{
  "best_metric": 0.6604854464530945,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.0027855153203342,
  "eval_steps": 50,
  "global_step": 90,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011142061281337047,
      "grad_norm": 1.0420100688934326,
      "learning_rate": 1e-05,
      "loss": 1.1642,
      "step": 1
    },
    {
      "epoch": 0.011142061281337047,
      "eval_loss": 1.8091527223587036,
      "eval_runtime": 17.0987,
      "eval_samples_per_second": 8.89,
      "eval_steps_per_second": 2.222,
      "step": 1
    },
    {
      "epoch": 0.022284122562674095,
      "grad_norm": 1.1613749265670776,
      "learning_rate": 2e-05,
      "loss": 1.2725,
      "step": 2
    },
    {
      "epoch": 0.033426183844011144,
      "grad_norm": 1.1371344327926636,
      "learning_rate": 3e-05,
      "loss": 1.4025,
      "step": 3
    },
    {
      "epoch": 0.04456824512534819,
      "grad_norm": 1.4346470832824707,
      "learning_rate": 4e-05,
      "loss": 1.4288,
      "step": 4
    },
    {
      "epoch": 0.055710306406685235,
      "grad_norm": 1.3074644804000854,
      "learning_rate": 5e-05,
      "loss": 1.4659,
      "step": 5
    },
    {
      "epoch": 0.06685236768802229,
      "grad_norm": 1.416764497756958,
      "learning_rate": 6e-05,
      "loss": 1.439,
      "step": 6
    },
    {
      "epoch": 0.07799442896935933,
      "grad_norm": 1.8262981176376343,
      "learning_rate": 7e-05,
      "loss": 1.2719,
      "step": 7
    },
    {
      "epoch": 0.08913649025069638,
      "grad_norm": 1.8879832029342651,
      "learning_rate": 8e-05,
      "loss": 1.1828,
      "step": 8
    },
    {
      "epoch": 0.10027855153203342,
      "grad_norm": 1.7780221700668335,
      "learning_rate": 9e-05,
      "loss": 0.9261,
      "step": 9
    },
    {
      "epoch": 0.11142061281337047,
      "grad_norm": 1.4061527252197266,
      "learning_rate": 0.0001,
      "loss": 0.8449,
      "step": 10
    },
    {
      "epoch": 0.12256267409470752,
      "grad_norm": 1.4167653322219849,
      "learning_rate": 9.996145181203615e-05,
      "loss": 0.9189,
      "step": 11
    },
    {
      "epoch": 0.13370473537604458,
      "grad_norm": 1.4484316110610962,
      "learning_rate": 9.98458666866564e-05,
      "loss": 0.8569,
      "step": 12
    },
    {
      "epoch": 0.14484679665738162,
      "grad_norm": 1.3803526163101196,
      "learning_rate": 9.965342284774632e-05,
      "loss": 0.7734,
      "step": 13
    },
    {
      "epoch": 0.15598885793871867,
      "grad_norm": 1.325583815574646,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.8063,
      "step": 14
    },
    {
      "epoch": 0.1671309192200557,
      "grad_norm": 1.6950255632400513,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.9614,
      "step": 15
    },
    {
      "epoch": 0.17827298050139276,
      "grad_norm": 1.4282883405685425,
      "learning_rate": 9.861849601988383e-05,
      "loss": 0.7504,
      "step": 16
    },
    {
      "epoch": 0.1894150417827298,
      "grad_norm": 1.3364102840423584,
      "learning_rate": 9.812276182268236e-05,
      "loss": 0.7784,
      "step": 17
    },
    {
      "epoch": 0.20055710306406685,
      "grad_norm": 1.332399606704712,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.7068,
      "step": 18
    },
    {
      "epoch": 0.2116991643454039,
      "grad_norm": 1.4372507333755493,
      "learning_rate": 9.690956679612421e-05,
      "loss": 0.699,
      "step": 19
    },
    {
      "epoch": 0.22284122562674094,
      "grad_norm": 1.3753567934036255,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.8339,
      "step": 20
    },
    {
      "epoch": 0.233983286908078,
      "grad_norm": 1.4257323741912842,
      "learning_rate": 9.540715869125407e-05,
      "loss": 0.6704,
      "step": 21
    },
    {
      "epoch": 0.24512534818941503,
      "grad_norm": 2.0480964183807373,
      "learning_rate": 9.45503262094184e-05,
      "loss": 0.6739,
