{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.005293526017680377,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010587052035360753,
      "grad_norm": 4.395105497678742e-05,
      "learning_rate": 1e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.00010587052035360753,
      "eval_loss": 11.5,
      "eval_runtime": 71.5228,
      "eval_samples_per_second": 222.419,
      "eval_steps_per_second": 55.605,
      "step": 1
    },
    {
      "epoch": 0.00021174104070721507,
      "grad_norm": 4.58413123851642e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.0003176115610608226,
      "grad_norm": 4.140105738770217e-05,
      "learning_rate": 3e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.00042348208141443014,
      "grad_norm": 4.382082261145115e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.0005293526017680377,
      "grad_norm": 4.889183765044436e-05,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.0006352231221216452,
      "grad_norm": 4.410705514601432e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.0007410936424752528,
      "grad_norm": 4.27704508183524e-05,
      "learning_rate": 7e-05,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.0008469641628288603,
      "grad_norm": 5.128671182319522e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.0009528346831824678,
      "grad_norm": 4.963524406775832e-05,
      "learning_rate": 9e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.0010587052035360754,
      "grad_norm": 5.1579288992797956e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.001164575723889683,
      "grad_norm": 5.476976730278693e-05,
      "learning_rate": 9.999316524962345e-05,
      "loss": 46.0,
      "step": 11
    },
    {
      "epoch": 0.0012704462442432905,
      "grad_norm": 6.490119267255068e-05,
      "learning_rate": 9.997266286704631e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.001376316764596898,
      "grad_norm": 6.41516744508408e-05,
      "learning_rate": 9.993849845741524e-05,
      "loss": 46.0,
      "step": 13
    },
    {
      "epoch": 0.0014821872849505055,
      "grad_norm": 6.963236228330061e-05,
      "learning_rate": 9.989068136093873e-05,
      "loss": 46.0,
      "step": 14
    },
    {
      "epoch": 0.001588057805304113,
      "grad_norm": 7.260955317178741e-05,
      "learning_rate": 9.98292246503335e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.0016939283256577206,
      "grad_norm": 8.003199764061719e-05,
      "learning_rate": 9.975414512725057e-05,
      "loss": 46.0,
      "step": 16
    },
    {
      "epoch": 0.001799798846011328,
      "grad_norm": 6.157662573968992e-05,
      "learning_rate": 9.966546331768191e-05,
      "loss": 46.0,
      "step": 17
    },
    {
      "epoch": 0.0019056693663649356,
      "grad_norm": 9.91981869447045e-05,
      "learning_rate": 9.956320346634876e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.0020115398867185433,
      "grad_norm": 8.243980119004846e-05,
      "learning_rate": 9.944739353007344e-05,
      "loss": 46.0,
      "step": 19
    },
    {
      "epoch": 0.002117410407072151,
      "grad_norm": 9.023436723509803e-05,
      "learning_rate": 9.931806517013612e-05,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.0022232809274257584,
      "grad_norm": 0.000126901242765598,
      "learning_rate": 9.917525374361912e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.002329151447779366,
      "grad_norm": 8.287958917208016e-05,
      "learning_rate": 9.901899829374047e-05,
      "loss": 46.0,
      "step": 22
    },
    {
      "epoch": 0.0024350219681329734,
      "grad_norm": 7.875176379457116e-05,
      "learning_rate": 9.884934153917997e-05,
      "loss": 46.0,
      "step": 23
    },
    {
      "epoch": 0.002540892488486581,
      "grad_norm": 8.90982846613042e-05,
      "learning_rate": 9.86663298624003e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.0026467630088401885,
      "grad_norm": 9.042149758897722e-05,
      "learning_rate": 9.847001329696653e-05,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.002752633529193796,
      "grad_norm": 0.00010223303979728371,
      "learning_rate": 9.826044551386744e-05,
      "loss": 46.0,
      "step": 26
    },
    {
      "epoch": 0.0028585040495474035,
      "grad_norm": 0.0001294900430366397,
