{
  "best_metric": 6.804412841796875,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.015535187199005748,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00031070374398011494,
      "grad_norm": 0.9489419460296631,
      "learning_rate": 5e-05,
      "loss": 6.9511,
      "step": 1
    },
    {
      "epoch": 0.00031070374398011494,
      "eval_loss": 6.953388690948486,
      "eval_runtime": 0.3922,
      "eval_samples_per_second": 127.499,
      "eval_steps_per_second": 33.15,
      "step": 1
    },
    {
      "epoch": 0.0006214074879602299,
      "grad_norm": 0.9570797085762024,
      "learning_rate": 0.0001,
      "loss": 6.9527,
      "step": 2
    },
    {
      "epoch": 0.0009321112319403449,
      "grad_norm": 0.997393786907196,
      "learning_rate": 9.990365154573717e-05,
      "loss": 6.9529,
      "step": 3
    },
    {
      "epoch": 0.0012428149759204598,
      "grad_norm": 0.9764484763145447,
      "learning_rate": 9.961501876182148e-05,
      "loss": 6.943,
      "step": 4
    },
    {
      "epoch": 0.0015535187199005747,
      "grad_norm": 0.9417179822921753,
      "learning_rate": 9.913533761814537e-05,
      "loss": 6.9405,
      "step": 5
    },
    {
      "epoch": 0.0018642224638806897,
      "grad_norm": 0.9699556827545166,
      "learning_rate": 9.846666218300807e-05,
      "loss": 6.9342,
      "step": 6
    },
    {
      "epoch": 0.0021749262078608047,
      "grad_norm": 0.9726319909095764,
      "learning_rate": 9.761185582727977e-05,
      "loss": 6.9243,
      "step": 7
    },
    {
      "epoch": 0.0024856299518409195,
      "grad_norm": 0.9405907988548279,
      "learning_rate": 9.657457896300791e-05,
      "loss": 6.9239,
      "step": 8
    },
    {
      "epoch": 0.0027963336958210347,
      "grad_norm": 0.988777220249176,
      "learning_rate": 9.535927336897098e-05,
      "loss": 6.9198,
      "step": 9
    },
    {
      "epoch": 0.0031070374398011495,
      "grad_norm": 0.9727218747138977,
      "learning_rate": 9.397114317029975e-05,
      "loss": 6.9108,
      "step": 10
    },
    {
      "epoch": 0.0034177411837812647,
      "grad_norm": 1.006295084953308,
      "learning_rate": 9.241613255361455e-05,
      "loss": 6.9103,
      "step": 11
    },
    {
      "epoch": 0.0037284449277613795,
      "grad_norm": 0.9963254332542419,
      "learning_rate": 9.070090031310558e-05,
      "loss": 6.9044,
      "step": 12
    },
    {
      "epoch": 0.004039148671741494,
      "grad_norm": 0.9690650105476379,
      "learning_rate": 8.883279133655399e-05,
      "loss": 6.9037,
      "step": 13
    },
    {
      "epoch": 0.0043498524157216095,
      "grad_norm": 0.9783103466033936,
      "learning_rate": 8.681980515339464e-05,
      "loss": 6.8951,
      "step": 14
    },
    {
      "epoch": 0.004660556159701725,
      "grad_norm": 1.007731556892395,
      "learning_rate": 8.467056167950311e-05,
      "loss": 6.8898,
      "step": 15
    },
    {
      "epoch": 0.004971259903681839,
      "grad_norm": 1.0209459066390991,
      "learning_rate": 8.239426430539243e-05,
      "loss": 6.8842,
      "step": 16
    },
    {
      "epoch": 0.005281963647661954,
      "grad_norm": 0.9666637778282166,
      "learning_rate": 8.000066048588211e-05,
      "loss": 6.8795,
      "step": 17
    },
    {
      "epoch": 0.005592667391642069,
      "grad_norm": 0.983328640460968,
      "learning_rate": 7.75e-05,
      "loss": 6.8744,
      "step": 18
    },
    {
      "epoch": 0.005903371135622185,
      "grad_norm": 0.9825755953788757,
      "learning_rate": 7.490299105985507e-05,
      "loss": 6.8702,
      "step": 19
    },
    {
      "epoch": 0.006214074879602299,
      "grad_norm": 0.9652051329612732,
      "learning_rate": 7.222075445642904e-05,
      "loss": 6.8662,
      "step": 20
    },
    {
      "epoch": 0.006524778623582414,
      "grad_norm": 0.9733561277389526,
      "learning_rate": 6.946477593864228e-05,
      "loss": 6.8622,
      "step": 21
    },
    {
      "epoch": 0.006835482367562529,
      "grad_norm": 0.9990824460983276,
      "learning_rate": 6.664685702961344e-05,
      "loss": 6.858,
      "step": 22
    },
    {
      "epoch": 0.007146186111542644,
      "grad_norm": 0.9708381295204163,
      "learning_rate": 6.377906449072578e-05,
      "loss": 6.8543,
      "step": 23
    },
    {
      "epoch": 0.007456889855522759,
      "grad_norm": 0.9715843200683594,
      "learning_rate": 6.087367864990233e-05,
      "loss": 6.8534,
      "step": 24
    },
    {
      "epoch": 0.007767593599502874,
      "grad_norm": 0.9847354888916016,
      "learning_rate": 5.794314081535644e-05,
      "loss": 6.8506,
      "step": 25
    },
    {
      "epoch": 0.007767593599502874,
