{
  "best_metric": 0.7220537066459656,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.04877453969028167,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00048774539690281675,
      "grad_norm": 0.42755216360092163,
      "learning_rate": 1e-05,
      "loss": 0.8209,
      "step": 1
    },
    {
      "epoch": 0.00048774539690281675,
      "eval_loss": 1.4778821468353271,
      "eval_runtime": 249.3288,
      "eval_samples_per_second": 13.849,
      "eval_steps_per_second": 3.465,
      "step": 1
    },
    {
      "epoch": 0.0009754907938056335,
      "grad_norm": 0.4249762296676636,
      "learning_rate": 2e-05,
      "loss": 0.8839,
      "step": 2
    },
    {
      "epoch": 0.0014632361907084503,
      "grad_norm": 0.46692362427711487,
      "learning_rate": 3e-05,
      "loss": 0.8946,
      "step": 3
    },
    {
      "epoch": 0.001950981587611267,
      "grad_norm": 0.42918190360069275,
      "learning_rate": 4e-05,
      "loss": 0.891,
      "step": 4
    },
    {
      "epoch": 0.0024387269845140835,
      "grad_norm": 0.4296896755695343,
      "learning_rate": 5e-05,
      "loss": 0.8432,
      "step": 5
    },
    {
      "epoch": 0.0029264723814169005,
      "grad_norm": 0.5116732716560364,
      "learning_rate": 6e-05,
      "loss": 0.8429,
      "step": 6
    },
    {
      "epoch": 0.003414217778319717,
      "grad_norm": 0.54510098695755,
      "learning_rate": 7e-05,
      "loss": 0.8155,
      "step": 7
    },
    {
      "epoch": 0.003901963175222534,
      "grad_norm": 0.497958242893219,
      "learning_rate": 8e-05,
      "loss": 0.9446,
      "step": 8
    },
    {
      "epoch": 0.0043897085721253505,
      "grad_norm": 0.5095407366752625,
      "learning_rate": 9e-05,
      "loss": 0.7652,
      "step": 9
    },
    {
      "epoch": 0.004877453969028167,
      "grad_norm": 0.6286997199058533,
      "learning_rate": 0.0001,
      "loss": 0.8051,
      "step": 10
    },
    {
      "epoch": 0.005365199365930984,
      "grad_norm": 0.551766037940979,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.84,
      "step": 11
    },
    {
      "epoch": 0.005852944762833801,
      "grad_norm": 0.48569273948669434,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.7634,
      "step": 12
    },
    {
      "epoch": 0.0063406901597366176,
      "grad_norm": 0.5907832980155945,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.8695,
      "step": 13
    },
    {
      "epoch": 0.006828435556639434,
      "grad_norm": 0.5869553089141846,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.7659,
      "step": 14
    },
    {
      "epoch": 0.007316180953542251,
      "grad_norm": 0.5571699142456055,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.7572,
      "step": 15
    },
    {
      "epoch": 0.007803926350445068,
      "grad_norm": 0.682612419128418,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.7622,
      "step": 16
    },
    {
      "epoch": 0.008291671747347884,
      "grad_norm": 0.6647069454193115,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.8033,
      "step": 17
    },
    {
      "epoch": 0.008779417144250701,
      "grad_norm": 0.7218847870826721,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.749,
      "step": 18
    },
    {
      "epoch": 0.009267162541153518,
      "grad_norm": 0.6879798173904419,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.6535,
      "step": 19
    },
    {
      "epoch": 0.009754907938056334,
      "grad_norm": 0.6669095158576965,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.6185,
      "step": 20
    },
    {
      "epoch": 0.010242653334959152,
      "grad_norm": 0.7336055040359497,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.7455,
      "step": 21
    },
    {
      "epoch": 0.010730398731861967,
      "grad_norm": 0.7467696070671082,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.6521,
      "step": 22
    },
    {
      "epoch": 0.011218144128764785,
      "grad_norm": 0.7632023096084595,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.7245,
      "step": 23
    },
    {
      "epoch": 0.011705889525667602,
      "grad_norm": 0.8390482068061829,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.7136,
      "step": 24
    },
    {
      "epoch": 0.012193634922570418,
      "grad_norm": 0.8675934076309204,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.6735,
      "step": 25
    },
    {
      "epoch": 0.012681380319473235,
      "grad_norm": 0.9683317542076111,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.7933,
      "step": 26
    },
    {
      "epoch": 0.013169125716376053,
      "grad_norm": 1.026005744934082,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.8079,
      "step": 27
    },
    {
      "epoch": 0.013656871113278868,
      "grad_norm": 1.0004651546478271,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.7579,
      "step": 28
    },
    {
      "epoch": 0.014144616510181686,
      "grad_norm": 0.9923139214515686,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.6652,
      "step": 29
    },
    {
      "epoch": 0.014632361907084501,
      "grad_norm": 1.1677155494689941,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.7852,
      "step": 30
    },
    {
      "epoch": 0.015120107303987319,
      "grad_norm": 1.1109479665756226,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.7314,
      "step": 31
    },
    {
      "epoch": 0.015607852700890136,
      "grad_norm": 1.178887963294983,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.6344,
      "step": 32
    },
    {
      "epoch": 0.016095598097792953,
      "grad_norm": 1.1039280891418457,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.8052,
      "step": 33
    },
    {
      "epoch": 0.016583343494695767,
