{
  "best_metric": 6.883584976196289,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 3.03988603988604,
  "eval_steps": 25,
  "global_step": 99,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.030389363722697058,
      "grad_norm": 0.1357833743095398,
      "learning_rate": 2.5e-05,
      "loss": 6.9382,
      "step": 1
    },
    {
      "epoch": 0.030389363722697058,
      "eval_loss": 6.938218593597412,
      "eval_runtime": 0.0715,
      "eval_samples_per_second": 699.748,
      "eval_steps_per_second": 181.935,
      "step": 1
    },
    {
      "epoch": 0.060778727445394115,
      "grad_norm": 0.13408163189888,
      "learning_rate": 5e-05,
      "loss": 6.9392,
      "step": 2
    },
    {
      "epoch": 0.09116809116809117,
      "grad_norm": 0.14098231494426727,
      "learning_rate": 7.500000000000001e-05,
      "loss": 6.9395,
      "step": 3
    },
    {
      "epoch": 0.12155745489078823,
      "grad_norm": 0.1429039090871811,
      "learning_rate": 0.0001,
      "loss": 6.9391,
      "step": 4
    },
    {
      "epoch": 0.15194681861348527,
      "grad_norm": 0.13866113126277924,
      "learning_rate": 9.997539658034168e-05,
      "loss": 6.9388,
      "step": 5
    },
    {
      "epoch": 0.18233618233618235,
      "grad_norm": 0.15095753967761993,
      "learning_rate": 9.990161322484486e-05,
      "loss": 6.9363,
      "step": 6
    },
    {
      "epoch": 0.2127255460588794,
      "grad_norm": 0.16712909936904907,
      "learning_rate": 9.977873061452552e-05,
      "loss": 6.9343,
      "step": 7
    },
    {
      "epoch": 0.24311490978157646,
      "grad_norm": 0.18588651716709137,
      "learning_rate": 9.96068831197139e-05,
      "loss": 6.9333,
      "step": 8
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.13056699931621552,
      "learning_rate": 9.938625865312251e-05,
      "loss": 6.9341,
      "step": 9
    },
    {
      "epoch": 0.30389363722697055,
      "grad_norm": 0.13966338336467743,
      "learning_rate": 9.911709846436641e-05,
      "loss": 6.9323,
      "step": 10
    },
    {
      "epoch": 0.3342830009496676,
      "grad_norm": 0.1428191214799881,
      "learning_rate": 9.879969687616027e-05,
      "loss": 6.9316,
      "step": 11
    },
    {
      "epoch": 0.3646723646723647,
      "grad_norm": 0.14790380001068115,
      "learning_rate": 9.84344009624807e-05,
      "loss": 6.9306,
      "step": 12
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.15512308478355408,
      "learning_rate": 9.80216101690461e-05,
      "loss": 6.9292,
      "step": 13
    },
    {
      "epoch": 0.4254510921177588,
      "grad_norm": 0.16272898018360138,
      "learning_rate": 9.756177587652856e-05,
      "loss": 6.927,
      "step": 14
    },
    {
      "epoch": 0.45584045584045585,
      "grad_norm": 0.16427749395370483,
      "learning_rate": 9.705540090697575e-05,
      "loss": 6.9266,
      "step": 15
    },
    {
      "epoch": 0.4862298195631529,
      "grad_norm": 0.18800827860832214,
      "learning_rate": 9.650303897398232e-05,
      "loss": 6.9249,
      "step": 16
    },
    {
      "epoch": 0.51661918328585,
      "grad_norm": 0.14342306554317474,
      "learning_rate": 9.590529407721231e-05,
      "loss": 6.9271,
      "step": 17
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.14963504672050476,
      "learning_rate": 9.526281984193436e-05,
      "loss": 6.9258,
      "step": 18
    },
    {
      "epoch": 0.577397910731244,
      "grad_norm": 0.16108295321464539,
      "learning_rate": 9.4576318804292e-05,
      "loss": 6.9243,
      "step": 19
    },
    {
      "epoch": 0.6077872744539411,
