,
      "loss": 1.6352,
      "step": 17
    },
    {
      "epoch": 0.09927611168562564,
      "grad_norm": 16.9337158203125,
      "learning_rate": 9.422472115147382e-05,
      "loss": 0.8618,
      "step": 18
    },
    {
      "epoch": 0.10479145122371596,
      "grad_norm": 24.55199432373047,
      "learning_rate": 9.3448873204592e-05,
      "loss": 0.5281,
      "step": 19
    },
    {
      "epoch": 0.11030679076180627,
      "grad_norm": 27.92365074157715,
      "learning_rate": 9.2628195591462e-05,
      "loss": 1.0844,
      "step": 20
    },
    {
      "epoch": 0.11582213029989659,
      "grad_norm": 26.889196395874023,
      "learning_rate": 9.176364518546989e-05,
      "loss": 1.218,
      "step": 21
    },
    {
      "epoch": 0.1213374698379869,
      "grad_norm": 26.291074752807617,
      "learning_rate": 9.08562300137157e-05,
      "loss": 1.0191,
      "step": 22
    },
    {
      "epoch": 0.1268528093760772,
      "grad_norm": 22.38892364501953,
      "learning_rate": 8.990700808169889e-05,
      "loss": 0.5982,
      "step": 23
    },
    {
      "epoch": 0.13236814891416754,
      "grad_norm": 11.694781303405762,
      "learning_rate": 8.891708613973126e-05,
      "loss": 0.1916,
      "step": 24
    },
    {
      "epoch": 0.13788348845225784,
      "grad_norm": 1.7668880224227905,
      "learning_rate": 8.788761839251559e-05,
      "loss": 0.025,
      "step": 25
    },
    {
      "epoch": 0.13788348845225784,
      "eval_loss": 0.4710754156112671,
      "eval_runtime": 2.0825,
      "eval_samples_per_second": 24.009,
      "eval_steps_per_second": 6.242,
      "step": 25
    },
    {
      "epoch": 0.14339882799034814,
      "grad_norm": 15.763641357421875,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.0617,
      "step": 26
    },
    {
      "epoch": 0.14891416752843847,
      "grad_norm": 15.280720710754395,
      "learning_rate": 8.571489144483944e-05,
      "loss": 1.3544,
      "step": 27
    },
    {
      "epoch": 0.15442950706652878,
      "grad_norm": 14.879006385803223,
      "learning_rate": 8.457416554680877e-05,
      "loss": 1.4492,
      "step": 28
    },
    {
      "epoch": 0.1599448466046191,
      "grad_norm": 14.426602363586426,
      "learning_rate": 8.339895749467238e-05,
      "loss": 1.3997,
      "step": 29
    },
    {
      "epoch": 0.1654601861427094,
      "grad_norm": 14.272067070007324,
      "learning_rate": 8.219063752844926e-05,
      "loss": 1.2409,
      "step": 30
    },
    {
      "epoch": 0.1709755256807997,
      "grad_norm": 9.54008960723877,
      "learning_rate": 8.095061449516903e-05,
      "loss": 0.7096,
      "step": 31
    },
    {
      "epoch": 0.17649086521889004,
      "grad_norm": 0.5781741738319397,
      "learning_rate": 7.968033420621935e-05,
      "loss": 0.0109,
      "step": 32
    },
    {
      "epoch": 0.18200620475698034,
      "grad_norm": 1.3752659559249878,
      "learning_rate": 7.838127775159452e-05,
      "loss": 0.0241,
      "step": 33
    },
    {
      "epoch": 0.18752154429507067,
      "grad_norm": 1.6789705753326416,
      "learning_rate": 7.705495977301078e-05,
      "loss": 0.0301,
      "step": 34
    },
    {
      "epoch": 0.19303688383316098,
      "grad_norm": 1.4155908823013306,
      "learning_rate": 7.570292669790186e-05,
      "loss": 0.0255,
      "step": 35
    },
    {
      "epoch": 0.19855222337125128,
      "grad_norm": 0.8778910040855408,
      "learning_rate": 7.43267549363537e-05,
      "loss": 0.0164,
      "step": 36
    },
    {
