{
  "best_metric": 0.6698483228683472,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.7339449541284404,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007339449541284404,
      "grad_norm": 1.2576438188552856,
      "learning_rate": 1e-05,
      "loss": 0.9112,
      "step": 1
    },
    {
      "epoch": 0.007339449541284404,
      "eval_loss": 1.086421012878418,
      "eval_runtime": 7.3885,
      "eval_samples_per_second": 31.129,
      "eval_steps_per_second": 7.85,
      "step": 1
    },
    {
      "epoch": 0.014678899082568808,
      "grad_norm": 1.320379614830017,
      "learning_rate": 2e-05,
      "loss": 0.9991,
      "step": 2
    },
    {
      "epoch": 0.022018348623853212,
      "grad_norm": 1.2803949117660522,
      "learning_rate": 3e-05,
      "loss": 1.0084,
      "step": 3
    },
    {
      "epoch": 0.029357798165137616,
      "grad_norm": 1.0986052751541138,
      "learning_rate": 4e-05,
      "loss": 0.8749,
      "step": 4
    },
    {
      "epoch": 0.03669724770642202,
      "grad_norm": 0.9205357432365417,
      "learning_rate": 5e-05,
      "loss": 0.9294,
      "step": 5
    },
    {
      "epoch": 0.044036697247706424,
      "grad_norm": 0.8968833684921265,
      "learning_rate": 6e-05,
      "loss": 0.6873,
      "step": 6
    },
    {
      "epoch": 0.05137614678899083,
      "grad_norm": 0.7835147976875305,
      "learning_rate": 7e-05,
      "loss": 0.8424,
      "step": 7
    },
    {
      "epoch": 0.05871559633027523,
      "grad_norm": 0.638231098651886,
      "learning_rate": 8e-05,
      "loss": 0.8373,
      "step": 8
    },
    {
      "epoch": 0.06605504587155964,
      "grad_norm": 0.8740332722663879,
      "learning_rate": 9e-05,
      "loss": 0.8565,
      "step": 9
    },
    {
      "epoch": 0.07339449541284404,
      "grad_norm": 0.7018423676490784,
      "learning_rate": 0.0001,
      "loss": 0.7369,
      "step": 10
    },
    {
      "epoch": 0.08073394495412844,
      "grad_norm": 0.7135981917381287,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.671,
      "step": 11
    },
    {
      "epoch": 0.08807339449541285,
      "grad_norm": 0.791584312915802,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.7039,
      "step": 12
    },
    {
      "epoch": 0.09541284403669725,
      "grad_norm": 0.6780750751495361,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.7024,
      "step": 13
    },
    {
      "epoch": 0.10275229357798166,
      "grad_norm": 0.6978002190589905,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.8127,
      "step": 14
    },
    {
      "epoch": 0.11009174311926606,
      "grad_norm": 0.6280326843261719,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.7367,
      "step": 15
    },
    {
      "epoch": 0.11743119266055047,
      "grad_norm": 0.5914128422737122,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.7386,
      "step": 16
    },
    {
      "epoch": 0.12477064220183487,
      "grad_norm": 0.5690916180610657,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.6967,
      "step": 17
    },
    {
      "epoch": 0.13211009174311927,
      "grad_norm": 0.6618253588676453,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.8074,
      "step": 18
    },
    {
      "epoch": 0.13944954128440368,
      "grad_norm": 0.5351158976554871,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.7263,
      "step": 19
    },
    {
      "epoch": 0.14678899082568808,
      "grad_norm": 0.5452873110771179,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.7654,
      "step": 20
    },
    {
      "epoch": 0.15412844036697249,
      "grad_norm": 0.5408823490142822,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.6872,
      "step": 21
    },
    {
      "epoch": 0.1614678899082569,
      "grad_norm": 0.5791258811950684,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.7021,
      "step": 22
    },
    {
      "epoch": 0.1688073394495413,
      "grad_norm": 0.6007850170135498,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.7315,
      "step": 23
    },
    {
      "epoch": 0.1761467889908257,
      "grad_norm": 0.5800233483314514,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.7132,
      "step": 24
    },
    {
      "epoch": 0.1834862385321101,
      "grad_norm": 0.6535601019859314,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.7046,
      "step": 25
    },
    {
      "epoch": 0.1908256880733945,
      "grad_norm": 0.7141433954238892,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.8598,
      "step": 26
    },
    {
      "epoch": 0.1981651376146789,
      "grad_norm": 0.6294669508934021,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.9351,
      "step": 27
    },
    {
      "epoch": 0.20550458715596331,
      "grad_norm": 0.6602486371994019,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.8266,
      "step": 28
    },
    {
      "epoch": 0.21284403669724772,
      "grad_norm": 0.6365261077880859,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8377,
      "step": 29
    },
    {
      "epoch": 0.22018348623853212,
      "grad_norm": 0.6225994229316711,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.8686,
      "step": 30
    },
    {
      "epoch": 0.22752293577981653,
      "grad_norm": 0.6388337016105652,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.8258,
      "step": 31
    },
    {
      "epoch": 0.23486238532110093,
      "grad_norm": 0.6848137974739075,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.9546,
      "step": 32
    },
    {
      "epoch": 0.24220183486238533,
      "grad_norm": 0.760630190372467,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.9698,
      "step": 33
    },
    {
      "epoch": 0.24954128440366974,
