{
  "best_metric": 0.11276046931743622,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.5194805194805194,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01038961038961039,
      "grad_norm": 29.42839241027832,
      "learning_rate": 5e-05,
      "loss": 12.5793,
      "step": 1
    },
    {
      "epoch": 0.01038961038961039,
      "eval_loss": 12.91598129272461,
      "eval_runtime": 1.2245,
      "eval_samples_per_second": 40.834,
      "eval_steps_per_second": 10.617,
      "step": 1
    },
    {
      "epoch": 0.02077922077922078,
      "grad_norm": 27.93857765197754,
      "learning_rate": 0.0001,
      "loss": 12.6222,
      "step": 2
    },
    {
      "epoch": 0.03116883116883117,
      "grad_norm": 29.941917419433594,
      "learning_rate": 9.990365154573717e-05,
      "loss": 11.1105,
      "step": 3
    },
    {
      "epoch": 0.04155844155844156,
      "grad_norm": 16.940210342407227,
      "learning_rate": 9.961501876182148e-05,
      "loss": 6.5359,
      "step": 4
    },
    {
      "epoch": 0.05194805194805195,
      "grad_norm": 13.729902267456055,
      "learning_rate": 9.913533761814537e-05,
      "loss": 4.2541,
      "step": 5
    },
    {
      "epoch": 0.06233766233766234,
      "grad_norm": 11.259726524353027,
      "learning_rate": 9.846666218300807e-05,
      "loss": 2.5924,
      "step": 6
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": 7.546064376831055,
      "learning_rate": 9.761185582727977e-05,
      "loss": 1.6459,
      "step": 7
    },
    {
      "epoch": 0.08311688311688312,
      "grad_norm": 6.118514537811279,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.9988,
      "step": 8
    },
    {
      "epoch": 0.09350649350649351,
      "grad_norm": 24.73691177368164,
      "learning_rate": 9.535927336897098e-05,
      "loss": 1.0609,
      "step": 9
    },
    {
      "epoch": 0.1038961038961039,
      "grad_norm": 6.850076198577881,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.6934,
      "step": 10
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 2.605048179626465,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.6198,
      "step": 11
    },
    {
      "epoch": 0.12467532467532468,
      "grad_norm": 2.4998886585235596,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.62,
      "step": 12
    },
    {
      "epoch": 0.13506493506493505,
      "grad_norm": 0.8932002186775208,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.5783,
      "step": 13
    },
    {
      "epoch": 0.14545454545454545,
      "grad_norm": 0.9613502025604248,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.5604,
      "step": 14
    },
    {
      "epoch": 0.15584415584415584,
      "grad_norm": 1.1828709840774536,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.5304,
      "step": 15
    },
    {
      "epoch": 0.16623376623376623,
      "grad_norm": 1.1727975606918335,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.5029,
      "step": 16
    },
    {
      "epoch": 0.17662337662337663,
      "grad_norm": 2.1680853366851807,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.4585,
      "step": 17
    },
    {
      "epoch": 0.18701298701298702,
      "grad_norm": 2.0632667541503906,
      "learning_rate": 7.75e-05,
      "loss": 0.3572,
      "step": 18
    },
    {
      "epoch": 0.1974025974025974,
      "grad_norm": 2.8442530632019043,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.3188,
      "step": 19
    },
    {
      "epoch": 0.2077922077922078,
      "grad_norm": 3.280733585357666,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.2639,
      "step": 20
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 4.4080810546875,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.3252,
      "step": 21
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 3.1304285526275635,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.2713,
      "step": 22
    },
    {
      "epoch": 0.23896103896103896,
      "grad_norm": 3.426896095275879,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.2683,
      "step": 23
    },
    {
      "epoch": 0.24935064935064935,
      "grad_norm": 2.8846006393432617,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.231,
      "step": 24
    },
    {
      "epoch": 0.2597402597402597,
      "grad_norm": 1.9578534364700317,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.2224,
      "step": 25
    },
    {
      "epoch": 0.2597402597402597,
      "eval_loss": 0.21341951191425323,
      "eval_runtime": 1.2605,
      "eval_samples_per_second": 39.668,
      "eval_steps_per_second": 10.314,
      "step": 25
    },
    {
      "epoch": 0.2701298701298701,
      "grad_norm": 1.8199442625045776,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.189,
      "step": 26
    },
    {
      "epoch": 0.2805194805194805,
      "grad_norm": 1.7070503234863281,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.1914,
      "step": 27
    },
    {
      "epoch": 0.2909090909090909,
      "grad_norm": 1.6178464889526367,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.221,
      "step": 28
    },
    {
      "epoch": 0.3012987012987013,
      "grad_norm": 1.722450613975525,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.2057,
      "step": 29
    },
    {
      "epoch": 0.3116883116883117,
      "grad_norm": 1.5822162628173828,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.2006,
      "step": 30
    },
    {
      "epoch": 0.3220779220779221,
      "grad_norm": 1.6125823259353638,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.2074,
      "step": 31
    },
    {
      "epoch": 0.33246753246753247,
      "grad_norm": 1.8437734842300415,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.1725,
      "step": 32
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 1.5423240661621094,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.1747,
      "step": 33
    },
    {
      "epoch": 0.35324675324675325,
      "grad_norm": 1.7353768348693848,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.1812,
      "step": 34
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 1.5530339479446411,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.1674,
      "step": 35
    },
    {
      "epoch": 0.37402597402597404,
      "grad_norm": 1.0867341756820679,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.1958,
      "step": 36
    },
    {
      "epoch": 0.38441558441558443,
      "grad_norm": 1.0079206228256226,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.1409,
      "step": 37
    },
    {
      "epoch": 0.3948051948051948,
      "grad_norm": 1.1320562362670898,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.142,
      "step": 38
    },
    {
      "epoch": 0.4051948051948052,
      "grad_norm": 1.299381971359253,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.187,
      "step": 39
    },
    {
      "epoch": 0.4155844155844156,
      "grad_norm": 1.3311715126037598,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.185,
      "step": 40
    },
    {
      "epoch": 0.42597402597402595,
      "grad_norm": 1.184550166130066,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.1746,
      "step": 41
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 1.0470242500305176,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.1865,
      "step": 42
    },
    {
      "epoch": 0.44675324675324674,
      "grad_norm": 1.2727560997009277,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.1466,
      "step": 43
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 1.119794249534607,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.1663,
      "step": 44
    },
    {
      "epoch": 0.4675324675324675,
      "grad_norm": 1.0451369285583496,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.1812,
      "step": 45
    },
    {
      "epoch": 0.4779220779220779,
      "grad_norm": 0.8651501536369324,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.164,
      "step": 46
    },
    {
      "epoch": 0.4883116883116883,
      "grad_norm": 1.185897946357727,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.17,
      "step": 47
    },
    {
      "epoch": 0.4987012987012987,
      "grad_norm": 1.228886604309082,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.1999,
      "step": 48
    },
    {
      "epoch": 0.509090909090909,
      "grad_norm": 0.9948132038116455,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.1337,
      "step": 49
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 1.1506510972976685,
      "learning_rate": 1e-05,
      "loss": 0.176,
      "step": 50
    },
    {
      "epoch": 0.5194805194805194,
      "eval_loss": 0.11276046931743622,
      "eval_runtime": 1.2757,
      "eval_samples_per_second": 39.195,
      "eval_steps_per_second": 10.191,
      "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": 1.62480894509056e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}