      "grad_norm": 0.9677231907844543,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.6957,
      "step": 34
    },
    {
      "epoch": 0.017071088891598585,
      "grad_norm": 1.3303396701812744,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.7921,
      "step": 35
    },
    {
      "epoch": 0.017558834288501402,
      "grad_norm": 1.3315911293029785,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.8033,
      "step": 36
    },
    {
      "epoch": 0.01804657968540422,
      "grad_norm": 1.4298336505889893,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.8131,
      "step": 37
    },
    {
      "epoch": 0.018534325082307037,
      "grad_norm": 1.2538775205612183,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.7601,
      "step": 38
    },
    {
      "epoch": 0.01902207047920985,
      "grad_norm": 1.2895811796188354,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.7014,
      "step": 39
    },
    {
      "epoch": 0.01950981587611267,
      "grad_norm": 1.301110863685608,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.7467,
      "step": 40
    },
    {
      "epoch": 0.019997561273015486,
      "grad_norm": 1.4002180099487305,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.7049,
      "step": 41
    },
    {
      "epoch": 0.020485306669918303,
      "grad_norm": 1.42429518699646,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.6995,
      "step": 42
    },
    {
      "epoch": 0.02097305206682112,
      "grad_norm": 1.5314632654190063,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.6996,
      "step": 43
    },
    {
      "epoch": 0.021460797463723934,
      "grad_norm": 1.3588933944702148,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.6915,
      "step": 44
    },
    {
      "epoch": 0.021948542860626752,
      "grad_norm": 1.8157392740249634,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.7544,
      "step": 45
    },
    {
      "epoch": 0.02243628825752957,
      "grad_norm": 1.422425389289856,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.665,
      "step": 46
    },
    {
      "epoch": 0.022924033654432387,
      "grad_norm": 1.61789870262146,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.7163,
      "step": 47
    },
    {
      "epoch": 0.023411779051335204,
      "grad_norm": 1.9989192485809326,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8351,
      "step": 48
    },
    {
      "epoch": 0.02389952444823802,
      "grad_norm": 1.481856346130371,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.4612,
      "step": 49
    },
    {
      "epoch": 0.024387269845140835,
      "grad_norm": 5.016469478607178,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.2368,
      "step": 50
    },
    {
      "epoch": 0.024387269845140835,
      "eval_loss": 0.7829228043556213,
      "eval_runtime": 251.0575,
      "eval_samples_per_second": 13.754,
      "eval_steps_per_second": 3.441,
      "step": 50
    },
    {
      "epoch": 0.024875015242043653,
      "grad_norm": 0.5631384253501892,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.8365,
      "step": 51
    },
    {
      "epoch": 0.02536276063894647,
      "grad_norm": 0.4840724766254425,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.8109,
      "step": 52
    },
    {
      "epoch": 0.025850506035849288,
      "grad_norm": 0.42858225107192993,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.8418,
      "step": 53
    },
    {
      "epoch": 0.026338251432752105,
      "grad_norm": 0.3773359954357147,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.7861,
      "step": 54
    },
    {
      "epoch": 0.02682599682965492,
      "grad_norm": 0.35703587532043457,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.7623,
      "step": 55
    },
    {
      "epoch": 0.027313742226557736,
      "grad_norm": 0.388830304145813,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.7697,
      "step": 56
    },
    {
      "epoch": 0.027801487623460554,
      "grad_norm": 0.4029677212238312,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.8793,
      "step": 57
    },
    {
      "epoch": 0.02828923302036337,
      "grad_norm": 0.4202454388141632,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.7603,
      "step": 58
    },
    {
      "epoch": 0.02877697841726619,
      "grad_norm": 0.4346356689929962,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.7832,
      "step": 59
    },
    {
      "epoch": 0.029264723814169002,
      "grad_norm": 0.4237990081310272,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.7074,
      "step": 60
    },
    {
      "epoch": 0.02975246921107182,
      "grad_norm": 0.4588177502155304,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.6918,
      "step": 61
    },
    {
      "epoch": 0.030240214607974637,
      "grad_norm": 0.48189812898635864,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.8579,
      "step": 62
    },
    {
      "epoch": 0.030727960004877455,
      "grad_norm": 0.4455983638763428,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.5964,
      "step": 63
    },
    {
      "epoch": 0.031215705401780272,
      "grad_norm": 0.45201095938682556,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.7495,
      "step": 64
    },
    {
      "epoch": 0.031703450798683086,
      "grad_norm": 0.5913598537445068,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.7466,
      "step": 65
    },
    {
      "epoch": 0.03219119619558591,
      "grad_norm": 0.558763861656189,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.6726,
      "step": 66
    },
    {
      "epoch": 0.03267894159248872,
      "grad_norm": 0.5548415184020996,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.6972,