      "epoch": 0.2040675629093416,
      "grad_norm": 0.4698180556297302,
      "learning_rate": 7.292804904308087e-05,
      "loss": 0.0094,
      "step": 37
    },
    {
      "epoch": 0.2095829024474319,
      "grad_norm": 7.407131671905518,
      "learning_rate": 7.150843984658754e-05,
      "loss": 0.5839,
      "step": 38
    },
    {
      "epoch": 0.21509824198552224,
      "grad_norm": 11.81148624420166,
      "learning_rate": 7.006958254769438e-05,
      "loss": 0.9861,
      "step": 39
    },
    {
      "epoch": 0.22061358152361255,
      "grad_norm": 11.63061237335205,
      "learning_rate": 6.861315478964841e-05,
      "loss": 0.9721,
      "step": 40
    },
    {
      "epoch": 0.22612892106170285,
      "grad_norm": 11.430267333984375,
      "learning_rate": 6.714085470206609e-05,
      "loss": 0.9024,
      "step": 41
    },
    {
      "epoch": 0.23164426059979318,
      "grad_norm": 11.040278434753418,
      "learning_rate": 6.56543989209901e-05,
      "loss": 0.7755,
      "step": 42
    },
    {
      "epoch": 0.23715960013788348,
      "grad_norm": 9.684221267700195,
      "learning_rate": 6.415552058736854e-05,
      "loss": 0.5668,
      "step": 43
    },
    {
      "epoch": 0.2426749396759738,
      "grad_norm": 2.087521553039551,
      "learning_rate": 6.264596732629e-05,
      "loss": 0.0431,
      "step": 44
    },
    {
      "epoch": 0.2481902792140641,
      "grad_norm": 3.5265278816223145,
      "learning_rate": 6.112749920933111e-05,
      "loss": 0.0777,
      "step": 45
    },
    {
      "epoch": 0.2537056187521544,
      "grad_norm": 4.007287502288818,
      "learning_rate": 5.960188670239154e-05,
      "loss": 0.0911,
      "step": 46
    },
    {
      "epoch": 0.2592209582902447,
      "grad_norm": 3.595430612564087,
      "learning_rate": 5.80709086014102e-05,
      "loss": 0.0834,
      "step": 47
    },
    {
      "epoch": 0.2647362978283351,
      "grad_norm": 2.904953956604004,
      "learning_rate": 5.653634995836856e-05,
      "loss": 0.0653,
      "step": 48
    },
    {
      "epoch": 0.2702516373664254,
      "grad_norm": 1.9227010011672974,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0425,
      "step": 49
    },
    {
      "epoch": 0.2757669769045157,
      "grad_norm": 1.1187314987182617,
      "learning_rate": 5.346365004163145e-05,
      "loss": 0.0248,
      "step": 50
    },
    {
      "epoch": 0.2757669769045157,
      "eval_loss": 0.31743958592414856,
      "eval_runtime": 2.0803,
      "eval_samples_per_second": 24.035,
      "eval_steps_per_second": 6.249,
      "step": 50
    },
    {
      "epoch": 0.281282316442606,
      "grad_norm": 9.661118507385254,
      "learning_rate": 5.192909139858981e-05,
      "loss": 0.6918,
      "step": 51
    },
    {
      "epoch": 0.2867976559806963,
      "grad_norm": 9.91291332244873,
      "learning_rate": 5.0398113297608465e-05,
      "loss": 0.7725,
      "step": 52
    },
    {
      "epoch": 0.29231299551878664,
      "grad_norm": 9.74583911895752,
      "learning_rate": 4.887250079066892e-05,
      "loss": 0.8055,
      "step": 53
    },
    {
      "epoch": 0.29782833505687695,
      "grad_norm": 9.611279487609863,
      "learning_rate": 4.7354032673710005e-05,
      "loss": 0.8017,
      "step": 54
    },
    {
      "epoch": 0.30334367459496725,
      "grad_norm": 9.350974082946777,
      "learning_rate": 4.584447941263149e-05,
      "loss": 0.7482,
      "step": 55
    },
    {
      "epoch": 0.30885901413305755,
      "grad_norm": 0.41890618205070496,
