{
  "best_metric": 0.672206699848175,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.13717421124828533,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013717421124828531,
      "grad_norm": 1.8108248710632324,
      "learning_rate": 1e-05,
      "loss": 2.1791,
      "step": 1
    },
    {
      "epoch": 0.0013717421124828531,
      "eval_loss": 2.359384059906006,
      "eval_runtime": 102.5952,
      "eval_samples_per_second": 11.969,
      "eval_steps_per_second": 2.992,
      "step": 1
    },
    {
      "epoch": 0.0027434842249657062,
      "grad_norm": 2.168975591659546,
      "learning_rate": 2e-05,
      "loss": 2.4753,
      "step": 2
    },
    {
      "epoch": 0.00411522633744856,
      "grad_norm": 1.929791808128357,
      "learning_rate": 3e-05,
      "loss": 2.5551,
      "step": 3
    },
    {
      "epoch": 0.0054869684499314125,
      "grad_norm": 2.3733065128326416,
      "learning_rate": 4e-05,
      "loss": 2.6526,
      "step": 4
    },
    {
      "epoch": 0.006858710562414266,
      "grad_norm": 2.5940165519714355,
      "learning_rate": 5e-05,
      "loss": 2.4588,
      "step": 5
    },
    {
      "epoch": 0.00823045267489712,
      "grad_norm": 2.2310335636138916,
      "learning_rate": 6e-05,
      "loss": 2.5103,
      "step": 6
    },
    {
      "epoch": 0.009602194787379973,
      "grad_norm": 1.8037067651748657,
      "learning_rate": 7e-05,
      "loss": 2.1907,
      "step": 7
    },
    {
      "epoch": 0.010973936899862825,
      "grad_norm": 1.7454071044921875,
      "learning_rate": 8e-05,
      "loss": 1.7885,
      "step": 8
    },
    {
      "epoch": 0.012345679012345678,
      "grad_norm": 1.7510610818862915,
      "learning_rate": 9e-05,
      "loss": 1.554,
      "step": 9
    },
    {
      "epoch": 0.013717421124828532,
      "grad_norm": 1.5554914474487305,
      "learning_rate": 0.0001,
      "loss": 1.475,
      "step": 10
    },
    {
      "epoch": 0.015089163237311385,
      "grad_norm": 1.3975311517715454,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.346,
      "step": 11
    },
    {
      "epoch": 0.01646090534979424,
      "grad_norm": 1.5020421743392944,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.2495,
      "step": 12
    },
    {
      "epoch": 0.01783264746227709,
      "grad_norm": 1.7484345436096191,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.2833,
      "step": 13
    },
    {
      "epoch": 0.019204389574759947,
      "grad_norm": 1.5758137702941895,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.2012,
      "step": 14
    },
    {
      "epoch": 0.0205761316872428,
      "grad_norm": 1.180163860321045,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.1123,
      "step": 15
    },
    {
      "epoch": 0.02194787379972565,
      "grad_norm": 1.1840097904205322,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.0274,
      "step": 16
    },
    {
      "epoch": 0.023319615912208505,
      "grad_norm": 1.1171801090240479,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.1094,
      "step": 17
    },
    {
      "epoch": 0.024691358024691357,
      "grad_norm": 1.2143296003341675,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.0646,
      "step": 18
    },
    {
      "epoch": 0.02606310013717421,
      "grad_norm": 1.1554465293884277,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.1274,
      "step": 19
    },
    {
      "epoch": 0.027434842249657063,
      "grad_norm": 0.978050947189331,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.8353,
      "step": 20
    },
    {
      "epoch": 0.02880658436213992,
      "grad_norm": 1.0037025213241577,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.9977,
      "step": 21
    },
    {
      "epoch": 0.03017832647462277,
      "grad_norm": 1.0239306688308716,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.945,
      "step": 22
    },
    {
      "epoch": 0.03155006858710562,
      "grad_norm": 1.0410940647125244,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.8752,
      "step": 23
    },
    {
      "epoch": 0.03292181069958848,
      "grad_norm": 1.0184775590896606,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.8255,
      "step": 24
    },
    {
      "epoch": 0.03429355281207133,
      "grad_norm": 0.9275608658790588,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.9649,
      "step": 25
    },
    {
      "epoch": 0.03566529492455418,
      "grad_norm": 0.884083092212677,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.8024,
      "step": 26
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 1.0138894319534302,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.879,
      "step": 27
    },
    {
      "epoch": 0.038408779149519894,
      "grad_norm": 1.2958335876464844,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.845,
      "step": 28
    },
    {
      "epoch": 0.039780521262002745,
      "grad_norm": 0.8304831981658936,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8288,
      "step": 29
    },
    {
      "epoch": 0.0411522633744856,
      "grad_norm": 0.850218653678894,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.9146,
      "step": 30
    },
    {
      "epoch": 0.04252400548696845,
      "grad_norm": 1.0305699110031128,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.8331,
      "step": 31
    },
    {
      "epoch": 0.0438957475994513,
      "grad_norm": 0.8513186573982239,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.7539,
      "step": 32
    },
    {
      "epoch": 0.04526748971193416,
      "grad_norm": 0.9753694534301758,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.8104,
      "step": 33
    },
    {
      "epoch": 0.04663923182441701,