      "grad_norm": 0.16339664161205292,
      "learning_rate": 9.384654164309083e-05,
      "loss": 6.9222,
      "step": 20
    },
    {
      "epoch": 0.6381766381766382,
      "grad_norm": 0.168046772480011,
      "learning_rate": 9.30742863589421e-05,
      "loss": 6.9206,
      "step": 21
    },
    {
      "epoch": 0.6685660018993352,
      "grad_norm": 0.1747824251651764,
      "learning_rate": 9.226039740166091e-05,
      "loss": 6.9185,
      "step": 22
    },
    {
      "epoch": 0.6989553656220323,
      "grad_norm": 0.18280130624771118,
      "learning_rate": 9.140576474687264e-05,
      "loss": 6.9179,
      "step": 23
    },
    {
      "epoch": 0.7293447293447294,
      "grad_norm": 0.21718308329582214,
      "learning_rate": 9.051132292283771e-05,
      "loss": 6.9149,
      "step": 24
    },
    {
      "epoch": 0.7597340930674265,
      "grad_norm": 0.16105718910694122,
      "learning_rate": 8.957804998855866e-05,
      "loss": 6.9191,
      "step": 25
    },
    {
      "epoch": 0.7597340930674265,
      "eval_loss": 6.916116714477539,
      "eval_runtime": 0.0686,
      "eval_samples_per_second": 729.3,
      "eval_steps_per_second": 189.618,
      "step": 25
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.1643819510936737,
      "learning_rate": 8.860696646428693e-05,
      "loss": 6.9186,
      "step": 26
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.1819484382867813,
      "learning_rate": 8.759913421559902e-05,
      "loss": 6.9156,
      "step": 27
    },
    {
      "epoch": 0.8509021842355176,
      "grad_norm": 0.17893028259277344,
      "learning_rate": 8.655565529226198e-05,
      "loss": 6.9141,
      "step": 28
    },
    {
      "epoch": 0.8812915479582146,
      "grad_norm": 0.18618154525756836,
      "learning_rate": 8.547767072315835e-05,
      "loss": 6.9128,
      "step": 29
    },
    {
      "epoch": 0.9116809116809117,
      "grad_norm": 0.18693046271800995,
      "learning_rate": 8.436635926858759e-05,
      "loss": 6.9101,
      "step": 30
    },
    {
      "epoch": 0.9420702754036088,
      "grad_norm": 0.1917145699262619,
      "learning_rate": 8.322293613130917e-05,
      "loss": 6.9086,
      "step": 31
    },
    {
      "epoch": 0.9724596391263058,
      "grad_norm": 0.22024141252040863,
      "learning_rate": 8.204865162773613e-05,
      "loss": 6.902,
      "step": 32
    },
    {
      "epoch": 1.01329534662868,
      "grad_norm": 0.25598573684692383,
      "learning_rate": 8.084478982073247e-05,
      "loss": 9.9181,
      "step": 33
    },
    {
      "epoch": 1.043684710351377,
      "grad_norm": 0.16839833557605743,
      "learning_rate": 7.961266711550922e-05,
      "loss": 6.8916,
      "step": 34
    },
    {
      "epoch": 1.074074074074074,
      "grad_norm": 0.17936962842941284,
      "learning_rate": 7.835363082015468e-05,
      "loss": 6.959,
      "step": 35
    },
    {
      "epoch": 1.104463437796771,
      "grad_norm": 0.18253256380558014,
      "learning_rate": 7.706905767237288e-05,
      "loss": 6.9025,
      "step": 36
    },
    {
      "epoch": 1.134852801519468,
      "grad_norm": 0.185040682554245,
      "learning_rate": 7.576035233404096e-05,
      "loss": 6.9272,
      "step": 37
    },
    {
      "epoch": 1.1652421652421652,
      "grad_norm": 0.19758865237236023,
      "learning_rate": 7.442894585523218e-05,
      "loss": 7.2086,
      "step": 38
    },
    {
      "epoch": 1.1956315289648622,
      "grad_norm": 0.1904238611459732,
      "learning_rate": 7.307629410938363e-05,
      "loss": 6.8585,
      "step": 39
    },
    {
      "epoch": 1.2260208926875593,
