{
  "best_metric": 0.3743059039115906,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.007089056269384138,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.089056269384139e-05,
      "grad_norm": 0.8523349165916443,
      "learning_rate": 1e-05,
      "loss": 0.7354,
      "step": 1
    },
    {
      "epoch": 7.089056269384139e-05,
      "eval_loss": 1.757895827293396,
      "eval_runtime": 1770.2655,
      "eval_samples_per_second": 13.421,
      "eval_steps_per_second": 3.355,
      "step": 1
    },
    {
      "epoch": 0.00014178112538768277,
      "grad_norm": 1.323467493057251,
      "learning_rate": 2e-05,
      "loss": 0.7794,
      "step": 2
    },
    {
      "epoch": 0.00021267168808152416,
      "grad_norm": 1.6836873292922974,
      "learning_rate": 3e-05,
      "loss": 0.9378,
      "step": 3
    },
    {
      "epoch": 0.00028356225077536554,
      "grad_norm": 1.7740553617477417,
      "learning_rate": 4e-05,
      "loss": 1.0128,
      "step": 4
    },
    {
      "epoch": 0.0003544528134692069,
      "grad_norm": 2.306671619415283,
      "learning_rate": 5e-05,
      "loss": 1.2748,
      "step": 5
    },
    {
      "epoch": 0.0004253433761630483,
      "grad_norm": 1.819011926651001,
      "learning_rate": 6e-05,
      "loss": 1.2096,
      "step": 6
    },
    {
      "epoch": 0.0004962339388568897,
      "grad_norm": 2.2308766841888428,
      "learning_rate": 7e-05,
      "loss": 1.3804,
      "step": 7
    },
    {
      "epoch": 0.0005671245015507311,
      "grad_norm": 1.9061588048934937,
      "learning_rate": 8e-05,
      "loss": 1.0324,
      "step": 8
    },
    {
      "epoch": 0.0006380150642445725,
      "grad_norm": 1.6470242738723755,
      "learning_rate": 9e-05,
      "loss": 0.8648,
      "step": 9
    },
    {
      "epoch": 0.0007089056269384139,
      "grad_norm": 1.5834276676177979,
      "learning_rate": 0.0001,
      "loss": 0.8482,
      "step": 10
    },
    {
      "epoch": 0.0007797961896322552,
      "grad_norm": 1.7377867698669434,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.7211,
      "step": 11
    },
    {
      "epoch": 0.0008506867523260966,
      "grad_norm": 1.5416024923324585,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.7497,
      "step": 12
    },
    {
      "epoch": 0.000921577315019938,
      "grad_norm": 1.1225073337554932,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.7273,
      "step": 13
    },
    {
      "epoch": 0.0009924678777137794,
      "grad_norm": 0.8795270323753357,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.5149,
      "step": 14
    },
    {
      "epoch": 0.0010633584404076207,
      "grad_norm": 0.7676340937614441,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.5692,
      "step": 15
    },
    {
      "epoch": 0.0011342490031014622,
      "grad_norm": 0.8031944632530212,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.5355,
      "step": 16
    },
    {
      "epoch": 0.0012051395657953034,
      "grad_norm": 0.8596481680870056,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.5862,
      "step": 17
    },
    {
      "epoch": 0.001276030128489145,
      "grad_norm": 0.7639876008033752,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.5911,
      "step": 18
    },
    {
      "epoch": 0.0013469206911829862,
      "grad_norm": 0.8159843683242798,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.5586,
      "step": 19
    },
    {
      "epoch": 0.0014178112538768277,
      "grad_norm": 0.7155534625053406,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.4336,
      "step": 20
    },
    {
      "epoch": 0.001488701816570669,
      "grad_norm": 0.7884729504585266,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.5175,
      "step": 21
    },
    {
      "epoch": 0.0015595923792645105,
      "grad_norm": 0.7705971598625183,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.497,
      "step": 22
    },
    {
      "epoch": 0.0016304829419583518,
      "grad_norm": 0.8776505589485168,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.5092,
      "step": 23
    },
    {
      "epoch": 0.0017013735046521932,
      "grad_norm": 0.775719940662384,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.4751,
      "step": 24
    },
    {
      "epoch": 0.0017722640673460345,
      "grad_norm": 0.7960324287414551,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.4633,
      "step": 25
    },
    {
      "epoch": 0.001843154630039876,
      "grad_norm": 0.8504328727722168,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.4781,
      "step": 26
    },
    {
      "epoch": 0.0019140451927337173,
      "grad_norm": 0.79278165102005,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.4015,
      "step": 27
    },
    {
      "epoch": 0.001984935755427559,
      "grad_norm": 0.7221006155014038,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.4712,
      "step": 28
    },
    {
      "epoch": 0.0020558263181214,
      "grad_norm": 0.6746979355812073,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.3633,
      "step": 29
    },
    {
      "epoch": 0.0021267168808152413,
      "grad_norm": 0.7011294364929199,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.4035,
      "step": 30
    },
    {
      "epoch": 0.002197607443509083,
      "grad_norm": 0.9637427926063538,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.5063,
      "step": 31
    },
    {
      "epoch": 0.0022684980062029243,
      "grad_norm": 0.8260793685913086,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.4903,
      "step": 32
    },
    {
      "epoch": 0.0023393885688967656,
      "grad_norm": 0.8451759219169617,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.5101,
      "step": 33
    },
    {
      "epoch": 0.002410279131590607,