      "grad_norm": 1.4575302600860596,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.289,
      "step": 34
    },
    {
      "epoch": 0.25688073394495414,
      "grad_norm": 0.4609055817127228,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.54,
      "step": 35
    },
    {
      "epoch": 0.26422018348623855,
      "grad_norm": 0.47219833731651306,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.5379,
      "step": 36
    },
    {
      "epoch": 0.27155963302752295,
      "grad_norm": 0.43857619166374207,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.5831,
      "step": 37
    },
    {
      "epoch": 0.27889908256880735,
      "grad_norm": 0.44134005904197693,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.6643,
      "step": 38
    },
    {
      "epoch": 0.28623853211009176,
      "grad_norm": 0.3944750726222992,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.5563,
      "step": 39
    },
    {
      "epoch": 0.29357798165137616,
      "grad_norm": 0.39067232608795166,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.593,
      "step": 40
    },
    {
      "epoch": 0.30091743119266057,
      "grad_norm": 0.5718076229095459,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.5941,
      "step": 41
    },
    {
      "epoch": 0.30825688073394497,
      "grad_norm": 0.3971261978149414,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.7517,
      "step": 42
    },
    {
      "epoch": 0.3155963302752294,
      "grad_norm": 0.3980463147163391,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.7895,
      "step": 43
    },
    {
      "epoch": 0.3229357798165138,
      "grad_norm": 0.3441670536994934,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.4756,
      "step": 44
    },
    {
      "epoch": 0.3302752293577982,
      "grad_norm": 0.3822227418422699,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.5701,
      "step": 45
    },
    {
      "epoch": 0.3376146788990826,
      "grad_norm": 0.40735456347465515,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.6265,
      "step": 46
    },
    {
      "epoch": 0.344954128440367,
      "grad_norm": 0.4540577232837677,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.699,
      "step": 47
    },
    {
      "epoch": 0.3522935779816514,
      "grad_norm": 0.4145893454551697,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7058,
      "step": 48
    },
    {
      "epoch": 0.3596330275229358,
      "grad_norm": 0.4242461025714874,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.6845,
      "step": 49
    },
    {
      "epoch": 0.3669724770642202,
      "grad_norm": 0.4225294291973114,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.5969,
      "step": 50
    },
    {
      "epoch": 0.3669724770642202,
      "eval_loss": 0.7089372873306274,
      "eval_runtime": 7.3832,
      "eval_samples_per_second": 31.152,
      "eval_steps_per_second": 7.856,
      "step": 50
    },
    {
      "epoch": 0.3743119266055046,
      "grad_norm": 0.45440104603767395,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.6622,
      "step": 51
    },
    {
      "epoch": 0.381651376146789,
      "grad_norm": 0.4386112093925476,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.6675,
      "step": 52
    },
    {
      "epoch": 0.3889908256880734,
      "grad_norm": 0.43003344535827637,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.6793,
      "step": 53
    },
    {
      "epoch": 0.3963302752293578,
      "grad_norm": 0.5001123547554016,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.6817,
      "step": 54
    },
    {
      "epoch": 0.4036697247706422,
      "grad_norm": 0.5568297505378723,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.6538,
      "step": 55
    },
    {
      "epoch": 0.41100917431192663,
      "grad_norm": 0.44233083724975586,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.717,
      "step": 56
    },
    {
      "epoch": 0.41834862385321103,
      "grad_norm": 0.5203274488449097,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.6568,
      "step": 57
    },
    {
      "epoch": 0.42568807339449544,
      "grad_norm": 0.529590368270874,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.7246,
      "step": 58
    },
    {
      "epoch": 0.43302752293577984,
      "grad_norm": 0.47836318612098694,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.6922,
      "step": 59
    },
    {
      "epoch": 0.44036697247706424,
      "grad_norm": 0.5171796083450317,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.7058,
      "step": 60
    },
    {
      "epoch": 0.44770642201834865,
      "grad_norm": 0.49430549144744873,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.6869,
      "step": 61
    },
    {
      "epoch": 0.45504587155963305,
      "grad_norm": 0.5193171501159668,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.7945,
      "step": 62
    },
    {
      "epoch": 0.46238532110091746,
      "grad_norm": 0.6313068866729736,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.7861,
      "step": 63
    },
    {
      "epoch": 0.46972477064220186,
      "grad_norm": 0.6041170358657837,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.7491,
      "step": 64
    },
    {
      "epoch": 0.47706422018348627,
      "grad_norm": 0.6043881773948669,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.9072,
      "step": 65
    },
    {
      "epoch": 0.48440366972477067,
      "grad_norm": 0.6289061307907104,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.9472,
      "step": 66
    },
    {
      "epoch": 0.4917431192660551,
      "grad_norm": 0.7074716091156006,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.0706,