      "grad_norm": 0.2162361592054367,
      "learning_rate": 7.170387620131993e-05,
      "loss": 7.3381,
      "step": 40
    },
    {
      "epoch": 1.2564102564102564,
      "grad_norm": 0.17022086679935455,
      "learning_rate": 7.031319284987394e-05,
      "loss": 6.1575,
      "step": 41
    },
    {
      "epoch": 1.2867996201329535,
      "grad_norm": 0.16576489806175232,
      "learning_rate": 6.890576474687263e-05,
      "loss": 6.9278,
      "step": 42
    },
    {
      "epoch": 1.3171889838556505,
      "grad_norm": 0.16799896955490112,
      "learning_rate": 6.7483130894283e-05,
      "loss": 6.9742,
      "step": 43
    },
    {
      "epoch": 1.3475783475783476,
      "grad_norm": 0.16917121410369873,
      "learning_rate": 6.604684692133597e-05,
      "loss": 6.8591,
      "step": 44
    },
    {
      "epoch": 1.3779677113010447,
      "grad_norm": 0.16244754195213318,
      "learning_rate": 6.459848338346861e-05,
      "loss": 6.9428,
      "step": 45
    },
    {
      "epoch": 1.4083570750237417,
      "grad_norm": 0.1710527092218399,
      "learning_rate": 6.313962404494496e-05,
      "loss": 7.0195,
      "step": 46
    },
    {
      "epoch": 1.4387464387464388,
      "grad_norm": 0.1634788066148758,
      "learning_rate": 6.167186414703289e-05,
      "loss": 6.8305,
      "step": 47
    },
    {
      "epoch": 1.4691358024691357,
      "grad_norm": 0.1797107458114624,
      "learning_rate": 6.019680866363139e-05,
      "loss": 7.3825,
      "step": 48
    },
    {
      "epoch": 1.499525166191833,
      "grad_norm": 0.1428283154964447,
      "learning_rate": 5.8716070546254966e-05,
      "loss": 6.246,
      "step": 49
    },
    {
      "epoch": 1.5299145299145298,
      "grad_norm": 0.14042928814888,
      "learning_rate": 5.7231268960295e-05,
      "loss": 6.9065,
      "step": 50
    },
    {
      "epoch": 1.5299145299145298,
      "eval_loss": 6.891157627105713,
      "eval_runtime": 0.0711,
      "eval_samples_per_second": 702.839,
      "eval_steps_per_second": 182.738,
      "step": 50
    },
    {
      "epoch": 1.560303893637227,
      "grad_norm": 0.13292936980724335,
      "learning_rate": 5.574402751448614e-05,
      "loss": 6.8319,
      "step": 51
    },
    {
      "epoch": 1.590693257359924,
      "grad_norm": 0.14090725779533386,
      "learning_rate": 5.425597248551387e-05,
      "loss": 6.9562,
      "step": 52
    },
    {
      "epoch": 1.6210826210826212,
      "grad_norm": 0.13612942397594452,
      "learning_rate": 5.2768731039705e-05,
      "loss": 6.8707,
      "step": 53
    },
    {
      "epoch": 1.651471984805318,
      "grad_norm": 0.14546889066696167,
      "learning_rate": 5.128392945374505e-05,
      "loss": 7.2714,
      "step": 54
    },
    {
      "epoch": 1.6818613485280152,
      "grad_norm": 0.13168302178382874,
      "learning_rate": 4.980319133636863e-05,
      "loss": 6.7413,
      "step": 55
    },
    {
      "epoch": 1.7122507122507122,
      "grad_norm": 0.14720255136489868,
      "learning_rate": 4.83281358529671e-05,
      "loss": 7.3065,
      "step": 56
    },
    {
      "epoch": 1.7426400759734093,
      "grad_norm": 0.12005792558193207,
      "learning_rate": 4.686037595505507e-05,
      "loss": 6.2386,
      "step": 57
    },
    {
      "epoch": 1.7730294396961064,
      "grad_norm": 0.11440925300121307,
      "learning_rate": 4.54015166165314e-05,
      "loss": 6.8224,
      "step": 58
    },
    {
      "epoch": 1.8034188034188035,
      "grad_norm": 0.11298578232526779,
      "learning_rate": 4.395315307866405e-05,
      "loss": 6.9501,
      "step": 59
    },
    {
      "epoch": 1.8338081671415005,
