{
  "best_metric": 1.0215978622436523,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.29542097488921715,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005908419497784343,
      "grad_norm": 51.34055709838867,
      "learning_rate": 1e-05,
      "loss": 6.3437,
      "step": 1
    },
    {
      "epoch": 0.005908419497784343,
      "eval_loss": 1.8814340829849243,
      "eval_runtime": 20.607,
      "eval_samples_per_second": 13.879,
      "eval_steps_per_second": 3.494,
      "step": 1
    },
    {
      "epoch": 0.011816838995568686,
      "grad_norm": 51.71321105957031,
      "learning_rate": 2e-05,
      "loss": 6.4062,
      "step": 2
    },
    {
      "epoch": 0.01772525849335303,
      "grad_norm": 47.652870178222656,
      "learning_rate": 3e-05,
      "loss": 6.0732,
      "step": 3
    },
    {
      "epoch": 0.023633677991137372,
      "grad_norm": 34.534549713134766,
      "learning_rate": 4e-05,
      "loss": 5.0456,
      "step": 4
    },
    {
      "epoch": 0.029542097488921712,
      "grad_norm": 50.97783279418945,
      "learning_rate": 5e-05,
      "loss": 4.1734,
      "step": 5
    },
    {
      "epoch": 0.03545051698670606,
      "grad_norm": 25.17313003540039,
      "learning_rate": 6e-05,
      "loss": 4.1785,
      "step": 6
    },
    {
      "epoch": 0.0413589364844904,
      "grad_norm": 34.59897232055664,
      "learning_rate": 7e-05,
      "loss": 4.1085,
      "step": 7
    },
    {
      "epoch": 0.047267355982274745,
      "grad_norm": 18.07676124572754,
      "learning_rate": 8e-05,
      "loss": 3.6911,
      "step": 8
    },
    {
      "epoch": 0.053175775480059084,
      "grad_norm": 15.92068862915039,
      "learning_rate": 9e-05,
      "loss": 3.6311,
      "step": 9
    },
    {
      "epoch": 0.059084194977843424,
      "grad_norm": 12.019160270690918,
      "learning_rate": 0.0001,
      "loss": 3.1151,
      "step": 10
    },
    {
      "epoch": 0.06499261447562776,
      "grad_norm": 13.678496360778809,
      "learning_rate": 9.999316524962345e-05,
      "loss": 3.5686,
      "step": 11
    },
    {
      "epoch": 0.07090103397341212,
      "grad_norm": 12.054726600646973,
      "learning_rate": 9.997266286704631e-05,
      "loss": 3.6136,
      "step": 12
    },
    {
      "epoch": 0.07680945347119646,
      "grad_norm": 13.952569007873535,
      "learning_rate": 9.993849845741524e-05,
      "loss": 3.4011,
      "step": 13
    },
    {
      "epoch": 0.0827178729689808,
      "grad_norm": 12.28878402709961,
      "learning_rate": 9.989068136093873e-05,
      "loss": 3.6625,
      "step": 14
    },
    {
      "epoch": 0.08862629246676514,
      "grad_norm": 11.535065650939941,
      "learning_rate": 9.98292246503335e-05,
      "loss": 3.5663,
      "step": 15
    },
    {
      "epoch": 0.09453471196454949,
      "grad_norm": 12.758620262145996,
      "learning_rate": 9.975414512725057e-05,
      "loss": 3.5768,
      "step": 16
    },
    {
      "epoch": 0.10044313146233383,
      "grad_norm": 12.950556755065918,
      "learning_rate": 9.966546331768191e-05,
      "loss": 3.3219,
      "step": 17
    },
    {
      "epoch": 0.10635155096011817,
      "grad_norm": 11.887937545776367,
      "learning_rate": 9.956320346634876e-05,
      "loss": 3.7698,
      "step": 18
    },
    {
      "epoch": 0.11225997045790251,
      "grad_norm": 11.189031600952148,
      "learning_rate": 9.944739353007344e-05,
      "loss": 3.5234,
      "step": 19
    },
    {
      "epoch": 0.11816838995568685,
      "grad_norm": 11.704141616821289,
      "learning_rate": 9.931806517013612e-05,
      "loss": 3.1704,
      "step": 20
    },
    {
      "epoch": 0.1240768094534712,
      "grad_norm": 15.247882843017578,
      "learning_rate": 9.917525374361912e-05,
      "loss": 3.8576,
      "step": 21
    },
    {
      "epoch": 0.12998522895125553,
      "grad_norm": 14.080589294433594,
      "learning_rate": 9.901899829374047e-05,
      "loss": 3.871,
      "step": 22
    },
    {
      "epoch": 0.1358936484490399,
      "grad_norm": 11.416792869567871,
      "learning_rate": 9.884934153917997e-05,
      "loss": 3.5375,
      "step": 23
    },
    {
      "epoch": 0.14180206794682423,
      "grad_norm": 11.188799858093262,
      "learning_rate": 9.86663298624003e-05,
      "loss": 3.6145,
      "step": 24
    },
    {
      "epoch": 0.14771048744460857,
      "grad_norm": 15.087061882019043,
      "learning_rate": 9.847001329696653e-05,
      "loss": 4.0115,
      "step": 25
    },
    {
      "epoch": 0.1536189069423929,
      "grad_norm": 11.513084411621094,
