{
  "best_metric": 7.173201084136963,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.12254901960784313,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0024509803921568627,
      "grad_norm": 9.625750541687012,
      "learning_rate": 5e-05,
      "loss": 8.8526,
      "step": 1
    },
    {
      "epoch": 0.0024509803921568627,
      "eval_loss": 7.889531135559082,
      "eval_runtime": 0.3576,
      "eval_samples_per_second": 139.825,
      "eval_steps_per_second": 36.354,
      "step": 1
    },
    {
      "epoch": 0.004901960784313725,
      "grad_norm": 5.023439407348633,
      "learning_rate": 0.0001,
      "loss": 8.2542,
      "step": 2
    },
    {
      "epoch": 0.007352941176470588,
      "grad_norm": 5.015538215637207,
      "learning_rate": 9.990365154573717e-05,
      "loss": 8.4811,
      "step": 3
    },
    {
      "epoch": 0.00980392156862745,
      "grad_norm": 3.248521327972412,
      "learning_rate": 9.961501876182148e-05,
      "loss": 8.002,
      "step": 4
    },
    {
      "epoch": 0.012254901960784314,
      "grad_norm": 2.9420642852783203,
      "learning_rate": 9.913533761814537e-05,
      "loss": 7.9323,
      "step": 5
    },
    {
      "epoch": 0.014705882352941176,
      "grad_norm": 2.4188315868377686,
      "learning_rate": 9.846666218300807e-05,
      "loss": 7.5659,
      "step": 6
    },
    {
      "epoch": 0.01715686274509804,
      "grad_norm": 2.414440631866455,
      "learning_rate": 9.761185582727977e-05,
      "loss": 7.4863,
      "step": 7
    },
    {
      "epoch": 0.0196078431372549,
      "grad_norm": 2.3313796520233154,
      "learning_rate": 9.657457896300791e-05,
      "loss": 7.4965,
      "step": 8
    },
    {
      "epoch": 0.022058823529411766,
      "grad_norm": 1.9911783933639526,
      "learning_rate": 9.535927336897098e-05,
      "loss": 7.2629,
      "step": 9
    },
    {
      "epoch": 0.024509803921568627,
      "grad_norm": 1.8694437742233276,
      "learning_rate": 9.397114317029975e-05,
      "loss": 6.973,
      "step": 10
    },
    {
      "epoch": 0.02696078431372549,
      "grad_norm": 1.8836764097213745,
      "learning_rate": 9.241613255361455e-05,
      "loss": 6.9858,
      "step": 11
    },
    {
      "epoch": 0.029411764705882353,
      "grad_norm": 1.952439546585083,
      "learning_rate": 9.070090031310558e-05,
      "loss": 7.0427,
      "step": 12
    },
    {
      "epoch": 0.031862745098039214,
      "grad_norm": 4.279866695404053,
      "learning_rate": 8.883279133655399e-05,
      "loss": 7.814,
      "step": 13
    },
    {
      "epoch": 0.03431372549019608,
      "grad_norm": 3.3466460704803467,
      "learning_rate": 8.681980515339464e-05,
      "loss": 7.9276,
      "step": 14
    },
    {
      "epoch": 0.03676470588235294,
      "grad_norm": 2.222371816635132,
      "learning_rate": 8.467056167950311e-05,
      "loss": 7.7675,
      "step": 15
    },
    {
      "epoch": 0.0392156862745098,
      "grad_norm": 1.613579273223877,
      "learning_rate": 8.239426430539243e-05,
      "loss": 7.6608,
      "step": 16
    },
    {
      "epoch": 0.041666666666666664,
      "grad_norm": 1.416901707649231,
      "learning_rate": 8.000066048588211e-05,
      "loss": 7.4629,
      "step": 17
    },
    {
      "epoch": 0.04411764705882353,
      "grad_norm": 1.302959680557251,
      "learning_rate": 7.75e-05,
      "loss": 7.4589,
      "step": 18
    },
    {
      "epoch": 0.04656862745098039,
      "grad_norm": 1.200455665588379,
      "learning_rate": 7.490299105985507e-05,
      "loss": 7.3293,
      "step": 19
    },
    {
      "epoch": 0.049019607843137254,
      "grad_norm": 1.1874973773956299,
      "learning_rate": 7.222075445642904e-05,
      "loss": 7.1817,
      "step": 20
    },
    {
      "epoch": 0.051470588235294115,
      "grad_norm": 1.3522136211395264,
      "learning_rate": 6.946477593864228e-05,
      "loss": 7.0447,
      "step": 21
    },
    {
      "epoch": 0.05392156862745098,
      "grad_norm": 1.3078893423080444,
      "learning_rate": 6.664685702961344e-05,
      "loss": 7.041,
      "step": 22
    },
    {
      "epoch": 0.056372549019607844,
      "grad_norm": 1.2533669471740723,
      "learning_rate": 6.377906449072578e-05,
      "loss": 6.7884,
      "step": 23
    },
    {
      "epoch": 0.058823529411764705,
      "grad_norm": 1.1526771783828735,
      "learning_rate": 6.087367864990233e-05,
      "loss": 6.8752,
      "step": 24
    },
    {
      "epoch": 0.061274509803921566,
      "grad_norm": 1.6346200704574585,
      "learning_rate": 5.794314081535644e-05,
      "loss": 6.5119,
      "step": 25
    },
    {
      "epoch": 0.061274509803921566,