      "learning_rate": 4.43456010790099e-05,
      "loss": 0.0797,
      "step": 56
    },
    {
      "epoch": 0.31437435367114785,
      "grad_norm": 0.7210342288017273,
      "learning_rate": 4.285914529793391e-05,
      "loss": 0.0184,
      "step": 57
    },
    {
      "epoch": 0.3198896932092382,
      "grad_norm": 0.8834096193313599,
      "learning_rate": 4.13868452103516e-05,
      "loss": 0.0226,
      "step": 58
    },
    {
      "epoch": 0.3254050327473285,
      "grad_norm": 0.9115370512008667,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 0.0235,
      "step": 59
    },
    {
      "epoch": 0.3309203722854188,
      "grad_norm": 0.8448688387870789,
      "learning_rate": 3.8491560153412466e-05,
      "loss": 0.0218,
      "step": 60
    },
    {
      "epoch": 0.3364357118235091,
      "grad_norm": 0.7082563042640686,
      "learning_rate": 3.707195095691913e-05,
      "loss": 0.0184,
      "step": 61
    },
    {
      "epoch": 0.3419510513615994,
      "grad_norm": 0.5660529136657715,
      "learning_rate": 3.567324506364632e-05,
      "loss": 0.0147,
      "step": 62
    },
    {
      "epoch": 0.3474663908996898,
      "grad_norm": 5.351521015167236,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 0.4547,
      "step": 63
    },
    {
      "epoch": 0.3529817304377801,
      "grad_norm": 8.921615600585938,
      "learning_rate": 3.2945040226989244e-05,
      "loss": 0.7382,
      "step": 64
    },
    {
      "epoch": 0.3584970699758704,
      "grad_norm": 8.974565505981445,
      "learning_rate": 3.16187222484055e-05,
      "loss": 0.7427,
      "step": 65
    },
    {
      "epoch": 0.3640124095139607,
      "grad_norm": 8.922871589660645,
      "learning_rate": 3.0319665793780648e-05,
      "loss": 0.7236,
      "step": 66
    },
    {
      "epoch": 0.369527749052051,
      "grad_norm": 8.645066261291504,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 0.6789,
      "step": 67
    },
    {
      "epoch": 0.37504308859014135,
      "grad_norm": 5.97182035446167,
      "learning_rate": 2.7809362471550748e-05,
      "loss": 0.4572,
      "step": 68
    },
    {
      "epoch": 0.38055842812823165,
      "grad_norm": 0.8891826868057251,
      "learning_rate": 2.660104250532764e-05,
      "loss": 0.0231,
      "step": 69
    },
    {
      "epoch": 0.38607376766632195,
      "grad_norm": 1.1015204191207886,
      "learning_rate": 2.5425834453191232e-05,
      "loss": 0.029,
      "step": 70
    },
    {
      "epoch": 0.39158910720441226,
      "grad_norm": 1.2106517553329468,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 0.0317,
      "step": 71
    },
    {
      "epoch": 0.39710444674250256,
      "grad_norm": 1.1796172857284546,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.0314,
      "step": 72
    },
    {
      "epoch": 0.4026197862805929,
      "grad_norm": 1.0850085020065308,
      "learning_rate": 2.2112381607484417e-05,
      "loss": 0.0283,
      "step": 73
    },
    {
      "epoch": 0.4081351258186832,
      "grad_norm": 0.9120981097221375,
      "learning_rate": 2.1082913860268765e-05,
      "loss": 0.0237,
      "step": 74
    },
    {
      "epoch": 0.4136504653567735,
      "grad_norm": 0.8024790287017822,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 0.0207,
      "step": 75
    },
    {
      "epoch": 0.4136504653567735,
      "eval_loss": 0.28790074586868286,
      "eval_runtime": 2.0948,
      "eval_samples_per_second": 23.869,
      "eval_steps_per_second": 6.206,
