{
  "best_metric": 0.328974187374115,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.5637773079633545,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01127554615926709,
      "grad_norm": 13.466485023498535,
      "learning_rate": 5e-05,
      "loss": 13.4143,
      "step": 1
    },
    {
      "epoch": 0.01127554615926709,
      "eval_loss": 11.712335586547852,
      "eval_runtime": 9.4734,
      "eval_samples_per_second": 5.278,
      "eval_steps_per_second": 1.372,
      "step": 1
    },
    {
      "epoch": 0.02255109231853418,
      "grad_norm": 13.599178314208984,
      "learning_rate": 0.0001,
      "loss": 13.1612,
      "step": 2
    },
    {
      "epoch": 0.03382663847780127,
      "grad_norm": 13.578472137451172,
      "learning_rate": 9.990365154573717e-05,
      "loss": 12.7346,
      "step": 3
    },
    {
      "epoch": 0.04510218463706836,
      "grad_norm": 10.256945610046387,
      "learning_rate": 9.961501876182148e-05,
      "loss": 10.6121,
      "step": 4
    },
    {
      "epoch": 0.05637773079633545,
      "grad_norm": 9.487074851989746,
      "learning_rate": 9.913533761814537e-05,
      "loss": 8.4671,
      "step": 5
    },
    {
      "epoch": 0.06765327695560254,
      "grad_norm": 15.24462604522705,
      "learning_rate": 9.846666218300807e-05,
      "loss": 5.9039,
      "step": 6
    },
    {
      "epoch": 0.07892882311486962,
      "grad_norm": 16.493919372558594,
      "learning_rate": 9.761185582727977e-05,
      "loss": 4.4318,
      "step": 7
    },
    {
      "epoch": 0.09020436927413672,
      "grad_norm": 12.750604629516602,
      "learning_rate": 9.657457896300791e-05,
      "loss": 2.9455,
      "step": 8
    },
    {
      "epoch": 0.1014799154334038,
      "grad_norm": 64.26519012451172,
      "learning_rate": 9.535927336897098e-05,
      "loss": 2.5642,
      "step": 9
    },
    {
      "epoch": 0.1127554615926709,
      "grad_norm": 28.544361114501953,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.8061,
      "step": 10
    },
    {
      "epoch": 0.12403100775193798,
      "grad_norm": 5.757697105407715,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.4737,
      "step": 11
    },
    {
      "epoch": 0.13530655391120508,
      "grad_norm": 3.7276666164398193,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.4577,
      "step": 12
    },
    {
      "epoch": 0.14658210007047218,
      "grad_norm": 21.954557418823242,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.8196,
      "step": 13
    },
    {
      "epoch": 0.15785764622973925,
      "grad_norm": 9.83080005645752,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.5569,
      "step": 14
    },
    {
      "epoch": 0.16913319238900634,
      "grad_norm": 2.6958820819854736,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.3743,
      "step": 15
    },
    {
      "epoch": 0.18040873854827344,
      "grad_norm": 3.052065849304199,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.4194,
      "step": 16
    },
    {
      "epoch": 0.1916842847075405,
      "grad_norm": 3.0218756198883057,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.3867,
      "step": 17
    },
    {
      "epoch": 0.2029598308668076,
      "grad_norm": 1.5468084812164307,
      "learning_rate": 7.75e-05,
      "loss": 0.3578,
      "step": 18
    },
    {
      "epoch": 0.2142353770260747,
      "grad_norm": 4.755566596984863,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.3618,
      "step": 19
    },
    {
      "epoch": 0.2255109231853418,
      "grad_norm": 1.2197436094284058,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.3533,
      "step": 20
    },
    {
      "epoch": 0.23678646934460887,
      "grad_norm": 6.478429794311523,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.4427,
      "step": 21
    },
    {
      "epoch": 0.24806201550387597,
      "grad_norm": 2.4955391883850098,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.3681,
      "step": 22
    },
    {
      "epoch": 0.25933756166314303,
      "grad_norm": 8.185530662536621,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.4906,
      "step": 23
    },
    {
      "epoch": 0.27061310782241016,
      "grad_norm": 7.43537712097168,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.5079,
      "step": 24
    },
    {
      "epoch": 0.28188865398167723,
      "grad_norm": 3.7920496463775635,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.3621,
      "step": 25
    },
    {
      "epoch": 0.28188865398167723,
