{
  "best_metric": 0.0002391961170360446,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.2062780269058295,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02391629297458894,
      "grad_norm": 0.5000861883163452,
      "learning_rate": 5e-05,
      "loss": 0.0601,
      "step": 1
    },
    {
      "epoch": 0.02391629297458894,
      "eval_loss": 0.1901516318321228,
      "eval_runtime": 4.4167,
      "eval_samples_per_second": 11.321,
      "eval_steps_per_second": 2.943,
      "step": 1
    },
    {
      "epoch": 0.04783258594917788,
      "grad_norm": 0.9140944480895996,
      "learning_rate": 0.0001,
      "loss": 0.0932,
      "step": 2
    },
    {
      "epoch": 0.07174887892376682,
      "grad_norm": 0.46170955896377563,
      "learning_rate": 9.990365154573717e-05,
      "loss": 0.0591,
      "step": 3
    },
    {
      "epoch": 0.09566517189835576,
      "grad_norm": 0.21453425288200378,
      "learning_rate": 9.961501876182148e-05,
      "loss": 0.0169,
      "step": 4
    },
    {
      "epoch": 0.11958146487294469,
      "grad_norm": 0.10587561875581741,
      "learning_rate": 9.913533761814537e-05,
      "loss": 0.016,
      "step": 5
    },
    {
      "epoch": 0.14349775784753363,
      "grad_norm": 0.10676142573356628,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.0105,
      "step": 6
    },
    {
      "epoch": 0.16741405082212257,
      "grad_norm": 0.09449061751365662,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.0077,
      "step": 7
    },
    {
      "epoch": 0.19133034379671152,
      "grad_norm": 0.12052935361862183,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.0112,
      "step": 8
    },
    {
      "epoch": 0.21524663677130046,
      "grad_norm": 0.08228503167629242,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.0058,
      "step": 9
    },
    {
      "epoch": 0.23916292974588937,
      "grad_norm": 0.11513187736272812,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.0068,
      "step": 10
    },
    {
      "epoch": 0.26307922272047835,
      "grad_norm": 0.09261412918567657,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.0168,
      "step": 11
    },
    {
      "epoch": 0.28699551569506726,
      "grad_norm": 0.051280997693538666,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.0034,
      "step": 12
    },
    {
      "epoch": 0.3109118086696562,
      "grad_norm": 0.03256010264158249,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.0031,
      "step": 13
    },
    {
      "epoch": 0.33482810164424515,
      "grad_norm": 0.04068237543106079,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0025,
      "step": 14
    },
    {
      "epoch": 0.35874439461883406,
      "grad_norm": 0.03880110755562782,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.0025,
      "step": 15
    },
    {
      "epoch": 0.38266068759342303,
      "grad_norm": 0.025225255638360977,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.0019,
      "step": 16
    },
    {
      "epoch": 0.40657698056801195,
      "grad_norm": 0.045391716063022614,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.002,
      "step": 17
    },
    {
      "epoch": 0.4304932735426009,
      "grad_norm": 0.03613187372684479,
      "learning_rate": 7.75e-05,
      "loss": 0.0014,
      "step": 18
    },
    {
      "epoch": 0.45440956651718983,
      "grad_norm": 0.03006964921951294,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.0013,
      "step": 19
    },
    {
      "epoch": 0.47832585949177875,
      "grad_norm": 0.039465390145778656,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.0016,
      "step": 20
    },
    {
      "epoch": 0.5022421524663677,
      "grad_norm": 0.05139923840761185,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.0051,
      "step": 21
    },
    {
      "epoch": 0.5261584454409567,
      "grad_norm": 0.03245363384485245,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.001,
      "step": 22
    },
    {
      "epoch": 0.5500747384155455,
      "grad_norm": 0.023098977282643318,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.0009,
      "step": 23
    },
    {
      "epoch": 0.5739910313901345,
      "grad_norm": 0.02532481960952282,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.0008,
      "step": 24
    },
    {
      "epoch": 0.5979073243647235,
      "grad_norm": 0.022385241463780403,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.0008,
      "step": 25
    },
    {
      "epoch": 0.5979073243647235,
      "eval_loss": 0.0008296275627799332,