      "step": 22
    },
    {
      "epoch": 0.2562674094707521,
      "grad_norm": 0.6940401792526245,
      "learning_rate": 9.362480035363986e-05,
      "loss": 0.7361,
      "step": 23
    },
    {
      "epoch": 0.26740947075208915,
      "grad_norm": 0.8433642983436584,
      "learning_rate": 9.263200821770461e-05,
      "loss": 0.7383,
      "step": 24
    },
    {
      "epoch": 0.2785515320334262,
      "grad_norm": 0.8747265338897705,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.772,
      "step": 25
    },
    {
      "epoch": 0.28969359331476324,
      "grad_norm": 0.8755362629890442,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.747,
      "step": 26
    },
    {
      "epoch": 0.3008356545961003,
      "grad_norm": 1.0401290655136108,
      "learning_rate": 8.926584654403724e-05,
      "loss": 0.789,
      "step": 27
    },
    {
      "epoch": 0.31197771587743733,
      "grad_norm": 0.9953641295433044,
      "learning_rate": 8.802029828000156e-05,
      "loss": 0.8023,
      "step": 28
    },
    {
      "epoch": 0.3231197771587744,
      "grad_norm": 1.0071543455123901,
      "learning_rate": 8.671612547178428e-05,
      "loss": 0.6908,
      "step": 29
    },
    {
      "epoch": 0.3342618384401114,
      "grad_norm": 1.1228718757629395,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.7995,
      "step": 30
    },
    {
      "epoch": 0.34540389972144847,
      "grad_norm": 1.0646946430206299,
      "learning_rate": 8.39400372766471e-05,
      "loss": 0.6854,
      "step": 31
    },
    {
      "epoch": 0.3565459610027855,
      "grad_norm": 0.9896352291107178,
      "learning_rate": 8.247240241650918e-05,
      "loss": 0.6517,
      "step": 32
    },
    {
      "epoch": 0.36768802228412256,
      "grad_norm": 1.0033907890319824,
      "learning_rate": 8.095469746549172e-05,
      "loss": 0.6694,
      "step": 33
    },
    {
      "epoch": 0.3788300835654596,
      "grad_norm": 1.1896623373031616,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.7511,
      "step": 34
    },
    {
      "epoch": 0.38997214484679665,
      "grad_norm": 1.091591238975525,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.6982,
      "step": 35
    },
    {
      "epoch": 0.4011142061281337,
      "grad_norm": 1.131341814994812,
      "learning_rate": 7.612492823579745e-05,
      "loss": 0.761,
      "step": 36
    },
    {
      "epoch": 0.41225626740947074,
      "grad_norm": 1.158227801322937,
      "learning_rate": 7.443106207484776e-05,
      "loss": 0.8267,
      "step": 37
    },
    {
      "epoch": 0.4233983286908078,
      "grad_norm": 1.8035699129104614,
      "learning_rate": 7.269952498697734e-05,
      "loss": 0.6249,
      "step": 38
    },
    {
      "epoch": 0.43454038997214484,
      "grad_norm": 1.2867003679275513,
      "learning_rate": 7.09329868768714e-05,
      "loss": 0.891,
      "step": 39
    },
    {
      "epoch": 0.4456824512534819,
      "grad_norm": 1.0538527965545654,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.7137,
      "step": 40
    },
    {
      "epoch": 0.4568245125348189,
      "grad_norm": 1.4648083448410034,
      "learning_rate": 6.730585285387465e-05,
      "loss": 0.6051,
      "step": 41
    },
    {
      "epoch": 0.467966573816156,
      "grad_norm": 1.2210773229599,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7698,
      "step": 42
    },
    {
      "epoch": 0.479108635097493,
      "grad_norm": 1.5098011493682861,
      "learning_rate": 6.357202249325371e-05,
      "loss": 0.7258,
      "step": 43
    },
    {
      "epoch": 0.49025069637883006,
      "grad_norm": 1.8282679319381714,
      "learning_rate": 6.167226819279528e-05,
      "loss": 0.5714,
      "step": 44
    },
    {
      "epoch": 0.5013927576601671,
      "grad_norm": 0.700736403465271,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.6174,
      "step": 45
    },
    {
      "epoch": 0.5125348189415042,