      "grad_norm": 0.9042930603027344,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.8383,
      "step": 34
    },
    {
      "epoch": 0.04801097393689986,
      "grad_norm": 1.0121922492980957,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.9992,
      "step": 35
    },
    {
      "epoch": 0.04938271604938271,
      "grad_norm": 0.9063836932182312,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.8403,
      "step": 36
    },
    {
      "epoch": 0.05075445816186557,
      "grad_norm": 0.7969421148300171,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.8814,
      "step": 37
    },
    {
      "epoch": 0.05212620027434842,
      "grad_norm": 0.8667128086090088,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.8195,
      "step": 38
    },
    {
      "epoch": 0.053497942386831275,
      "grad_norm": 0.7646212577819824,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.731,
      "step": 39
    },
    {
      "epoch": 0.05486968449931413,
      "grad_norm": 0.8752400875091553,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.792,
      "step": 40
    },
    {
      "epoch": 0.056241426611796985,
      "grad_norm": 0.7880658507347107,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.8621,
      "step": 41
    },
    {
      "epoch": 0.05761316872427984,
      "grad_norm": 0.7580417990684509,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.7901,
      "step": 42
    },
    {
      "epoch": 0.05898491083676269,
      "grad_norm": 0.8328334093093872,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.876,
      "step": 43
    },
    {
      "epoch": 0.06035665294924554,
      "grad_norm": 0.7832382321357727,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.7966,
      "step": 44
    },
    {
      "epoch": 0.06172839506172839,
      "grad_norm": 0.9131791591644287,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.8224,
      "step": 45
    },
    {
      "epoch": 0.06310013717421124,
      "grad_norm": 0.853861927986145,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.8777,
      "step": 46
    },
    {
      "epoch": 0.0644718792866941,
      "grad_norm": 0.8206557631492615,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.7516,
      "step": 47
    },
    {
      "epoch": 0.06584362139917696,
      "grad_norm": 0.8616703748703003,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7658,
      "step": 48
    },
    {
      "epoch": 0.06721536351165981,
      "grad_norm": 0.7976633310317993,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.7094,
      "step": 49
    },
    {
      "epoch": 0.06858710562414266,
      "grad_norm": 0.9627761244773865,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.7091,
      "step": 50
    },
    {
      "epoch": 0.06858710562414266,
      "eval_loss": 0.7677202820777893,
      "eval_runtime": 104.2498,
      "eval_samples_per_second": 11.779,
      "eval_steps_per_second": 2.945,
      "step": 50
    },
    {
      "epoch": 0.06995884773662552,
      "grad_norm": 0.8886013627052307,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.0666,
      "step": 51
    },
    {
      "epoch": 0.07133058984910837,
      "grad_norm": 0.9581699967384338,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.0,
      "step": 52
    },
    {
      "epoch": 0.07270233196159122,
      "grad_norm": 0.7953754663467407,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.0147,
      "step": 53
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.7907536029815674,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.8676,
      "step": 54
    },
    {
      "epoch": 0.07544581618655692,
      "grad_norm": 0.7577344179153442,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.9509,
      "step": 55
    },
    {
      "epoch": 0.07681755829903979,
      "grad_norm": 0.980762779712677,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.8895,
      "step": 56
    },
    {
      "epoch": 0.07818930041152264,
      "grad_norm": 0.8946378827095032,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.867,
      "step": 57
    },
    {
      "epoch": 0.07956104252400549,
      "grad_norm": 0.9008687734603882,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.8059,
      "step": 58
    },
    {
      "epoch": 0.08093278463648834,
      "grad_norm": 0.8883490562438965,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.7215,
      "step": 59
    },
    {
      "epoch": 0.0823045267489712,
      "grad_norm": 0.8660940527915955,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.705,
      "step": 60
    },
    {
      "epoch": 0.08367626886145405,
      "grad_norm": 0.8446040153503418,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.8148,
      "step": 61
    },
    {
      "epoch": 0.0850480109739369,
      "grad_norm": 0.7114365696907043,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.7353,
      "step": 62
    },
    {
      "epoch": 0.08641975308641975,
      "grad_norm": 0.6913666725158691,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.7051,
      "step": 63
    },
    {
      "epoch": 0.0877914951989026,
      "grad_norm": 0.7440309524536133,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.6897,
      "step": 64
    },
    {
      "epoch": 0.08916323731138547,
      "grad_norm": 0.6593201756477356,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.7488,
      "step": 65
    },
    {
      "epoch": 0.09053497942386832,
      "grad_norm": 0.8882130980491638,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.7327,
      "step": 66
    },
    {
      "epoch": 0.09190672153635117,
      "grad_norm": 0.7141872644424438,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.763,