      "grad_norm": 0.11483923345804214,
      "learning_rate": 4.2516869105717004e-05,
      "loss": 6.957,
      "step": 60
    },
    {
      "epoch": 1.8641975308641974,
      "grad_norm": 0.11452340334653854,
      "learning_rate": 4.109423525312738e-05,
      "loss": 6.8562,
      "step": 61
    },
    {
      "epoch": 1.8945868945868947,
      "grad_norm": 0.12229608744382858,
      "learning_rate": 3.968680715012606e-05,
      "loss": 7.0527,
      "step": 62
    },
    {
      "epoch": 1.9249762583095915,
      "grad_norm": 0.11904427409172058,
      "learning_rate": 3.829612379868006e-05,
      "loss": 6.8479,
      "step": 63
    },
    {
      "epoch": 1.9553656220322888,
      "grad_norm": 0.12863321602344513,
      "learning_rate": 3.692370589061639e-05,
      "loss": 7.3454,
      "step": 64
    },
    {
      "epoch": 1.9857549857549857,
      "grad_norm": 0.13798318803310394,
      "learning_rate": 3.557105414476782e-05,
      "loss": 8.6353,
      "step": 65
    },
    {
      "epoch": 2.02659069325736,
      "grad_norm": 0.10759957879781723,
      "learning_rate": 3.423964766595906e-05,
      "loss": 7.4987,
      "step": 66
    },
    {
      "epoch": 2.056980056980057,
      "grad_norm": 0.10079392790794373,
      "learning_rate": 3.293094232762715e-05,
      "loss": 6.8864,
      "step": 67
    },
    {
      "epoch": 2.087369420702754,
      "grad_norm": 0.09840377420186996,
      "learning_rate": 3.164636917984534e-05,
      "loss": 6.8948,
      "step": 68
    },
    {
      "epoch": 2.117758784425451,
      "grad_norm": 0.09733422100543976,
      "learning_rate": 3.0387332884490805e-05,
      "loss": 6.8686,
      "step": 69
    },
    {
      "epoch": 2.148148148148148,
      "grad_norm": 0.10290233790874481,
      "learning_rate": 2.9155210179267546e-05,
      "loss": 6.9335,
      "step": 70
    },
    {
      "epoch": 2.178537511870845,
      "grad_norm": 0.10776888579130173,
      "learning_rate": 2.7951348372263875e-05,
      "loss": 7.0476,
      "step": 71
    },
    {
      "epoch": 2.208926875593542,
      "grad_norm": 0.10383031517267227,
      "learning_rate": 2.677706386869083e-05,
      "loss": 6.762,
      "step": 72
    },
    {
      "epoch": 2.2393162393162394,
      "grad_norm": 0.13066378235816956,
      "learning_rate": 2.5633640731412412e-05,
      "loss": 7.2873,
      "step": 73
    },
    {
      "epoch": 2.269705603038936,
      "grad_norm": 0.0905405804514885,
      "learning_rate": 2.4522329276841663e-05,
      "loss": 6.4179,
      "step": 74
    },
    {
      "epoch": 2.3000949667616335,
      "grad_norm": 0.09294768422842026,
      "learning_rate": 2.3444344707738015e-05,
      "loss": 6.8739,
      "step": 75
    },
    {
      "epoch": 2.3000949667616335,
      "eval_loss": 6.883584976196289,
      "eval_runtime": 0.069,
      "eval_samples_per_second": 724.277,
      "eval_steps_per_second": 188.312,
      "step": 75
    },
    {
      "epoch": 2.3304843304843303,
      "grad_norm": 0.09302153438329697,
      "learning_rate": 2.2400865784401e-05,
      "loss": 6.88,
      "step": 76
    },
    {
      "epoch": 2.3608736942070276,
      "grad_norm": 0.09038078039884567,
      "learning_rate": 2.1393033535713093e-05,
      "loss": 6.9026,
      "step": 77
    },
    {
      "epoch": 2.3912630579297245,
      "grad_norm": 0.09370548278093338,
      "learning_rate": 2.0421950011441354e-05,
      "loss": 6.9711,
      "step": 78
    },
    {
      "epoch": 2.421652421652422,
      "grad_norm": 0.09348244965076447,
      "learning_rate": 1.9488677077162295e-05,
      "loss": 6.8911,
      "step": 79