      "eval_loss": 7.274782180786133,
      "eval_runtime": 0.3562,
      "eval_samples_per_second": 140.38,
      "eval_steps_per_second": 36.499,
      "step": 25
    },
    {
      "epoch": 0.06372549019607843,
      "grad_norm": 2.4334850311279297,
      "learning_rate": 5.500000000000001e-05,
      "loss": 7.5853,
      "step": 26
    },
    {
      "epoch": 0.0661764705882353,
      "grad_norm": 1.9980462789535522,
      "learning_rate": 5.205685918464356e-05,
      "loss": 7.6894,
      "step": 27
    },
    {
      "epoch": 0.06862745098039216,
      "grad_norm": 1.1127245426177979,
      "learning_rate": 4.912632135009769e-05,
      "loss": 7.4654,
      "step": 28
    },
    {
      "epoch": 0.07107843137254902,
      "grad_norm": 1.1269689798355103,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 7.516,
      "step": 29
    },
    {
      "epoch": 0.07352941176470588,
      "grad_norm": 0.969700813293457,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 7.3744,
      "step": 30
    },
    {
      "epoch": 0.07598039215686274,
      "grad_norm": 0.9497419595718384,
      "learning_rate": 4.053522406135775e-05,
      "loss": 7.33,
      "step": 31
    },
    {
      "epoch": 0.0784313725490196,
      "grad_norm": 0.9529443979263306,
      "learning_rate": 3.777924554357096e-05,
      "loss": 7.2131,
      "step": 32
    },
    {
      "epoch": 0.08088235294117647,
      "grad_norm": 0.9932823181152344,
      "learning_rate": 3.509700894014496e-05,
      "loss": 7.0009,
      "step": 33
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 0.9452614784240723,
      "learning_rate": 3.250000000000001e-05,
      "loss": 6.7679,
      "step": 34
    },
    {
      "epoch": 0.0857843137254902,
      "grad_norm": 0.9876568913459778,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 6.7409,
      "step": 35
    },
    {
      "epoch": 0.08823529411764706,
      "grad_norm": 0.9435369372367859,
      "learning_rate": 2.760573569460757e-05,
      "loss": 6.7302,
      "step": 36
    },
    {
      "epoch": 0.09068627450980392,
      "grad_norm": 1.037487506866455,
      "learning_rate": 2.53294383204969e-05,
      "loss": 6.665,
      "step": 37
    },
    {
      "epoch": 0.09313725490196079,
      "grad_norm": 1.9251594543457031,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 7.3112,
      "step": 38
    },
    {
      "epoch": 0.09558823529411764,
      "grad_norm": 2.173351526260376,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 7.5422,
      "step": 39
    },
    {
      "epoch": 0.09803921568627451,
      "grad_norm": 1.453737497329712,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 7.2394,
      "step": 40
    },
    {
      "epoch": 0.10049019607843138,
      "grad_norm": 1.0192174911499023,
      "learning_rate": 1.758386744638546e-05,
      "loss": 7.4375,
      "step": 41
    },
    {
      "epoch": 0.10294117647058823,
      "grad_norm": 1.0053462982177734,
      "learning_rate": 1.602885682970026e-05,
      "loss": 7.3853,
      "step": 42
    },
    {
      "epoch": 0.1053921568627451,
      "grad_norm": 1.0146454572677612,
      "learning_rate": 1.464072663102903e-05,
      "loss": 7.2052,
      "step": 43
    },
    {
      "epoch": 0.10784313725490197,
      "grad_norm": 0.9978232979774475,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 7.1877,
      "step": 44
    },
    {
      "epoch": 0.11029411764705882,
      "grad_norm": 0.906777024269104,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 7.0487,
      "step": 45
    },
    {
      "epoch": 0.11274509803921569,
      "grad_norm": 0.9139236211776733,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 7.0347,
      "step": 46
    },
    {
      "epoch": 0.11519607843137254,
      "grad_norm": 0.8226746320724487,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 6.9112,
      "step": 47
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 0.8334608674049377,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 6.8026,
      "step": 48
    },
    {
      "epoch": 0.12009803921568628,
      "grad_norm": 0.9400653839111328,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 6.6872,
      "step": 49
    },
    {
      "epoch": 0.12254901960784313,
      "grad_norm": 1.1902639865875244,
      "learning_rate": 1e-05,
      "loss": 6.3615,
      "step": 50
    },
    {
      "epoch": 0.12254901960784313,
      "eval_loss": 7.173201084136963,
      "eval_runtime": 0.3489,
      "eval_samples_per_second": 143.317,
      "eval_steps_per_second": 37.263,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 238684194471936.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}