      "grad_norm": 0.9071231484413147,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.5358,
      "step": 34
    },
    {
      "epoch": 0.0024811696942844486,
      "grad_norm": 0.8283616900444031,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.4872,
      "step": 35
    },
    {
      "epoch": 0.00255206025697829,
      "grad_norm": 0.6727207899093628,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.3844,
      "step": 36
    },
    {
      "epoch": 0.002622950819672131,
      "grad_norm": 0.6684113144874573,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.4779,
      "step": 37
    },
    {
      "epoch": 0.0026938413823659724,
      "grad_norm": 0.6834886074066162,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.4227,
      "step": 38
    },
    {
      "epoch": 0.0027647319450598137,
      "grad_norm": 0.6929678916931152,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.3783,
      "step": 39
    },
    {
      "epoch": 0.0028356225077536554,
      "grad_norm": 0.8095279335975647,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.4663,
      "step": 40
    },
    {
      "epoch": 0.0029065130704474967,
      "grad_norm": 0.6838681697845459,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.4228,
      "step": 41
    },
    {
      "epoch": 0.002977403633141338,
      "grad_norm": 0.6704063415527344,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.424,
      "step": 42
    },
    {
      "epoch": 0.0030482941958351792,
      "grad_norm": 0.6688175201416016,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.4395,
      "step": 43
    },
    {
      "epoch": 0.003119184758529021,
      "grad_norm": 0.6819213032722473,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.409,
      "step": 44
    },
    {
      "epoch": 0.0031900753212228622,
      "grad_norm": 0.7437801957130432,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.424,
      "step": 45
    },
    {
      "epoch": 0.0032609658839167035,
      "grad_norm": 0.6554301977157593,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.415,
      "step": 46
    },
    {
      "epoch": 0.0033318564466105448,
      "grad_norm": 0.8241038918495178,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.5095,
      "step": 47
    },
    {
      "epoch": 0.0034027470093043865,
      "grad_norm": 0.6540892124176025,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.4263,
      "step": 48
    },
    {
      "epoch": 0.0034736375719982278,
      "grad_norm": 0.6774754524230957,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.3218,
      "step": 49
    },
    {
      "epoch": 0.003544528134692069,
      "grad_norm": 0.8738925457000732,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.4777,
      "step": 50
    },
    {
      "epoch": 0.003544528134692069,
      "eval_loss": 0.44972315430641174,
      "eval_runtime": 1780.5046,
      "eval_samples_per_second": 13.343,
      "eval_steps_per_second": 3.336,
      "step": 50
    },
    {
      "epoch": 0.0036154186973859103,
      "grad_norm": 2.26267409324646,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.5829,
      "step": 51
    },
    {
      "epoch": 0.003686309260079752,
      "grad_norm": 1.55825674533844,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.3442,
      "step": 52
    },
    {
      "epoch": 0.0037571998227735933,
      "grad_norm": 0.7894648909568787,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.3763,
      "step": 53
    },
    {
      "epoch": 0.0038280903854674346,
      "grad_norm": 0.49781158566474915,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.3286,
      "step": 54
    },
    {
      "epoch": 0.003898980948161276,
      "grad_norm": 4.833137035369873,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.5205,
      "step": 55
    },
    {
      "epoch": 0.003969871510855118,
      "grad_norm": 0.6314643025398254,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.4451,
      "step": 56
    },
    {
      "epoch": 0.004040762073548958,
      "grad_norm": 0.5179358720779419,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.3937,
      "step": 57
    },
    {
      "epoch": 0.0041116526362428,
      "grad_norm": 0.5772222876548767,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.3653,
      "step": 58
    },
    {
      "epoch": 0.004182543198936642,
      "grad_norm": 0.5230809450149536,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.3794,
      "step": 59
    },
    {
      "epoch": 0.004253433761630483,
      "grad_norm": 0.5087058544158936,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.3957,
      "step": 60
    },
    {
      "epoch": 0.004324324324324324,
      "grad_norm": 0.4886504113674164,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.3961,
      "step": 61
    },
    {
      "epoch": 0.004395214887018166,
      "grad_norm": 0.47368374466896057,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.373,
      "step": 62
    },
    {
      "epoch": 0.004466105449712007,
      "grad_norm": 0.6237163543701172,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.3751,
      "step": 63
    },
    {
      "epoch": 0.004536996012405849,
      "grad_norm": 0.5442241430282593,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.4068,
      "step": 64
    },
    {
      "epoch": 0.0046078865750996895,
      "grad_norm": 0.6219522953033447,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.508,
      "step": 65
    },
    {
      "epoch": 0.004678777137793531,
      "grad_norm": 0.5011370778083801,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.2985,
      "step": 66
    },
    {
      "epoch": 0.004749667700487373,
      "grad_norm": 0.5422576069831848,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.3871,