      "step": 67
    },
    {
      "epoch": 0.4990825688073395,
      "grad_norm": 1.0272139310836792,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.249,
      "step": 68
    },
    {
      "epoch": 0.5064220183486239,
      "grad_norm": 0.4037744998931885,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.5478,
      "step": 69
    },
    {
      "epoch": 0.5137614678899083,
      "grad_norm": 0.4181773364543915,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.6575,
      "step": 70
    },
    {
      "epoch": 0.5211009174311927,
      "grad_norm": 0.4181150496006012,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.5975,
      "step": 71
    },
    {
      "epoch": 0.5284403669724771,
      "grad_norm": 0.3705148994922638,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.5462,
      "step": 72
    },
    {
      "epoch": 0.5357798165137615,
      "grad_norm": 0.3600141704082489,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.5123,
      "step": 73
    },
    {
      "epoch": 0.5431192660550459,
      "grad_norm": 0.34120720624923706,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.5915,
      "step": 74
    },
    {
      "epoch": 0.5504587155963303,
      "grad_norm": 0.3528464436531067,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.5901,
      "step": 75
    },
    {
      "epoch": 0.5577981651376147,
      "grad_norm": 0.3352064788341522,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.6071,
      "step": 76
    },
    {
      "epoch": 0.5651376146788991,
      "grad_norm": 0.32289859652519226,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.5741,
      "step": 77
    },
    {
      "epoch": 0.5724770642201835,
      "grad_norm": 0.32375475764274597,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.526,
      "step": 78
    },
    {
      "epoch": 0.5798165137614679,
      "grad_norm": 0.3686944544315338,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.6329,
      "step": 79
    },
    {
      "epoch": 0.5871559633027523,
      "grad_norm": 0.40908193588256836,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.5515,
      "step": 80
    },
    {
      "epoch": 0.5944954128440367,
      "grad_norm": 0.4456939697265625,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.6521,
      "step": 81
    },
    {
      "epoch": 0.6018348623853211,
      "grad_norm": 0.3769167959690094,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.5615,
      "step": 82
    },
    {
      "epoch": 0.6091743119266055,
      "grad_norm": 0.41746941208839417,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.6451,
      "step": 83
    },
    {
      "epoch": 0.6165137614678899,
      "grad_norm": 0.3857053816318512,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.6505,
      "step": 84
    },
    {
      "epoch": 0.6238532110091743,
      "grad_norm": 0.37709927558898926,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.6044,
      "step": 85
    },
    {
      "epoch": 0.6311926605504588,
      "grad_norm": 0.3770582675933838,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.5986,
      "step": 86
    },
    {
      "epoch": 0.6385321100917432,
      "grad_norm": 0.4132257103919983,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.6329,
      "step": 87
    },
    {
      "epoch": 0.6458715596330276,
      "grad_norm": 0.40162786841392517,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.6208,
      "step": 88
    },
    {
      "epoch": 0.653211009174312,
      "grad_norm": 0.428101122379303,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.6981,
      "step": 89
    },
    {
      "epoch": 0.6605504587155964,
      "grad_norm": 0.41267475485801697,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.6747,
      "step": 90
    },
    {
      "epoch": 0.6678899082568808,
      "grad_norm": 0.4253780245780945,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.6754,
      "step": 91
    },
    {
      "epoch": 0.6752293577981652,
      "grad_norm": 0.4702104330062866,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.6771,
      "step": 92
    },
    {
      "epoch": 0.6825688073394496,
      "grad_norm": 0.4644729495048523,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.7873,
      "step": 93
    },
    {
      "epoch": 0.689908256880734,
      "grad_norm": 0.5347480177879333,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.776,
      "step": 94
    },
    {
      "epoch": 0.6972477064220184,
      "grad_norm": 0.48614299297332764,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.6903,
      "step": 95
    },
    {
      "epoch": 0.7045871559633028,
      "grad_norm": 0.5975285768508911,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.7214,
      "step": 96
    },
    {
      "epoch": 0.7119266055045872,
      "grad_norm": 0.5876331329345703,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.6721,
      "step": 97
    },
    {
      "epoch": 0.7192660550458716,
      "grad_norm": 0.6095494031906128,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.8158,
      "step": 98
    },
    {
      "epoch": 0.726605504587156,
      "grad_norm": 0.5459724068641663,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.793,
      "step": 99
    },
    {
      "epoch": 0.7339449541284404,
      "grad_norm": 0.5794693827629089,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.8975,
      "step": 100
    },
    {
      "epoch": 0.7339449541284404,
      "eval_loss": 0.6698483228683472,
      "eval_runtime": 7.4072,
      "eval_samples_per_second": 31.051,
      "eval_steps_per_second": 7.83,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.54569648635904e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}