      "grad_norm": 0.8653382062911987,
      "learning_rate": 5.782172325201155e-05,
      "loss": 0.6672,
      "step": 46
    },
    {
      "epoch": 0.5236768802228412,
      "grad_norm": 0.7241457104682922,
      "learning_rate": 5.587686987289189e-05,
      "loss": 0.6421,
      "step": 47
    },
    {
      "epoch": 0.5348189415041783,
      "grad_norm": 1.0107219219207764,
      "learning_rate": 5.392295478639225e-05,
      "loss": 0.7138,
      "step": 48
    },
    {
      "epoch": 0.5459610027855153,
      "grad_norm": 0.729120135307312,
      "learning_rate": 5.196299078795344e-05,
      "loss": 0.5774,
      "step": 49
    },
    {
      "epoch": 0.5571030640668524,
      "grad_norm": 0.8338662981987,
      "learning_rate": 5e-05,
      "loss": 0.6265,
      "step": 50
    },
    {
      "epoch": 0.5571030640668524,
      "eval_loss": 0.6604854464530945,
      "eval_runtime": 17.4209,
      "eval_samples_per_second": 8.725,
      "eval_steps_per_second": 2.181,
      "step": 50
    },
    {
      "epoch": 0.5682451253481894,
      "grad_norm": 0.8395673632621765,
      "learning_rate": 4.8037009212046586e-05,
      "loss": 0.5995,
      "step": 51
    },
    {
      "epoch": 0.5793871866295265,
      "grad_norm": 1.080180287361145,
      "learning_rate": 4.607704521360776e-05,
      "loss": 0.687,
      "step": 52
    },
    {
      "epoch": 0.5905292479108635,
      "grad_norm": 1.0408283472061157,
      "learning_rate": 4.412313012710813e-05,
      "loss": 0.6857,
      "step": 53
    },
    {
      "epoch": 0.6016713091922006,
      "grad_norm": 1.0837056636810303,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.7375,
      "step": 54
    },
    {
      "epoch": 0.6128133704735376,
      "grad_norm": 1.1068450212478638,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.6629,
      "step": 55
    },
    {
      "epoch": 0.6239554317548747,
      "grad_norm": 0.9491481184959412,
      "learning_rate": 3.832773180720475e-05,
      "loss": 0.6415,
      "step": 56
    },
    {
      "epoch": 0.6350974930362117,
      "grad_norm": 0.9771397709846497,
      "learning_rate": 3.642797750674629e-05,
      "loss": 0.6092,
      "step": 57
    },
    {
      "epoch": 0.6462395543175488,
      "grad_norm": 0.9483528733253479,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6702,
      "step": 58
    },
    {
      "epoch": 0.6573816155988857,
      "grad_norm": 1.1656486988067627,
      "learning_rate": 3.2694147146125345e-05,
      "loss": 0.7169,
      "step": 59
    },
    {
      "epoch": 0.6685236768802229,
      "grad_norm": 1.362808346748352,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.7768,
      "step": 60
    },
    {
      "epoch": 0.6796657381615598,
      "grad_norm": 1.020258903503418,
      "learning_rate": 2.9067013123128613e-05,
      "loss": 0.6284,
      "step": 61
    },
    {
      "epoch": 0.6908077994428969,
      "grad_norm": 1.527144432067871,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 0.5853,
      "step": 62
    },
    {
      "epoch": 0.7019498607242339,
      "grad_norm": 1.3415321111679077,
      "learning_rate": 2.556893792515227e-05,
      "loss": 0.5872,
      "step": 63
    },
    {
      "epoch": 0.713091922005571,
      "grad_norm": 1.19660484790802,
      "learning_rate": 2.3875071764202563e-05,
      "loss": 0.5428,
      "step": 64
    },
    {
      "epoch": 0.724233983286908,
      "grad_norm": 1.7170783281326294,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.604,
      "step": 65
    },
    {
      "epoch": 0.7353760445682451,
      "grad_norm": 1.8448792695999146,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6284,
      "step": 66
    },
    {
      "epoch": 0.7465181058495822,
      "grad_norm": 0.6753265261650085,
      "learning_rate": 1.9045302534508297e-05,
      "loss": 0.6319,
      "step": 67
    },
    {
      "epoch": 0.7576601671309192,
      "grad_norm": 0.8194894790649414,