      "eval_loss": 0.3736724555492401,
      "eval_runtime": 9.4175,
      "eval_samples_per_second": 5.309,
      "eval_steps_per_second": 1.38,
      "step": 25
    },
    {
      "epoch": 0.29316420014094435,
      "grad_norm": 3.929647207260132,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.3929,
      "step": 26
    },
    {
      "epoch": 0.3044397463002114,
      "grad_norm": 3.0069169998168945,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.3753,
      "step": 27
    },
    {
      "epoch": 0.3157152924594785,
      "grad_norm": 0.7478533983230591,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.3487,
      "step": 28
    },
    {
      "epoch": 0.3269908386187456,
      "grad_norm": 0.6217486262321472,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.3633,
      "step": 29
    },
    {
      "epoch": 0.3382663847780127,
      "grad_norm": 0.8256338834762573,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.3486,
      "step": 30
    },
    {
      "epoch": 0.34954193093727975,
      "grad_norm": 4.838144302368164,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.4128,
      "step": 31
    },
    {
      "epoch": 0.3608174770965469,
      "grad_norm": 4.683679103851318,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.3967,
      "step": 32
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 2.6548237800598145,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.3645,
      "step": 33
    },
    {
      "epoch": 0.383368569415081,
      "grad_norm": 1.9402390718460083,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.3623,
      "step": 34
    },
    {
      "epoch": 0.39464411557434814,
      "grad_norm": 3.5657272338867188,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.3842,
      "step": 35
    },
    {
      "epoch": 0.4059196617336152,
      "grad_norm": 2.6976256370544434,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.3498,
      "step": 36
    },
    {
      "epoch": 0.41719520789288234,
      "grad_norm": 1.291695475578308,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.3353,
      "step": 37
    },
    {
      "epoch": 0.4284707540521494,
      "grad_norm": 1.30393385887146,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.3776,
      "step": 38
    },
    {
      "epoch": 0.4397463002114165,
      "grad_norm": 4.662352085113525,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.4494,
      "step": 39
    },
    {
      "epoch": 0.4510218463706836,
      "grad_norm": 3.815720319747925,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.4232,
      "step": 40
    },
    {
      "epoch": 0.46229739252995067,
      "grad_norm": 3.353482961654663,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.4129,
      "step": 41
    },
    {
      "epoch": 0.47357293868921774,
      "grad_norm": 3.1307156085968018,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.3914,
      "step": 42
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 2.4309184551239014,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.3662,
      "step": 43
    },
    {
      "epoch": 0.49612403100775193,
      "grad_norm": 2.453277111053467,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.3712,
      "step": 44
    },
    {
      "epoch": 0.507399577167019,
      "grad_norm": 0.6218744516372681,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.3338,
      "step": 45
    },
    {
      "epoch": 0.5186751233262861,
      "grad_norm": 1.4151079654693604,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.3575,
      "step": 46
    },
    {
      "epoch": 0.5299506694855532,
      "grad_norm": 1.0527911186218262,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.3386,
      "step": 47
    },
    {
      "epoch": 0.5412262156448203,
      "grad_norm": 1.8253545761108398,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.3542,
      "step": 48
    },
    {
      "epoch": 0.5525017618040874,
      "grad_norm": 1.5399640798568726,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.3583,
      "step": 49
    },
    {
      "epoch": 0.5637773079633545,
      "grad_norm": 1.680297613143921,
      "learning_rate": 1e-05,
      "loss": 0.3236,
      "step": 50
    },
    {
      "epoch": 0.5637773079633545,
      "eval_loss": 0.328974187374115,
      "eval_runtime": 9.4029,
      "eval_samples_per_second": 5.318,
      "eval_steps_per_second": 1.383,
      "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": 3.7108326150334054e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}