      "eval_loss": 6.8462419509887695,
      "eval_runtime": 0.0798,
      "eval_samples_per_second": 626.959,
      "eval_steps_per_second": 163.009,
      "step": 25
    },
    {
      "epoch": 0.008078297343482988,
      "grad_norm": 1.0122259855270386,
      "learning_rate": 5.500000000000001e-05,
      "loss": 6.8429,
      "step": 26
    },
    {
      "epoch": 0.008389001087463105,
      "grad_norm": 0.98973149061203,
      "learning_rate": 5.205685918464356e-05,
      "loss": 6.8391,
      "step": 27
    },
    {
      "epoch": 0.008699704831443219,
      "grad_norm": 0.9703534245491028,
      "learning_rate": 4.912632135009769e-05,
      "loss": 6.8384,
      "step": 28
    },
    {
      "epoch": 0.009010408575423333,
      "grad_norm": 0.963632345199585,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 6.8381,
      "step": 29
    },
    {
      "epoch": 0.00932111231940345,
      "grad_norm": 0.9653098583221436,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 6.833,
      "step": 30
    },
    {
      "epoch": 0.009631816063383564,
      "grad_norm": 0.9719390273094177,
      "learning_rate": 4.053522406135775e-05,
      "loss": 6.8339,
      "step": 31
    },
    {
      "epoch": 0.009942519807363678,
      "grad_norm": 1.0127551555633545,
      "learning_rate": 3.777924554357096e-05,
      "loss": 6.8262,
      "step": 32
    },
    {
      "epoch": 0.010253223551343794,
      "grad_norm": 0.942281186580658,
      "learning_rate": 3.509700894014496e-05,
      "loss": 6.8296,
      "step": 33
    },
    {
      "epoch": 0.010563927295323908,
      "grad_norm": 0.9893297553062439,
      "learning_rate": 3.250000000000001e-05,
      "loss": 6.8218,
      "step": 34
    },
    {
      "epoch": 0.010874631039304023,
      "grad_norm": 0.9867397546768188,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 6.8176,
      "step": 35
    },
    {
      "epoch": 0.011185334783284139,
      "grad_norm": 0.9858079552650452,
      "learning_rate": 2.760573569460757e-05,
      "loss": 6.8177,
      "step": 36
    },
    {
      "epoch": 0.011496038527264253,
      "grad_norm": 0.9990798830986023,
      "learning_rate": 2.53294383204969e-05,
      "loss": 6.8247,
      "step": 37
    },
    {
      "epoch": 0.01180674227124437,
      "grad_norm": 0.977016806602478,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 6.8215,
      "step": 38
    },
    {
      "epoch": 0.012117446015224484,
      "grad_norm": 0.99068284034729,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 6.8134,
      "step": 39
    },
    {
      "epoch": 0.012428149759204598,
      "grad_norm": 1.0365233421325684,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 6.8113,
      "step": 40
    },
    {
      "epoch": 0.012738853503184714,
      "grad_norm": 0.9768825769424438,
      "learning_rate": 1.758386744638546e-05,
      "loss": 6.8113,
      "step": 41
    },
    {
      "epoch": 0.013049557247164828,
      "grad_norm": 1.002421259880066,
      "learning_rate": 1.602885682970026e-05,
      "loss": 6.8108,
      "step": 42
    },
    {
      "epoch": 0.013360260991144943,
      "grad_norm": 0.974835216999054,
      "learning_rate": 1.464072663102903e-05,
      "loss": 6.8086,
      "step": 43
    },
    {
      "epoch": 0.013670964735125059,
      "grad_norm": 0.9881023168563843,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 6.8085,
      "step": 44
    },
    {
      "epoch": 0.013981668479105173,
      "grad_norm": 0.9756224751472473,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 6.8074,
      "step": 45
    },
    {
      "epoch": 0.014292372223085287,
      "grad_norm": 0.9628235697746277,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 6.8105,
      "step": 46
    },
    {
      "epoch": 0.014603075967065404,
      "grad_norm": 0.9868977665901184,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 6.8046,
      "step": 47
    },
    {
      "epoch": 0.014913779711045518,
      "grad_norm": 0.975204348564148,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 6.8055,
      "step": 48
    },
    {
      "epoch": 0.015224483455025632,
      "grad_norm": 0.9711145162582397,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 6.8068,
      "step": 49
    },
    {
      "epoch": 0.015535187199005748,
      "grad_norm": 0.9790964126586914,
      "learning_rate": 1e-05,
      "loss": 6.8057,
      "step": 50
    },
    {
      "epoch": 0.015535187199005748,
      "eval_loss": 6.804412841796875,
      "eval_runtime": 0.0724,
      "eval_samples_per_second": 690.677,
      "eval_steps_per_second": 179.576,
      "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": 5705957376000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}