{
  "best_metric": 4.192285060882568,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.08279002380213184,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016558004760426368,
      "grad_norm": 974.1483764648438,
      "learning_rate": 5e-05,
      "loss": 52.0556,
      "step": 1
    },
    {
      "epoch": 0.0016558004760426368,
      "eval_loss": 98.47161102294922,
      "eval_runtime": 3.2623,
      "eval_samples_per_second": 15.327,
      "eval_steps_per_second": 3.985,
      "step": 1
    },
    {
      "epoch": 0.0033116009520852735,
      "grad_norm": 1284.825927734375,
      "learning_rate": 0.0001,
      "loss": 66.1523,
      "step": 2
    },
    {
      "epoch": 0.0049674014281279105,
      "grad_norm": 253.6217803955078,
      "learning_rate": 9.990365154573717e-05,
      "loss": 55.1,
      "step": 3
    },
    {
      "epoch": 0.006623201904170547,
      "grad_norm": 186.92532348632812,
      "learning_rate": 9.961501876182148e-05,
      "loss": 44.7275,
      "step": 4
    },
    {
      "epoch": 0.008279002380213184,
      "grad_norm": 223.95616149902344,
      "learning_rate": 9.913533761814537e-05,
      "loss": 37.6232,
      "step": 5
    },
    {
      "epoch": 0.009934802856255821,
      "grad_norm": 238.3695831298828,
      "learning_rate": 9.846666218300807e-05,
      "loss": 23.6101,
      "step": 6
    },
    {
      "epoch": 0.011590603332298458,
      "grad_norm": 237.3712921142578,
      "learning_rate": 9.761185582727977e-05,
      "loss": 7.2874,
      "step": 7
    },
    {
      "epoch": 0.013246403808341094,
      "grad_norm": 11.77100944519043,
      "learning_rate": 9.657457896300791e-05,
      "loss": 5.327,
      "step": 8
    },
    {
      "epoch": 0.014902204284383732,
      "grad_norm": 8.001509666442871,
      "learning_rate": 9.535927336897098e-05,
      "loss": 5.4539,
      "step": 9
    },
    {
      "epoch": 0.01655800476042637,
      "grad_norm": 45.08405685424805,
      "learning_rate": 9.397114317029975e-05,
      "loss": 5.8752,
      "step": 10
    },
    {
      "epoch": 0.018213805236469007,
      "grad_norm": 39.24134826660156,
      "learning_rate": 9.241613255361455e-05,
      "loss": 5.539,
      "step": 11
    },
    {
      "epoch": 0.019869605712511642,
      "grad_norm": 14.146797180175781,
      "learning_rate": 9.070090031310558e-05,
      "loss": 5.2755,
      "step": 12
    },
    {
      "epoch": 0.02152540618855428,
      "grad_norm": 15.426395416259766,
      "learning_rate": 8.883279133655399e-05,
      "loss": 5.8983,
      "step": 13
    },
    {
      "epoch": 0.023181206664596915,
      "grad_norm": 9.675007820129395,
      "learning_rate": 8.681980515339464e-05,
      "loss": 5.4224,
      "step": 14
    },
    {
      "epoch": 0.024837007140639553,
      "grad_norm": 6.938243865966797,
      "learning_rate": 8.467056167950311e-05,
      "loss": 4.7101,
      "step": 15
    },
    {
      "epoch": 0.026492807616682188,
      "grad_norm": 6.639142036437988,
      "learning_rate": 8.239426430539243e-05,
      "loss": 4.8444,
      "step": 16
    },
    {
      "epoch": 0.028148608092724826,
      "grad_norm": 7.042287349700928,
      "learning_rate": 8.000066048588211e-05,
      "loss": 4.6643,
      "step": 17
    },
    {
      "epoch": 0.029804408568767465,
      "grad_norm": 6.891635894775391,
      "learning_rate": 7.75e-05,
      "loss": 4.6337,
      "step": 18
    },
    {
      "epoch": 0.0314602090448101,
      "grad_norm": 6.530301094055176,
      "learning_rate": 7.490299105985507e-05,
      "loss": 4.557,
      "step": 19
    },
    {
      "epoch": 0.03311600952085274,
      "grad_norm": 12.216989517211914,
      "learning_rate": 7.222075445642904e-05,
      "loss": 4.6109,
      "step": 20
    },
    {
      "epoch": 0.03477180999689537,
      "grad_norm": 10.070948600769043,
      "learning_rate": 6.946477593864228e-05,
      "loss": 4.5409,
      "step": 21
    },
    {
      "epoch": 0.036427610472938014,
      "grad_norm": 5.426440715789795,
      "learning_rate": 6.664685702961344e-05,
      "loss": 4.8507,
      "step": 22
    },
    {
      "epoch": 0.03808341094898065,
      "grad_norm": 6.391597270965576,
      "learning_rate": 6.377906449072578e-05,
      "loss": 4.8648,
      "step": 23
    },
    {
      "epoch": 0.039739211425023284,
      "grad_norm": 4.860270023345947,
      "learning_rate": 6.087367864990233e-05,
      "loss": 4.6502,
      "step": 24
    },
    {
      "epoch": 0.04139501190106592,
      "grad_norm": 8.16153335571289,
      "learning_rate": 5.794314081535644e-05,
      "loss": 4.7464,
      "step": 25
    },
    {
      "epoch": 0.04139501190106592,