      "step": 75
    },
    {
      "epoch": 0.4191658048948638,
      "grad_norm": 8.318974494934082,
      "learning_rate": 1.91437699862843e-05,
      "loss": 0.6345,
      "step": 76
    },
    {
      "epoch": 0.4246811444329541,
      "grad_norm": 8.486698150634766,
      "learning_rate": 1.8236354814530112e-05,
      "loss": 0.6599,
      "step": 77
    },
    {
      "epoch": 0.4301964839710445,
      "grad_norm": 8.49923038482666,
      "learning_rate": 1.7371804408538024e-05,
      "loss": 0.6645,
      "step": 78
    },
    {
      "epoch": 0.4357118235091348,
      "grad_norm": 8.403206825256348,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 0.657,
      "step": 79
    },
    {
      "epoch": 0.4412271630472251,
      "grad_norm": 8.299516677856445,
      "learning_rate": 1.577527884852619e-05,
      "loss": 0.6464,
      "step": 80
    },
    {
      "epoch": 0.4467425025853154,
      "grad_norm": 1.9985052347183228,
      "learning_rate": 1.5045165171893116e-05,
      "loss": 0.1938,
      "step": 81
    },
    {
      "epoch": 0.4522578421234057,
      "grad_norm": 0.7599959969520569,
      "learning_rate": 1.4361637045396029e-05,
      "loss": 0.0196,
      "step": 82
    },
    {
      "epoch": 0.45777318166149605,
      "grad_norm": 0.8468267917633057,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 0.0219,
      "step": 83
    },
    {
      "epoch": 0.46328852119958636,
      "grad_norm": 0.8709926009178162,
      "learning_rate": 1.313747004979751e-05,
      "loss": 0.0224,
      "step": 84
    },
    {
      "epoch": 0.46880386073767666,
      "grad_norm": 0.857819676399231,
      "learning_rate": 1.2598258504653081e-05,
      "loss": 0.0221,
      "step": 85
    },
    {
      "epoch": 0.47431920027576696,
      "grad_norm": 0.807769775390625,
      "learning_rate": 1.2108485493362765e-05,
      "loss": 0.0207,
      "step": 86
    },
    {
      "epoch": 0.47983453981385726,
      "grad_norm": 0.8083691000938416,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 0.0209,
      "step": 87
    },
    {
      "epoch": 0.4853498793519476,
      "grad_norm": 4.770956993103027,
      "learning_rate": 1.1279480977092635e-05,
      "loss": 0.3815,
      "step": 88
    },
    {
      "epoch": 0.4908652188900379,
      "grad_norm": 8.195169448852539,
      "learning_rate": 1.094121605429547e-05,
      "loss": 0.6112,
      "step": 89
    },
    {
      "epoch": 0.4963805584281282,
      "grad_norm": 8.203980445861816,
      "learning_rate": 1.0654321702726141e-05,
      "loss": 0.6149,
      "step": 90
    },
    {
      "epoch": 0.5018958979662186,
      "grad_norm": 8.144838333129883,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 0.609,
      "step": 91
    },
    {
      "epoch": 0.5074112375043088,
      "grad_norm": 8.066883087158203,
      "learning_rate": 1.0235922451385733e-05,
      "loss": 0.5882,
      "step": 92
    },
    {
      "epoch": 0.5129265770423992,
      "grad_norm": 6.3228607177734375,
      "learning_rate": 1.0104905386425733e-05,
      "loss": 0.4687,
      "step": 93
    },
    {
      "epoch": 0.5184419165804894,
      "grad_norm": 0.907468318939209,
      "learning_rate": 1.002623399352217e-05,
      "loss": 0.0236,
      "step": 94
    },
    {
      "epoch": 0.5239572561185798,
      "grad_norm": 1.0146715641021729,
      "learning_rate": 1e-05,
      "loss": 0.0264,
      "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": 3.087136995672064e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}