{
  "best_metric": 2.122905731201172,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.010127607859023698,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010127607859023699,
      "grad_norm": 31.294456481933594,
      "learning_rate": 1e-05,
      "loss": 5.6035,
      "step": 1
    },
    {
      "epoch": 0.00010127607859023699,
      "eval_loss": 6.345576286315918,
      "eval_runtime": 1564.5156,
      "eval_samples_per_second": 10.629,
      "eval_steps_per_second": 2.658,
      "step": 1
    },
    {
      "epoch": 0.00020255215718047398,
      "grad_norm": 23.02219581604004,
      "learning_rate": 2e-05,
      "loss": 5.6016,
      "step": 2
    },
    {
      "epoch": 0.00030382823577071097,
      "grad_norm": 39.37947463989258,
      "learning_rate": 3e-05,
      "loss": 5.0194,
      "step": 3
    },
    {
      "epoch": 0.00040510431436094796,
      "grad_norm": 21.45987892150879,
      "learning_rate": 4e-05,
      "loss": 4.1124,
      "step": 4
    },
    {
      "epoch": 0.0005063803929511849,
      "grad_norm": 55.5565185546875,
      "learning_rate": 5e-05,
      "loss": 3.3009,
      "step": 5
    },
    {
      "epoch": 0.0006076564715414219,
      "grad_norm": 29.301273345947266,
      "learning_rate": 6e-05,
      "loss": 2.5402,
      "step": 6
    },
    {
      "epoch": 0.0007089325501316589,
      "grad_norm": 12.073786735534668,
      "learning_rate": 7e-05,
      "loss": 1.7624,
      "step": 7
    },
    {
      "epoch": 0.0008102086287218959,
      "grad_norm": 15.226734161376953,
      "learning_rate": 8e-05,
      "loss": 1.6079,
      "step": 8
    },
    {
      "epoch": 0.0009114847073121329,
      "grad_norm": 9.022705078125,
      "learning_rate": 9e-05,
      "loss": 1.5372,
      "step": 9
    },
    {
      "epoch": 0.0010127607859023698,
      "grad_norm": 17.463788986206055,
      "learning_rate": 0.0001,
      "loss": 1.6454,
      "step": 10
    },
    {
      "epoch": 0.001114036864492607,
      "grad_norm": 9.068487167358398,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.1799,
      "step": 11
    },
    {
      "epoch": 0.0012153129430828439,
      "grad_norm": 6.660534858703613,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.3202,
      "step": 12
    },
    {
      "epoch": 0.0013165890216730808,
      "grad_norm": 5.885499000549316,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.4402,
      "step": 13
    },
    {
      "epoch": 0.0014178651002633178,
      "grad_norm": 6.3276686668396,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.4109,
      "step": 14
    },
    {
      "epoch": 0.0015191411788535547,
      "grad_norm": 6.11013126373291,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.5649,
      "step": 15
    },
    {
      "epoch": 0.0016204172574437918,
      "grad_norm": 7.530121326446533,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.5869,
      "step": 16
    },
    {
      "epoch": 0.0017216933360340288,
      "grad_norm": 4.815801620483398,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.3504,
      "step": 17
    },
    {
      "epoch": 0.0018229694146242657,
      "grad_norm": 5.649615287780762,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.4349,
      "step": 18
    },
    {
      "epoch": 0.0019242454932145027,
      "grad_norm": 5.345456123352051,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.3531,
      "step": 19
    },
    {
      "epoch": 0.0020255215718047396,
      "grad_norm": 5.225619316101074,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.7181,
      "step": 20
    },
    {
      "epoch": 0.0021267976503949767,
      "grad_norm": 8.340807914733887,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.7208,
      "step": 21
    },
    {
      "epoch": 0.002228073728985214,
      "grad_norm": 5.898898124694824,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.6386,
      "step": 22
    },
    {
      "epoch": 0.0023293498075754506,
      "grad_norm": 5.504738807678223,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.5145,
      "step": 23
    },
    {
      "epoch": 0.0024306258861656878,
      "grad_norm": 7.0861053466796875,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.8006,
      "step": 24
    },
    {
      "epoch": 0.0025319019647559245,
      "grad_norm": 5.042062282562256,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.575,