      "learning_rate": 1.7527597583490822e-05,
      "loss": 0.5969,
      "step": 68
    },
    {
      "epoch": 0.7688022284122563,
      "grad_norm": 0.8043373227119446,
      "learning_rate": 1.605996272335291e-05,
      "loss": 0.6543,
      "step": 69
    },
    {
      "epoch": 0.7799442896935933,
      "grad_norm": 0.9129596948623657,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.7098,
      "step": 70
    },
    {
      "epoch": 0.7910863509749304,
      "grad_norm": 0.8895006775856018,
      "learning_rate": 1.3283874528215733e-05,
      "loss": 0.5837,
      "step": 71
    },
    {
      "epoch": 0.8022284122562674,
      "grad_norm": 0.7797386646270752,
      "learning_rate": 1.1979701719998453e-05,
      "loss": 0.6462,
      "step": 72
    },
    {
      "epoch": 0.8133704735376045,
      "grad_norm": 1.0365535020828247,
      "learning_rate": 1.0734153455962765e-05,
      "loss": 0.7263,
      "step": 73
    },
    {
      "epoch": 0.8245125348189415,
      "grad_norm": 0.8929746747016907,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.5768,
      "step": 74
    },
    {
      "epoch": 0.8356545961002786,
      "grad_norm": 0.9315441250801086,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.6044,
      "step": 75
    },
    {
      "epoch": 0.8467966573816156,
      "grad_norm": 0.9474170804023743,
      "learning_rate": 7.367991782295391e-06,
      "loss": 0.6207,
      "step": 76
    },
    {
      "epoch": 0.8579387186629527,
      "grad_norm": 1.0279390811920166,
      "learning_rate": 6.375199646360142e-06,
      "loss": 0.6206,
      "step": 77
    },
    {
      "epoch": 0.8690807799442897,
      "grad_norm": 1.0129948854446411,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.6151,
      "step": 78
    },
    {
      "epoch": 0.8802228412256268,
      "grad_norm": 0.9171512126922607,
      "learning_rate": 4.592841308745932e-06,
      "loss": 0.6025,
      "step": 79
    },
    {
      "epoch": 0.8913649025069638,
      "grad_norm": 1.0913035869598389,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.7344,
      "step": 80
    },
    {
      "epoch": 0.9025069637883009,
      "grad_norm": 1.4194581508636475,
      "learning_rate": 3.0904332038757977e-06,
      "loss": 0.7239,
      "step": 81
    },
    {
      "epoch": 0.9136490250696379,
      "grad_norm": 1.1939295530319214,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.636,
      "step": 82
    },
    {
      "epoch": 0.924791086350975,
      "grad_norm": 1.0078566074371338,
      "learning_rate": 1.8772381773176417e-06,
      "loss": 0.5,
      "step": 83
    },
    {
      "epoch": 0.935933147632312,
      "grad_norm": 1.0714085102081299,
      "learning_rate": 1.3815039801161721e-06,
      "loss": 0.4576,
      "step": 84
    },
    {
      "epoch": 0.947075208913649,
      "grad_norm": 1.0616954565048218,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.4891,
      "step": 85
    },
    {
      "epoch": 0.958217270194986,
      "grad_norm": 1.1367872953414917,
      "learning_rate": 6.15582970243117e-07,
      "loss": 0.589,
      "step": 86
    },
    {
      "epoch": 0.9693593314763231,
      "grad_norm": 1.2933335304260254,
      "learning_rate": 3.465771522536854e-07,
      "loss": 0.5224,
      "step": 87
    },
    {
      "epoch": 0.9805013927576601,
      "grad_norm": 1.6042691469192505,
      "learning_rate": 1.5413331334360182e-07,
      "loss": 0.5322,
      "step": 88
    },
    {
      "epoch": 0.9916434540389972,
      "grad_norm": 0.7805180549621582,
      "learning_rate": 3.8548187963854956e-08,
      "loss": 0.6384,
      "step": 89
    },
    {
      "epoch": 1.0027855153203342,
      "grad_norm": 1.1597189903259277,
      "learning_rate": 0.0,
      "loss": 0.7541,
      "step": 90
    }
  ],
  "logging_steps": 1,
  "max_steps": 90,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 1.3576622208712704e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}