      "step": 67
    },
    {
      "epoch": 0.004820558263181214,
      "grad_norm": 0.5588858127593994,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.4035,
      "step": 68
    },
    {
      "epoch": 0.0048914488258750555,
      "grad_norm": 0.5312881469726562,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.3745,
      "step": 69
    },
    {
      "epoch": 0.004962339388568897,
      "grad_norm": 0.7475187182426453,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.5522,
      "step": 70
    },
    {
      "epoch": 0.005033229951262738,
      "grad_norm": 0.47773832082748413,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.3167,
      "step": 71
    },
    {
      "epoch": 0.00510412051395658,
      "grad_norm": 0.6200078129768372,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.4522,
      "step": 72
    },
    {
      "epoch": 0.005175011076650421,
      "grad_norm": 0.5681312680244446,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.3945,
      "step": 73
    },
    {
      "epoch": 0.005245901639344262,
      "grad_norm": 0.6025010943412781,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.3965,
      "step": 74
    },
    {
      "epoch": 0.005316792202038104,
      "grad_norm": 0.5036550760269165,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.3446,
      "step": 75
    },
    {
      "epoch": 0.005387682764731945,
      "grad_norm": 0.5747814774513245,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.3936,
      "step": 76
    },
    {
      "epoch": 0.0054585733274257866,
      "grad_norm": 0.6142371892929077,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.4408,
      "step": 77
    },
    {
      "epoch": 0.005529463890119627,
      "grad_norm": 0.5577287673950195,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.3285,
      "step": 78
    },
    {
      "epoch": 0.005600354452813469,
      "grad_norm": 0.5796722173690796,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.3367,
      "step": 79
    },
    {
      "epoch": 0.005671245015507311,
      "grad_norm": 0.5557568073272705,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.3138,
      "step": 80
    },
    {
      "epoch": 0.005742135578201152,
      "grad_norm": 0.5195022821426392,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.2951,
      "step": 81
    },
    {
      "epoch": 0.005813026140894993,
      "grad_norm": 0.565771222114563,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.3469,
      "step": 82
    },
    {
      "epoch": 0.005883916703588835,
      "grad_norm": 0.707554817199707,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.3922,
      "step": 83
    },
    {
      "epoch": 0.005954807266282676,
      "grad_norm": 0.6795750856399536,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.4394,
      "step": 84
    },
    {
      "epoch": 0.006025697828976518,
      "grad_norm": 0.6365452408790588,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.4404,
      "step": 85
    },
    {
      "epoch": 0.0060965883916703585,
      "grad_norm": 0.6396660208702087,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3951,
      "step": 86
    },
    {
      "epoch": 0.0061674789543642,
      "grad_norm": 0.5342606902122498,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.3531,
      "step": 87
    },
    {
      "epoch": 0.006238369517058042,
      "grad_norm": 0.604596734046936,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.4086,
      "step": 88
    },
    {
      "epoch": 0.006309260079751883,
      "grad_norm": 0.5136443972587585,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.3438,
      "step": 89
    },
    {
      "epoch": 0.0063801506424457245,
      "grad_norm": 0.5856671929359436,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.3713,
      "step": 90
    },
    {
      "epoch": 0.006451041205139566,
      "grad_norm": 0.5504666566848755,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.3081,
      "step": 91
    },
    {
      "epoch": 0.006521931767833407,
      "grad_norm": 0.5364263653755188,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.3002,
      "step": 92
    },
    {
      "epoch": 0.006592822330527249,
      "grad_norm": 0.5979559421539307,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.4272,
      "step": 93
    },
    {
      "epoch": 0.0066637128932210896,
      "grad_norm": 0.5369541645050049,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.371,
      "step": 94
    },
    {
      "epoch": 0.006734603455914931,
      "grad_norm": 0.7055835723876953,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.4687,
      "step": 95
    },
    {
      "epoch": 0.006805494018608773,
      "grad_norm": 0.6241551637649536,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.4236,
      "step": 96
    },
    {
      "epoch": 0.006876384581302614,
      "grad_norm": 0.6014761924743652,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.3931,
      "step": 97
    },
    {
      "epoch": 0.0069472751439964555,
      "grad_norm": 0.5446456670761108,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.376,
      "step": 98
    },
    {
      "epoch": 0.007018165706690297,
      "grad_norm": 0.5127068758010864,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.289,
      "step": 99
    },
    {
      "epoch": 0.007089056269384138,
      "grad_norm": 0.6141975522041321,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.4337,
      "step": 100
    },
    {
      "epoch": 0.007089056269384138,
      "eval_loss": 0.3743059039115906,
      "eval_runtime": 1778.6043,
      "eval_samples_per_second": 13.358,
      "eval_steps_per_second": 3.34,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.37604737531904e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}