      "step": 25
    },
    {
      "epoch": 0.0026331780433461616,
      "grad_norm": 6.518356800079346,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.6954,
      "step": 26
    },
    {
      "epoch": 0.002734454121936399,
      "grad_norm": 6.192532539367676,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.5781,
      "step": 27
    },
    {
      "epoch": 0.0028357302005266355,
      "grad_norm": 4.853874206542969,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.6337,
      "step": 28
    },
    {
      "epoch": 0.0029370062791168727,
      "grad_norm": 5.8297319412231445,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.6601,
      "step": 29
    },
    {
      "epoch": 0.0030382823577071094,
      "grad_norm": 5.028331279754639,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.6467,
      "step": 30
    },
    {
      "epoch": 0.0031395584362973465,
      "grad_norm": 6.4670491218566895,
      "learning_rate": 9.701596950580806e-05,
      "loss": 2.1582,
      "step": 31
    },
    {
      "epoch": 0.0032408345148875837,
      "grad_norm": 6.356573104858398,
      "learning_rate": 9.672822322997305e-05,
      "loss": 2.1429,
      "step": 32
    },
    {
      "epoch": 0.0033421105934778204,
      "grad_norm": 5.429017066955566,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.9339,
      "step": 33
    },
    {
      "epoch": 0.0034433866720680576,
      "grad_norm": 4.136333465576172,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.7328,
      "step": 34
    },
    {
      "epoch": 0.0035446627506582947,
      "grad_norm": 3.894758462905884,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.6804,
      "step": 35
    },
    {
      "epoch": 0.0036459388292485314,
      "grad_norm": 3.3863894939422607,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.5503,
      "step": 36
    },
    {
      "epoch": 0.0037472149078387686,
      "grad_norm": 3.318730592727661,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.7207,
      "step": 37
    },
    {
      "epoch": 0.0038484909864290053,
      "grad_norm": 5.84458065032959,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.3863,
      "step": 38
    },
    {
      "epoch": 0.0039497670650192425,
      "grad_norm": 8.405301094055176,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.7637,
      "step": 39
    },
    {
      "epoch": 0.004051043143609479,
      "grad_norm": 8.692002296447754,
      "learning_rate": 9.397368756032445e-05,
      "loss": 3.1337,
      "step": 40
    },
    {
      "epoch": 0.004152319222199717,
      "grad_norm": 10.421037673950195,
      "learning_rate": 9.357421218136386e-05,
      "loss": 2.7647,
      "step": 41
    },
    {
      "epoch": 0.0042535953007899535,
      "grad_norm": 5.511323928833008,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.4226,
      "step": 42
    },
    {
      "epoch": 0.00435487137938019,
      "grad_norm": 4.926803112030029,
      "learning_rate": 9.273963562927695e-05,
      "loss": 2.3849,
      "step": 43
    },
    {
      "epoch": 0.004456147457970428,
      "grad_norm": 4.43251895904541,
      "learning_rate": 9.230476262104677e-05,
      "loss": 2.2686,
      "step": 44
    },
    {
      "epoch": 0.0045574235365606645,
      "grad_norm": 5.309133529663086,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.2997,
      "step": 45
    },
    {
      "epoch": 0.004658699615150901,
      "grad_norm": 6.84977912902832,
      "learning_rate": 9.140044155740101e-05,
      "loss": 2.7412,
      "step": 46
    },
    {
      "epoch": 0.004759975693741138,
      "grad_norm": 6.702414035797119,
      "learning_rate": 9.093124073433463e-05,
      "loss": 2.5964,
      "step": 47
    },
    {
      "epoch": 0.0048612517723313755,
      "grad_norm": 5.800580024719238,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.7281,
      "step": 48
    },
    {
      "epoch": 0.004962527850921612,
      "grad_norm": 4.461594104766846,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.4342,
      "step": 49
    },
    {
      "epoch": 0.005063803929511849,
      "grad_norm": 5.537498950958252,
      "learning_rate": 8.945702546981969e-05,
      "loss": 2.6038,
      "step": 50
    },
    {
      "epoch": 0.005063803929511849,
      "eval_loss": 2.2712900638580322,
      "eval_runtime": 1571.7641,