      "step": 67
    },
    {
      "epoch": 0.033166686989391535,
      "grad_norm": 0.5588158369064331,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.7348,
      "step": 68
    },
    {
      "epoch": 0.033654432386294356,
      "grad_norm": 0.565741240978241,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.6659,
      "step": 69
    },
    {
      "epoch": 0.03414217778319717,
      "grad_norm": 0.557705819606781,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.5816,
      "step": 70
    },
    {
      "epoch": 0.03462992318009999,
      "grad_norm": 0.6664299368858337,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.6496,
      "step": 71
    },
    {
      "epoch": 0.035117668577002804,
      "grad_norm": 0.6529439687728882,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.6415,
      "step": 72
    },
    {
      "epoch": 0.03560541397390562,
      "grad_norm": 0.6623764634132385,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.5984,
      "step": 73
    },
    {
      "epoch": 0.03609315937080844,
      "grad_norm": 0.7059494256973267,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.631,
      "step": 74
    },
    {
      "epoch": 0.03658090476771125,
      "grad_norm": 0.7974410653114319,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.7556,
      "step": 75
    },
    {
      "epoch": 0.037068650164614074,
      "grad_norm": 0.8475507497787476,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.6946,
      "step": 76
    },
    {
      "epoch": 0.03755639556151689,
      "grad_norm": 0.9229975342750549,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.6986,
      "step": 77
    },
    {
      "epoch": 0.0380441409584197,
      "grad_norm": 1.0926481485366821,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.8234,
      "step": 78
    },
    {
      "epoch": 0.03853188635532252,
      "grad_norm": 1.0317264795303345,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.7751,
      "step": 79
    },
    {
      "epoch": 0.03901963175222534,
      "grad_norm": 1.0278832912445068,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.5828,
      "step": 80
    },
    {
      "epoch": 0.03950737714912816,
      "grad_norm": 1.0799914598464966,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7043,
      "step": 81
    },
    {
      "epoch": 0.03999512254603097,
      "grad_norm": 1.2069917917251587,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.7712,
      "step": 82
    },
    {
      "epoch": 0.040482867942933785,
      "grad_norm": 1.0386675596237183,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.6799,
      "step": 83
    },
    {
      "epoch": 0.040970613339836606,
      "grad_norm": 1.0302294492721558,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.6263,
      "step": 84
    },
    {
      "epoch": 0.04145835873673942,
      "grad_norm": 1.1998454332351685,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.753,
      "step": 85
    },
    {
      "epoch": 0.04194610413364224,
      "grad_norm": 1.2848238945007324,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8633,
      "step": 86
    },
    {
      "epoch": 0.042433849530545055,
      "grad_norm": 1.159552812576294,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.7037,
      "step": 87
    },
    {
      "epoch": 0.04292159492744787,
      "grad_norm": 1.185767650604248,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.6602,
      "step": 88
    },
    {
      "epoch": 0.04340934032435069,
      "grad_norm": 1.153672456741333,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.722,
      "step": 89
    },
    {
      "epoch": 0.043897085721253504,
      "grad_norm": 1.3746973276138306,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.7243,
      "step": 90
    },
    {
      "epoch": 0.044384831118156325,
      "grad_norm": 1.162945032119751,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.6855,
      "step": 91
    },
    {
      "epoch": 0.04487257651505914,
      "grad_norm": 1.436776876449585,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.7705,
      "step": 92
    },
    {
      "epoch": 0.04536032191196195,
      "grad_norm": 1.14664626121521,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.6167,
      "step": 93
    },
    {
      "epoch": 0.04584806730886477,
      "grad_norm": 1.2447847127914429,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.6369,
      "step": 94
    },
    {
      "epoch": 0.04633581270576759,
      "grad_norm": 1.4392436742782593,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.6753,
      "step": 95
    },
    {
      "epoch": 0.04682355810267041,
      "grad_norm": 1.3012615442276,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.5964,
      "step": 96
    },
    {
      "epoch": 0.04731130349957322,
      "grad_norm": 1.672782063484192,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.7482,
      "step": 97
    },
    {
      "epoch": 0.04779904889647604,
      "grad_norm": 1.9180303812026978,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.7675,
      "step": 98
    },
    {
      "epoch": 0.04828679429337886,
      "grad_norm": 2.4247143268585205,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.9774,
      "step": 99
    },
    {
      "epoch": 0.04877453969028167,
      "grad_norm": 1.9715301990509033,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.6453,
      "step": 100
    },
    {
      "epoch": 0.04877453969028167,
      "eval_loss": 0.7220537066459656,
      "eval_runtime": 252.6341,
      "eval_samples_per_second": 13.668,
      "eval_steps_per_second": 3.42,
      "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": 1.4609906241896448e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}