    },
    {
      "epoch": 2.4520417853751186,
      "grad_norm": 0.09923094511032104,
      "learning_rate": 1.8594235253127375e-05,
      "loss": 6.91,
      "step": 80
    },
    {
      "epoch": 2.482431149097816,
      "grad_norm": 0.12247008085250854,
      "learning_rate": 1.77396025983391e-05,
      "loss": 7.1999,
      "step": 81
    },
    {
      "epoch": 2.5128205128205128,
      "grad_norm": 0.08389267325401306,
      "learning_rate": 1.6925713641057904e-05,
      "loss": 6.4161,
      "step": 82
    },
    {
      "epoch": 2.5432098765432096,
      "grad_norm": 0.08750791847705841,
      "learning_rate": 1.6153458356909176e-05,
      "loss": 6.8745,
      "step": 83
    },
    {
      "epoch": 2.573599240265907,
      "grad_norm": 0.08594594895839691,
      "learning_rate": 1.5423681195707997e-05,
      "loss": 6.9089,
      "step": 84
    },
    {
      "epoch": 2.603988603988604,
      "grad_norm": 0.09055335074663162,
      "learning_rate": 1.4737180158065644e-05,
      "loss": 6.8928,
      "step": 85
    },
    {
      "epoch": 2.634377967711301,
      "grad_norm": 0.09193196147680283,
      "learning_rate": 1.4094705922787687e-05,
      "loss": 6.8778,
      "step": 86
    },
    {
      "epoch": 2.664767331433998,
      "grad_norm": 0.09884382039308548,
      "learning_rate": 1.3496961026017687e-05,
      "loss": 7.1493,
      "step": 87
    },
    {
      "epoch": 2.695156695156695,
      "grad_norm": 0.09690383821725845,
      "learning_rate": 1.2944599093024267e-05,
      "loss": 6.6664,
      "step": 88
    },
    {
      "epoch": 2.725546058879392,
      "grad_norm": 0.12492170184850693,
      "learning_rate": 1.2438224123471442e-05,
      "loss": 7.3624,
      "step": 89
    },
    {
      "epoch": 2.7559354226020893,
      "grad_norm": 0.08144571632146835,
      "learning_rate": 1.1978389830953907e-05,
      "loss": 6.2938,
      "step": 90
    },
    {
      "epoch": 2.786324786324786,
      "grad_norm": 0.08170946687459946,
      "learning_rate": 1.1565599037519316e-05,
      "loss": 6.8895,
      "step": 91
    },
    {
      "epoch": 2.8167141500474835,
      "grad_norm": 0.08227747678756714,
      "learning_rate": 1.1200303123839742e-05,
      "loss": 6.9282,
      "step": 92
    },
    {
      "epoch": 2.8471035137701803,
      "grad_norm": 0.08924560993909836,
      "learning_rate": 1.088290153563358e-05,
      "loss": 6.8725,
      "step": 93
    },
    {
      "epoch": 2.8774928774928776,
      "grad_norm": 0.09153356403112411,
      "learning_rate": 1.0613741346877497e-05,
      "loss": 6.9255,
      "step": 94
    },
    {
      "epoch": 2.9078822412155745,
      "grad_norm": 0.09689171612262726,
      "learning_rate": 1.0393116880286118e-05,
      "loss": 7.0523,
      "step": 95
    },
    {
      "epoch": 2.9382716049382713,
      "grad_norm": 0.09343353658914566,
      "learning_rate": 1.0221269385474488e-05,
      "loss": 6.7672,
      "step": 96
    },
    {
      "epoch": 2.9686609686609686,
      "grad_norm": 0.1134086549282074,
      "learning_rate": 1.0098386775155147e-05,
      "loss": 7.2979,
      "step": 97
    },
    {
      "epoch": 3.009496676163343,
      "grad_norm": 0.11922775208950043,
      "learning_rate": 1.0024603419658329e-05,
      "loss": 9.4261,
      "step": 98
    },
    {
      "epoch": 3.03988603988604,
      "grad_norm": 0.08165828138589859,
      "learning_rate": 1e-05,
      "loss": 6.7951,
      "step": 99
    }
  ],
  "logging_steps": 1,
  "max_steps": 99,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 11297795604480.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}