      "eval_samples_per_second": 10.58,
      "eval_steps_per_second": 2.645,
      "step": 50
    },
    {
      "epoch": 0.0051650800081020866,
      "grad_norm": 11.62936019897461,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.9625,
      "step": 51
    },
    {
      "epoch": 0.005266356086692323,
      "grad_norm": 8.94434928894043,
      "learning_rate": 8.842005554284296e-05,
      "loss": 2.1033,
      "step": 52
    },
    {
      "epoch": 0.00536763216528256,
      "grad_norm": 6.63067626953125,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.4185,
      "step": 53
    },
    {
      "epoch": 0.005468908243872798,
      "grad_norm": 5.48298454284668,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.2189,
      "step": 54
    },
    {
      "epoch": 0.005570184322463034,
      "grad_norm": 5.248403549194336,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.4783,
      "step": 55
    },
    {
      "epoch": 0.005671460401053271,
      "grad_norm": 3.091050386428833,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.1947,
      "step": 56
    },
    {
      "epoch": 0.005772736479643509,
      "grad_norm": 3.561055898666382,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.2281,
      "step": 57
    },
    {
      "epoch": 0.005874012558233745,
      "grad_norm": 3.302882432937622,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.5576,
      "step": 58
    },
    {
      "epoch": 0.005975288636823982,
      "grad_norm": 3.763090133666992,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.8619,
      "step": 59
    },
    {
      "epoch": 0.006076564715414219,
      "grad_norm": 4.980674743652344,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.2353,
      "step": 60
    },
    {
      "epoch": 0.006177840794004456,
      "grad_norm": 3.831450939178467,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.069,
      "step": 61
    },
    {
      "epoch": 0.006279116872594693,
      "grad_norm": 10.198344230651855,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.1834,
      "step": 62
    },
    {
      "epoch": 0.00638039295118493,
      "grad_norm": 4.180304050445557,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.115,
      "step": 63
    },
    {
      "epoch": 0.006481669029775167,
      "grad_norm": 3.688276767730713,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.0416,
      "step": 64
    },
    {
      "epoch": 0.006582945108365404,
      "grad_norm": 3.9528965950012207,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.2017,
      "step": 65
    },
    {
      "epoch": 0.006684221186955641,
      "grad_norm": 3.0600063800811768,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.8048,
      "step": 66
    },
    {
      "epoch": 0.006785497265545878,
      "grad_norm": 5.901766777038574,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.0497,
      "step": 67
    },
    {
      "epoch": 0.006886773344136115,
      "grad_norm": 6.350919246673584,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.1079,
      "step": 68
    },
    {
      "epoch": 0.006988049422726352,
      "grad_norm": 3.647548198699951,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.3041,
      "step": 69
    },
    {
      "epoch": 0.007089325501316589,
      "grad_norm": 4.118706226348877,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.333,
      "step": 70
    },
    {
      "epoch": 0.007190601579906826,
      "grad_norm": 6.582793712615967,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.6024,
      "step": 71
    },
    {
      "epoch": 0.007291877658497063,
      "grad_norm": 5.287528991699219,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.3089,
      "step": 72
    },
    {
      "epoch": 0.0073931537370873,
      "grad_norm": 4.048415660858154,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.5625,
      "step": 73
    },
    {
      "epoch": 0.007494429815677537,
      "grad_norm": 10.162145614624023,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.4619,
      "step": 74
    },
    {
      "epoch": 0.007595705894267774,
      "grad_norm": 3.710768699645996,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.5656,
      "step": 75
    },
    {
      "epoch": 0.007696981972858011,
      "grad_norm": 3.8244152069091797,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.8309,