      "step": 67
    },
    {
      "epoch": 0.09327846364883402,
      "grad_norm": 0.7310812473297119,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.6181,
      "step": 68
    },
    {
      "epoch": 0.09465020576131687,
      "grad_norm": 0.6965682506561279,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.736,
      "step": 69
    },
    {
      "epoch": 0.09602194787379972,
      "grad_norm": 0.6382268071174622,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.666,
      "step": 70
    },
    {
      "epoch": 0.09739368998628258,
      "grad_norm": 0.738567054271698,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.7502,
      "step": 71
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 0.7237371802330017,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.7352,
      "step": 72
    },
    {
      "epoch": 0.10013717421124829,
      "grad_norm": 0.6134920716285706,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.699,
      "step": 73
    },
    {
      "epoch": 0.10150891632373114,
      "grad_norm": 0.6023762822151184,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.5733,
      "step": 74
    },
    {
      "epoch": 0.102880658436214,
      "grad_norm": 0.7722994685173035,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.712,
      "step": 75
    },
    {
      "epoch": 0.10425240054869685,
      "grad_norm": 0.6359792351722717,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.6032,
      "step": 76
    },
    {
      "epoch": 0.1056241426611797,
      "grad_norm": 1.0157991647720337,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.6771,
      "step": 77
    },
    {
      "epoch": 0.10699588477366255,
      "grad_norm": 0.7552648186683655,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.8228,
      "step": 78
    },
    {
      "epoch": 0.1083676268861454,
      "grad_norm": 0.6754823923110962,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.7058,
      "step": 79
    },
    {
      "epoch": 0.10973936899862825,
      "grad_norm": 0.7087421417236328,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.7568,
      "step": 80
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.907531201839447,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7217,
      "step": 81
    },
    {
      "epoch": 0.11248285322359397,
      "grad_norm": 0.6867223381996155,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.6275,
      "step": 82
    },
    {
      "epoch": 0.11385459533607682,
      "grad_norm": 0.6423940658569336,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.5992,
      "step": 83
    },
    {
      "epoch": 0.11522633744855967,
      "grad_norm": 0.7836233973503113,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.7563,
      "step": 84
    },
    {
      "epoch": 0.11659807956104253,
      "grad_norm": 0.7429043054580688,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.7826,
      "step": 85
    },
    {
      "epoch": 0.11796982167352538,
      "grad_norm": 0.7121160626411438,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.6765,
      "step": 86
    },
    {
      "epoch": 0.11934156378600823,
      "grad_norm": 0.6519823670387268,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.6412,
      "step": 87
    },
    {
      "epoch": 0.12071330589849108,
      "grad_norm": 0.7616689801216125,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.6675,
      "step": 88
    },
    {
      "epoch": 0.12208504801097393,
      "grad_norm": 0.7042734026908875,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.6333,
      "step": 89
    },
    {
      "epoch": 0.12345679012345678,
      "grad_norm": 0.7615177035331726,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.6755,
      "step": 90
    },
    {
      "epoch": 0.12482853223593965,
      "grad_norm": 0.6770451068878174,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.6777,
      "step": 91
    },
    {
      "epoch": 0.1262002743484225,
      "grad_norm": 0.7251375913619995,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.7271,
      "step": 92
    },
    {
      "epoch": 0.12757201646090535,
      "grad_norm": 0.762030839920044,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.7694,
      "step": 93
    },
    {
      "epoch": 0.1289437585733882,
      "grad_norm": 0.7940636873245239,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.67,
      "step": 94
    },
    {
      "epoch": 0.13031550068587106,
      "grad_norm": 0.7140344381332397,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.7463,
      "step": 95
    },
    {
      "epoch": 0.13168724279835392,
      "grad_norm": 0.8514577150344849,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.7389,
      "step": 96
    },
    {
      "epoch": 0.13305898491083676,
      "grad_norm": 0.8461818099021912,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.7734,
      "step": 97
    },
    {
      "epoch": 0.13443072702331962,
      "grad_norm": 0.6528753042221069,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.5591,
      "step": 98
    },
    {
      "epoch": 0.13580246913580246,
      "grad_norm": 0.829468846321106,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.693,
      "step": 99
    },
    {
      "epoch": 0.13717421124828533,
      "grad_norm": 0.6663625240325928,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.5723,
      "step": 100
    },
    {
      "epoch": 0.13717421124828533,
      "eval_loss": 0.672206699848175,
      "eval_runtime": 104.206,
      "eval_samples_per_second": 11.784,
      "eval_steps_per_second": 2.946,
      "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": 1.5733112530639258e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}