{
  "best_metric": 0.18127788603305817,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.08503401360544217,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017006802721088435,
      "grad_norm": 0.5269389748573303,
      "learning_rate": 1e-05,
      "loss": 0.1901,
      "step": 1
    },
    {
      "epoch": 0.0017006802721088435,
      "eval_loss": 0.5936321020126343,
      "eval_runtime": 99.436,
      "eval_samples_per_second": 9.956,
      "eval_steps_per_second": 2.494,
      "step": 1
    },
    {
      "epoch": 0.003401360544217687,
      "grad_norm": 0.46303698420524597,
      "learning_rate": 2e-05,
      "loss": 0.1959,
      "step": 2
    },
    {
      "epoch": 0.00510204081632653,
      "grad_norm": 0.5892171263694763,
      "learning_rate": 3e-05,
      "loss": 0.2197,
      "step": 3
    },
    {
      "epoch": 0.006802721088435374,
      "grad_norm": 0.5525668263435364,
      "learning_rate": 4e-05,
      "loss": 0.2315,
      "step": 4
    },
    {
      "epoch": 0.008503401360544218,
      "grad_norm": 0.5089474320411682,
      "learning_rate": 5e-05,
      "loss": 0.2095,
      "step": 5
    },
    {
      "epoch": 0.01020408163265306,
      "grad_norm": 0.49851194024086,
      "learning_rate": 6e-05,
      "loss": 0.2095,
      "step": 6
    },
    {
      "epoch": 0.011904761904761904,
      "grad_norm": 0.47188305854797363,
      "learning_rate": 7e-05,
      "loss": 0.1942,
      "step": 7
    },
    {
      "epoch": 0.013605442176870748,
      "grad_norm": 0.48552876710891724,
      "learning_rate": 8e-05,
      "loss": 0.2285,
      "step": 8
    },
    {
      "epoch": 0.015306122448979591,
      "grad_norm": 0.3960217833518982,
      "learning_rate": 9e-05,
      "loss": 0.1824,
      "step": 9
    },
    {
      "epoch": 0.017006802721088437,
      "grad_norm": 0.3507472276687622,
      "learning_rate": 0.0001,
      "loss": 0.1569,
      "step": 10
    },
    {
      "epoch": 0.01870748299319728,
      "grad_norm": 0.33635377883911133,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.184,
      "step": 11
    },
    {
      "epoch": 0.02040816326530612,
      "grad_norm": 0.4036436676979065,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.1587,
      "step": 12
    },
    {
      "epoch": 0.022108843537414966,
      "grad_norm": 0.5375078320503235,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.2424,
      "step": 13
    },
    {
      "epoch": 0.023809523809523808,
      "grad_norm": 0.4145143926143646,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.1819,
      "step": 14
    },
    {
      "epoch": 0.025510204081632654,
      "grad_norm": 0.4353350102901459,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.154,
      "step": 15
    },
    {
      "epoch": 0.027210884353741496,
      "grad_norm": 0.32249438762664795,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.1298,
      "step": 16
    },
    {
      "epoch": 0.02891156462585034,
      "grad_norm": 0.39720624685287476,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.1577,
      "step": 17
    },
    {
      "epoch": 0.030612244897959183,
      "grad_norm": 0.37612348794937134,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.1394,
      "step": 18
    },
    {
      "epoch": 0.03231292517006803,
      "grad_norm": 0.32927829027175903,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.1571,
      "step": 19
    },
    {
      "epoch": 0.034013605442176874,
      "grad_norm": 0.34154942631721497,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.1513,
      "step": 20
    },
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 0.2961677610874176,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.1267,
      "step": 21
    },
    {
      "epoch": 0.03741496598639456,
      "grad_norm": 0.30949026346206665,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.1611,
      "step": 22
    },
    {
      "epoch": 0.0391156462585034,
      "grad_norm": 0.34329307079315186,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.1478,
      "step": 23
    },
    {
      "epoch": 0.04081632653061224,
      "grad_norm": 0.33806389570236206,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.1604,
      "step": 24
    },
    {
      "epoch": 0.04251700680272109,
      "grad_norm": 0.3135806620121002,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.1218,
      "step": 25
    },
    {
      "epoch": 0.04421768707482993,
      "grad_norm": 0.5712440609931946,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.1603,
      "step": 26
    },
    {
      "epoch": 0.04591836734693878,
      "grad_norm": 0.545917272567749,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.2418,
      "step": 27
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 0.3555242419242859,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.1463,
      "step": 28
    },
    {
      "epoch": 0.04931972789115646,
      "grad_norm": 0.39341312646865845,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.1591,
      "step": 29
    },
    {
      "epoch": 0.05102040816326531,
      "grad_norm": 0.36689674854278564,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.1539,
      "step": 30
    },
    {
      "epoch": 0.05272108843537415,
      "grad_norm": 0.46685174107551575,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.1796,
      "step": 31
    },
    {
      "epoch": 0.05442176870748299,
      "grad_norm": 0.48095518350601196,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.2008,
      "step": 32
    },
    {
      "epoch": 0.05612244897959184,
      "grad_norm": 0.4282090365886688,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.1706,
      "step": 33
    },
    {
      "epoch": 0.05782312925170068,
      "grad_norm": 0.7042590379714966,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.315,
      "step": 34
    },
    {
      "epoch": 0.05952380952380952,
      "grad_norm": 0.43822816014289856,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.1428,
      "step": 35
    },
    {
      "epoch": 0.061224489795918366,
      "grad_norm": 0.40582820773124695,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.1482,
      "step": 36
    },
    {
      "epoch": 0.06292517006802721,
      "grad_norm": 0.46641525626182556,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.2125,
      "step": 37
    },
    {
      "epoch": 0.06462585034013606,
      "grad_norm": 0.5421123504638672,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.1554,
      "step": 38
    },
    {
      "epoch": 0.0663265306122449,
      "grad_norm": 0.5820235013961792,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.1635,
      "step": 39
    },
    {
      "epoch": 0.06802721088435375,
      "grad_norm": 0.5159996151924133,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.2234,
      "step": 40
    },
    {
      "epoch": 0.06972789115646258,
      "grad_norm": 0.5390616059303284,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.2149,
      "step": 41
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 0.5398741364479065,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.2231,
      "step": 42
    },
    {
      "epoch": 0.07312925170068027,
      "grad_norm": 0.5961061716079712,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.1861,
      "step": 43
    },
    {
      "epoch": 0.07482993197278912,
      "grad_norm": 0.5682746767997742,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.2059,
      "step": 44
    },
    {
      "epoch": 0.07653061224489796,
      "grad_norm": 0.6431316137313843,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.2388,
      "step": 45
    },
    {
      "epoch": 0.0782312925170068,
      "grad_norm": 0.7409397959709167,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.26,
      "step": 46
    },
    {
      "epoch": 0.07993197278911565,
      "grad_norm": 1.0703874826431274,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.2309,
      "step": 47
    },
    {
      "epoch": 0.08163265306122448,
      "grad_norm": 0.7176180481910706,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.2351,
      "step": 48
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 1.2472457885742188,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.2577,
      "step": 49
    },
    {
      "epoch": 0.08503401360544217,
      "grad_norm": 1.9959722757339478,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.3351,
      "step": 50
    },
    {
      "epoch": 0.08503401360544217,
      "eval_loss": 0.18127788603305817,
      "eval_runtime": 100.6415,
      "eval_samples_per_second": 9.837,
      "eval_steps_per_second": 2.464,
      "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": 9.240637183151309e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}