      "learning_rate": 9.826044551386744e-05,
      "loss": 3.9049,
      "step": 26
    },
    {
      "epoch": 0.15952732644017725,
      "grad_norm": 12.167125701904297,
      "learning_rate": 9.803768380684242e-05,
      "loss": 4.083,
      "step": 27
    },
    {
      "epoch": 0.1654357459379616,
      "grad_norm": 12.131103515625,
      "learning_rate": 9.780178907671789e-05,
      "loss": 3.6772,
      "step": 28
    },
    {
      "epoch": 0.17134416543574593,
      "grad_norm": 13.083057403564453,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.8718,
      "step": 29
    },
    {
      "epoch": 0.17725258493353027,
      "grad_norm": 12.414674758911133,
      "learning_rate": 9.729086208503174e-05,
      "loss": 4.1398,
      "step": 30
    },
    {
      "epoch": 0.1831610044313146,
      "grad_norm": 11.669783592224121,
      "learning_rate": 9.701596950580806e-05,
      "loss": 4.2851,
      "step": 31
    },
    {
      "epoch": 0.18906942392909898,
      "grad_norm": 12.696599006652832,
      "learning_rate": 9.672822322997305e-05,
      "loss": 3.9792,
      "step": 32
    },
    {
      "epoch": 0.19497784342688332,
      "grad_norm": 14.1757173538208,
      "learning_rate": 9.642770192448536e-05,
      "loss": 4.8195,
      "step": 33
    },
    {
      "epoch": 0.20088626292466766,
      "grad_norm": 11.965018272399902,
      "learning_rate": 9.611448774886924e-05,
      "loss": 4.372,
      "step": 34
    },
    {
      "epoch": 0.206794682422452,
      "grad_norm": 11.343331336975098,
      "learning_rate": 9.578866633275288e-05,
      "loss": 4.5424,
      "step": 35
    },
    {
      "epoch": 0.21270310192023634,
      "grad_norm": 11.488658905029297,
      "learning_rate": 9.545032675245813e-05,
      "loss": 4.5233,
      "step": 36
    },
    {
      "epoch": 0.21861152141802068,
      "grad_norm": 13.247932434082031,
      "learning_rate": 9.509956150664796e-05,
      "loss": 5.7089,
      "step": 37
    },
    {
      "epoch": 0.22451994091580502,
      "grad_norm": 13.024702072143555,
      "learning_rate": 9.473646649103818e-05,
      "loss": 5.0666,
      "step": 38
    },
    {
      "epoch": 0.23042836041358936,
      "grad_norm": 15.370957374572754,
      "learning_rate": 9.43611409721806e-05,
      "loss": 5.4644,
      "step": 39
    },
    {
      "epoch": 0.2363367799113737,
      "grad_norm": 12.9291353225708,
      "learning_rate": 9.397368756032445e-05,
      "loss": 5.3628,
      "step": 40
    },
    {
      "epoch": 0.24224519940915806,
      "grad_norm": 14.708918571472168,
      "learning_rate": 9.357421218136386e-05,
      "loss": 5.6903,
      "step": 41
    },
    {
      "epoch": 0.2481536189069424,
      "grad_norm": 14.399056434631348,
      "learning_rate": 9.316282404787871e-05,
      "loss": 6.7158,
      "step": 42
    },
    {
      "epoch": 0.25406203840472674,
      "grad_norm": 23.516857147216797,
      "learning_rate": 9.273963562927695e-05,
      "loss": 5.2023,
      "step": 43
    },
    {
      "epoch": 0.25997045790251105,
      "grad_norm": 11.844979286193848,
      "learning_rate": 9.230476262104677e-05,
      "loss": 4.1234,
      "step": 44
    },
    {
      "epoch": 0.2658788774002954,
      "grad_norm": 8.362876892089844,
      "learning_rate": 9.185832391312644e-05,
      "loss": 3.7978,
      "step": 45
    },
    {
      "epoch": 0.2717872968980798,
      "grad_norm": 8.686746597290039,
      "learning_rate": 9.140044155740101e-05,
      "loss": 4.0384,
      "step": 46
    },
    {
      "epoch": 0.2776957163958641,
      "grad_norm": 8.486406326293945,
      "learning_rate": 9.093124073433463e-05,
      "loss": 3.8218,
      "step": 47
    },
    {
      "epoch": 0.28360413589364847,
      "grad_norm": 11.87731647491455,
      "learning_rate": 9.045084971874738e-05,
      "loss": 3.2001,
      "step": 48
    },
    {
      "epoch": 0.2895125553914328,
      "grad_norm": 7.831921100616455,
      "learning_rate": 8.995939984474624e-05,
      "loss": 3.533,
      "step": 49
    },
    {
      "epoch": 0.29542097488921715,
      "grad_norm": 12.459837913513184,
      "learning_rate": 8.945702546981969e-05,
      "loss": 3.2268,
      "step": 50
    },
    {
      "epoch": 0.29542097488921715,
      "eval_loss": 1.0215978622436523,
      "eval_runtime": 21.0397,
      "eval_samples_per_second": 13.593,
      "eval_steps_per_second": 3.422,
      "step": 50
    }
  ],
  "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": 7.15511889395712e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}