      "eval_loss": 4.563230037689209,
      "eval_runtime": 3.1876,
      "eval_samples_per_second": 15.686,
      "eval_steps_per_second": 4.078,
      "step": 25
    },
    {
      "epoch": 0.04305081237710856,
      "grad_norm": 13.002767562866211,
      "learning_rate": 5.500000000000001e-05,
      "loss": 5.5723,
      "step": 26
    },
    {
      "epoch": 0.044706612853151195,
      "grad_norm": 11.251646995544434,
      "learning_rate": 5.205685918464356e-05,
      "loss": 4.9891,
      "step": 27
    },
    {
      "epoch": 0.04636241332919383,
      "grad_norm": 9.315027236938477,
      "learning_rate": 4.912632135009769e-05,
      "loss": 4.458,
      "step": 28
    },
    {
      "epoch": 0.04801821380523647,
      "grad_norm": 7.1844916343688965,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 4.5533,
      "step": 29
    },
    {
      "epoch": 0.04967401428127911,
      "grad_norm": 6.5660529136657715,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 4.3428,
      "step": 30
    },
    {
      "epoch": 0.05132981475732174,
      "grad_norm": 4.740668773651123,
      "learning_rate": 4.053522406135775e-05,
      "loss": 4.3628,
      "step": 31
    },
    {
      "epoch": 0.052985615233364376,
      "grad_norm": 4.048844337463379,
      "learning_rate": 3.777924554357096e-05,
      "loss": 4.4662,
      "step": 32
    },
    {
      "epoch": 0.05464141570940702,
      "grad_norm": 5.773531913757324,
      "learning_rate": 3.509700894014496e-05,
      "loss": 4.2979,
      "step": 33
    },
    {
      "epoch": 0.05629721618544965,
      "grad_norm": 5.650273323059082,
      "learning_rate": 3.250000000000001e-05,
      "loss": 4.2232,
      "step": 34
    },
    {
      "epoch": 0.05795301666149229,
      "grad_norm": 7.855549335479736,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 4.5748,
      "step": 35
    },
    {
      "epoch": 0.05960881713753493,
      "grad_norm": 6.9513163566589355,
      "learning_rate": 2.760573569460757e-05,
      "loss": 4.5689,
      "step": 36
    },
    {
      "epoch": 0.061264617613577564,
      "grad_norm": 7.774838447570801,
      "learning_rate": 2.53294383204969e-05,
      "loss": 4.7269,
      "step": 37
    },
    {
      "epoch": 0.0629204180896202,
      "grad_norm": 4.152009963989258,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 4.7467,
      "step": 38
    },
    {
      "epoch": 0.06457621856566284,
      "grad_norm": 5.257497787475586,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 4.7762,
      "step": 39
    },
    {
      "epoch": 0.06623201904170548,
      "grad_norm": 5.551874160766602,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 4.1862,
      "step": 40
    },
    {
      "epoch": 0.06788781951774811,
      "grad_norm": 4.915943622589111,
      "learning_rate": 1.758386744638546e-05,
      "loss": 4.1091,
      "step": 41
    },
    {
      "epoch": 0.06954361999379075,
      "grad_norm": 4.883779525756836,
      "learning_rate": 1.602885682970026e-05,
      "loss": 4.2785,
      "step": 42
    },
    {
      "epoch": 0.07119942046983338,
      "grad_norm": 3.6552951335906982,
      "learning_rate": 1.464072663102903e-05,
      "loss": 4.1205,
      "step": 43
    },
    {
      "epoch": 0.07285522094587603,
      "grad_norm": 3.0899415016174316,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 4.1338,
      "step": 44
    },
    {
      "epoch": 0.07451102142191866,
      "grad_norm": 3.9144699573516846,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 4.1751,
      "step": 45
    },
    {
      "epoch": 0.0761668218979613,
      "grad_norm": 3.444018602371216,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 4.1967,
      "step": 46
    },
    {
      "epoch": 0.07782262237400393,
      "grad_norm": 6.361255168914795,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 4.4975,
      "step": 47
    },
    {
      "epoch": 0.07947842285004657,
      "grad_norm": 4.913413047790527,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 4.4034,
      "step": 48
    },
    {
      "epoch": 0.0811342233260892,
      "grad_norm": 5.116950988769531,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 4.42,
      "step": 49
    },
    {
      "epoch": 0.08279002380213184,
      "grad_norm": 8.649046897888184,
      "learning_rate": 1e-05,
      "loss": 4.4341,
      "step": 50
    },
    {
      "epoch": 0.08279002380213184,
      "eval_loss": 4.192285060882568,
      "eval_runtime": 3.273,
      "eval_samples_per_second": 15.277,
      "eval_steps_per_second": 3.972,
      "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": 6.174479344467968e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}