      "learning_rate": 9.803768380684242e-05,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.002964374569901011,
      "grad_norm": 9.50166504480876e-05,
      "learning_rate": 9.780178907671789e-05,
      "loss": 46.0,
      "step": 28
    },
    {
      "epoch": 0.0030702450902546185,
      "grad_norm": 0.00010819704766618088,
      "learning_rate": 9.755282581475769e-05,
      "loss": 46.0,
      "step": 29
    },
    {
      "epoch": 0.003176115610608226,
      "grad_norm": 7.831957918824628e-05,
      "learning_rate": 9.729086208503174e-05,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.0032819861309618336,
      "grad_norm": 0.0001063505478668958,
      "learning_rate": 9.701596950580806e-05,
      "loss": 46.0,
      "step": 31
    },
    {
      "epoch": 0.003387856651315441,
      "grad_norm": 0.00011041116522392258,
      "learning_rate": 9.672822322997305e-05,
      "loss": 46.0,
      "step": 32
    },
    {
      "epoch": 0.0034937271716690486,
      "grad_norm": 0.0001492316514486447,
      "learning_rate": 9.642770192448536e-05,
      "loss": 46.0,
      "step": 33
    },
    {
      "epoch": 0.003599597692022656,
      "grad_norm": 0.00012391034397296607,
      "learning_rate": 9.611448774886924e-05,
      "loss": 46.0,
      "step": 34
    },
    {
      "epoch": 0.0037054682123762637,
      "grad_norm": 0.00012100706953788176,
      "learning_rate": 9.578866633275288e-05,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 0.003811338732729871,
      "grad_norm": 0.00023128939210437238,
      "learning_rate": 9.545032675245813e-05,
      "loss": 46.0,
      "step": 36
    },
    {
      "epoch": 0.003917209253083479,
      "grad_norm": 0.00038155875517986715,
      "learning_rate": 9.509956150664796e-05,
      "loss": 46.0,
      "step": 37
    },
    {
      "epoch": 0.004023079773437087,
      "grad_norm": 0.00035766095970757306,
      "learning_rate": 9.473646649103818e-05,
      "loss": 46.0,
      "step": 38
    },
    {
      "epoch": 0.004128950293790694,
      "grad_norm": 0.0011300703044980764,
      "learning_rate": 9.43611409721806e-05,
      "loss": 46.0,
      "step": 39
    },
    {
      "epoch": 0.004234820814144302,
      "grad_norm": 0.0015645480016246438,
      "learning_rate": 9.397368756032445e-05,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 0.004340691334497909,
      "grad_norm": 0.001370024518109858,
      "learning_rate": 9.357421218136386e-05,
      "loss": 46.0,
      "step": 41
    },
    {
      "epoch": 0.004446561854851517,
      "grad_norm": 0.0015453952364623547,
      "learning_rate": 9.316282404787871e-05,
      "loss": 46.0,
      "step": 42
    },
    {
      "epoch": 0.004552432375205124,
      "grad_norm": 0.0013086320832371712,
      "learning_rate": 9.273963562927695e-05,
      "loss": 46.0,
      "step": 43
    },
    {
      "epoch": 0.004658302895558732,
      "grad_norm": 0.001663604867644608,
      "learning_rate": 9.230476262104677e-05,
      "loss": 46.0,
      "step": 44
    },
    {
      "epoch": 0.004764173415912339,
      "grad_norm": 0.0016766958869993687,
      "learning_rate": 9.185832391312644e-05,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 0.004870043936265947,
      "grad_norm": 0.0018082212191075087,
      "learning_rate": 9.140044155740101e-05,
      "loss": 46.0,
      "step": 46
    },
    {
      "epoch": 0.004975914456619554,
      "grad_norm": 0.0017413385212421417,
      "learning_rate": 9.093124073433463e-05,
      "loss": 46.0,
      "step": 47
    },
    {
      "epoch": 0.005081784976973162,
      "grad_norm": 0.0017923465929925442,
      "learning_rate": 9.045084971874738e-05,
      "loss": 46.0,
      "step": 48
    },
    {
      "epoch": 0.005187655497326769,
      "grad_norm": 0.0023123230785131454,
      "learning_rate": 8.995939984474624e-05,
      "loss": 46.0,
      "step": 49
    },
    {
      "epoch": 0.005293526017680377,
      "grad_norm": 0.0017731377156451344,
      "learning_rate": 8.945702546981969e-05,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 0.005293526017680377,
      "eval_loss": 11.5,
      "eval_runtime": 71.3773,
      "eval_samples_per_second": 222.872,
      "eval_steps_per_second": 55.718,
      "step": 50
    }
  ],
  "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": 8079813771264.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}