      "eval_runtime": 4.5093,
      "eval_samples_per_second": 11.088,
      "eval_steps_per_second": 2.883,
      "step": 25
    },
    {
      "epoch": 0.6218236173393124,
      "grad_norm": 0.012360863387584686,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0005,
      "step": 26
    },
    {
      "epoch": 0.6457399103139013,
      "grad_norm": 0.030168309807777405,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.001,
      "step": 27
    },
    {
      "epoch": 0.6696562032884903,
      "grad_norm": 0.01952563412487507,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.0006,
      "step": 28
    },
    {
      "epoch": 0.6935724962630793,
      "grad_norm": 0.025816479697823524,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.0001,
      "step": 29
    },
    {
      "epoch": 0.7174887892376681,
      "grad_norm": 0.023305699229240417,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.0003,
      "step": 30
    },
    {
      "epoch": 0.7414050822122571,
      "grad_norm": 0.042270027101039886,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.004,
      "step": 31
    },
    {
      "epoch": 0.7653213751868461,
      "grad_norm": 0.013639895245432854,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.0011,
      "step": 32
    },
    {
      "epoch": 0.7892376681614349,
      "grad_norm": 0.015320922248065472,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.0009,
      "step": 33
    },
    {
      "epoch": 0.8131539611360239,
      "grad_norm": 0.017550518736243248,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.0004,
      "step": 34
    },
    {
      "epoch": 0.8370702541106129,
      "grad_norm": 0.018104810267686844,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.0007,
      "step": 35
    },
    {
      "epoch": 0.8609865470852018,
      "grad_norm": 0.024184156209230423,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.0011,
      "step": 36
    },
    {
      "epoch": 0.8849028400597907,
      "grad_norm": 0.026356741786003113,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.001,
      "step": 37
    },
    {
      "epoch": 0.9088191330343797,
      "grad_norm": 0.014368100091814995,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.0003,
      "step": 38
    },
    {
      "epoch": 0.9327354260089686,
      "grad_norm": 0.01398097537457943,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.0003,
      "step": 39
    },
    {
      "epoch": 0.9566517189835575,
      "grad_norm": 0.01466523390263319,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.0001,
      "step": 40
    },
    {
      "epoch": 0.9805680119581465,
      "grad_norm": 0.014875360764563084,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.0002,
      "step": 41
    },
    {
      "epoch": 1.014947683109118,
      "grad_norm": 0.02478068880736828,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.0065,
      "step": 42
    },
    {
      "epoch": 1.038863976083707,
      "grad_norm": 0.009487264789640903,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.0005,
      "step": 43
    },
    {
      "epoch": 1.062780269058296,
      "grad_norm": 0.010159480385482311,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.0004,
      "step": 44
    },
    {
      "epoch": 1.086696562032885,
      "grad_norm": 0.009533469565212727,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.0003,
      "step": 45
    },
    {
      "epoch": 1.1106128550074739,
      "grad_norm": 0.008421096950769424,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.0002,
      "step": 46
    },
    {
      "epoch": 1.1345291479820627,
      "grad_norm": 0.00984017550945282,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.0003,
      "step": 47
    },
    {
      "epoch": 1.1584454409566518,
      "grad_norm": 0.014092501252889633,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.0002,
      "step": 48
    },
    {
      "epoch": 1.1823617339312407,
      "grad_norm": 0.003745349822565913,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.0001,
      "step": 49
    },
    {
      "epoch": 1.2062780269058295,
      "grad_norm": 0.0038105223793536425,
      "learning_rate": 1e-05,
      "loss": 0.0001,
      "step": 50
    },
    {
      "epoch": 1.2062780269058295,
      "eval_loss": 0.0002391961170360446,
      "eval_runtime": 4.1649,
      "eval_samples_per_second": 12.005,
      "eval_steps_per_second": 3.121,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.757792457246638e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}