      "step": 76
    },
    {
      "epoch": 0.007798258051448248,
      "grad_norm": 4.590068817138672,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.3288,
      "step": 77
    },
    {
      "epoch": 0.007899534130038485,
      "grad_norm": 3.5102505683898926,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.3495,
      "step": 78
    },
    {
      "epoch": 0.008000810208628722,
      "grad_norm": 3.706644296646118,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.3365,
      "step": 79
    },
    {
      "epoch": 0.008102086287218958,
      "grad_norm": 4.158026695251465,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.7593,
      "step": 80
    },
    {
      "epoch": 0.008203362365809196,
      "grad_norm": 4.4503173828125,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.9636,
      "step": 81
    },
    {
      "epoch": 0.008304638444399434,
      "grad_norm": 3.916571855545044,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.7637,
      "step": 82
    },
    {
      "epoch": 0.00840591452298967,
      "grad_norm": 3.083988904953003,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.5923,
      "step": 83
    },
    {
      "epoch": 0.008507190601579907,
      "grad_norm": 2.566749095916748,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.3581,
      "step": 84
    },
    {
      "epoch": 0.008608466680170145,
      "grad_norm": 3.232682466506958,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.4974,
      "step": 85
    },
    {
      "epoch": 0.00870974275876038,
      "grad_norm": 4.013308048248291,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.8144,
      "step": 86
    },
    {
      "epoch": 0.008811018837350618,
      "grad_norm": 2.443804979324341,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.4845,
      "step": 87
    },
    {
      "epoch": 0.008912294915940856,
      "grad_norm": 3.423102617263794,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.9203,
      "step": 88
    },
    {
      "epoch": 0.009013570994531091,
      "grad_norm": 4.804714679718018,
      "learning_rate": 6.307399704769099e-05,
      "loss": 2.4277,
      "step": 89
    },
    {
      "epoch": 0.009114847073121329,
      "grad_norm": 4.962749004364014,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.5357,
      "step": 90
    },
    {
      "epoch": 0.009216123151711565,
      "grad_norm": 6.186339378356934,
      "learning_rate": 6.147119600233758e-05,
      "loss": 2.6825,
      "step": 91
    },
    {
      "epoch": 0.009317399230301802,
      "grad_norm": 3.8425121307373047,
      "learning_rate": 6.066498153718735e-05,
      "loss": 2.2824,
      "step": 92
    },
    {
      "epoch": 0.00941867530889204,
      "grad_norm": 5.106661319732666,
      "learning_rate": 5.985585137257401e-05,
      "loss": 2.5763,
      "step": 93
    },
    {
      "epoch": 0.009519951387482276,
      "grad_norm": 3.5278234481811523,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.9765,
      "step": 94
    },
    {
      "epoch": 0.009621227466072513,
      "grad_norm": 3.7213644981384277,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 2.3297,
      "step": 95
    },
    {
      "epoch": 0.009722503544662751,
      "grad_norm": 3.549769401550293,
      "learning_rate": 5.74131823855921e-05,
      "loss": 2.2013,
      "step": 96
    },
    {
      "epoch": 0.009823779623252987,
      "grad_norm": 3.8638694286346436,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 2.3581,
      "step": 97
    },
    {
      "epoch": 0.009925055701843224,
      "grad_norm": 4.105386734008789,
      "learning_rate": 5.577423184847932e-05,
      "loss": 2.4061,
      "step": 98
    },
    {
      "epoch": 0.010026331780433462,
      "grad_norm": 6.937985420227051,
      "learning_rate": 5.495227651252315e-05,
      "loss": 2.8345,
      "step": 99
    },
    {
      "epoch": 0.010127607859023698,
      "grad_norm": 4.872765064239502,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 2.3537,
      "step": 100
    },
    {
      "epoch": 0.010127607859023698,
      "eval_loss": 2.122905731201172,
      "eval_runtime": 1571.7354,
      "eval_samples_per_second": 10.581,
      "eval_steps_per_second": 2.645,
      "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": 1.727221903392768e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}