{
  "best_metric": 10.372344017028809,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.05738880918220947,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011477761836441894,
      "grad_norm": 0.021021617576479912,
      "learning_rate": 5e-05,
      "loss": 10.377,
      "step": 1
    },
    {
      "epoch": 0.0011477761836441894,
      "eval_loss": 10.377026557922363,
      "eval_runtime": 0.101,
      "eval_samples_per_second": 495.209,
      "eval_steps_per_second": 128.754,
      "step": 1
    },
    {
      "epoch": 0.0022955523672883787,
      "grad_norm": 0.02225891686975956,
      "learning_rate": 0.0001,
      "loss": 10.3755,
      "step": 2
    },
    {
      "epoch": 0.003443328550932568,
      "grad_norm": 0.022853638976812363,
      "learning_rate": 9.990365154573717e-05,
      "loss": 10.3765,
      "step": 3
    },
    {
      "epoch": 0.004591104734576757,
      "grad_norm": 0.023556284606456757,
      "learning_rate": 9.961501876182148e-05,
      "loss": 10.3768,
      "step": 4
    },
    {
      "epoch": 0.005738880918220947,
      "grad_norm": 0.024813596159219742,
      "learning_rate": 9.913533761814537e-05,
      "loss": 10.3773,
      "step": 5
    },
    {
      "epoch": 0.006886657101865136,
      "grad_norm": 0.023740680888295174,
      "learning_rate": 9.846666218300807e-05,
      "loss": 10.3762,
      "step": 6
    },
    {
      "epoch": 0.008034433285509325,
      "grad_norm": 0.023969357833266258,
      "learning_rate": 9.761185582727977e-05,
      "loss": 10.3768,
      "step": 7
    },
    {
      "epoch": 0.009182209469153515,
      "grad_norm": 0.02269619144499302,
      "learning_rate": 9.657457896300791e-05,
      "loss": 10.3755,
      "step": 8
    },
    {
      "epoch": 0.010329985652797705,
      "grad_norm": 0.024315403774380684,
      "learning_rate": 9.535927336897098e-05,
      "loss": 10.3773,
      "step": 9
    },
    {
      "epoch": 0.011477761836441894,
      "grad_norm": 0.027994578704237938,
      "learning_rate": 9.397114317029975e-05,
      "loss": 10.3766,
      "step": 10
    },
    {
      "epoch": 0.012625538020086082,
      "grad_norm": 0.0290063489228487,
      "learning_rate": 9.241613255361455e-05,
      "loss": 10.375,
      "step": 11
    },
    {
      "epoch": 0.013773314203730272,
      "grad_norm": 0.02795129455626011,
      "learning_rate": 9.070090031310558e-05,
      "loss": 10.3751,
      "step": 12
    },
    {
      "epoch": 0.014921090387374462,
      "grad_norm": 0.023901531472802162,
      "learning_rate": 8.883279133655399e-05,
      "loss": 10.3753,
      "step": 13
    },
    {
      "epoch": 0.01606886657101865,
      "grad_norm": 0.023932108655571938,
      "learning_rate": 8.681980515339464e-05,
      "loss": 10.3756,
      "step": 14
    },
    {
      "epoch": 0.01721664275466284,
      "grad_norm": 0.025946082547307014,
      "learning_rate": 8.467056167950311e-05,
      "loss": 10.3751,
      "step": 15
    },
    {
      "epoch": 0.01836441893830703,
      "grad_norm": 0.026127338409423828,
      "learning_rate": 8.239426430539243e-05,
      "loss": 10.3755,
      "step": 16
    },
    {
      "epoch": 0.01951219512195122,
      "grad_norm": 0.0297646876424551,
      "learning_rate": 8.000066048588211e-05,
      "loss": 10.3745,
      "step": 17
    },
    {
      "epoch": 0.02065997130559541,
      "grad_norm": 0.032692939043045044,
      "learning_rate": 7.75e-05,
      "loss": 10.3742,
      "step": 18
    },
    {
      "epoch": 0.0218077474892396,
      "grad_norm": 0.030711574479937553,
      "learning_rate": 7.490299105985507e-05,
      "loss": 10.3748,
      "step": 19
    },
    {
      "epoch": 0.02295552367288379,
      "grad_norm": 0.03380997106432915,
      "learning_rate": 7.222075445642904e-05,
      "loss": 10.3742,
      "step": 20
    },
    {
      "epoch": 0.02410329985652798,
      "grad_norm": 0.032966237515211105,
      "learning_rate": 6.946477593864228e-05,
      "loss": 10.3742,
      "step": 21
    },
    {
      "epoch": 0.025251076040172165,
      "grad_norm": 0.03569738194346428,
      "learning_rate": 6.664685702961344e-05,
      "loss": 10.3737,
      "step": 22
    },
    {
      "epoch": 0.026398852223816355,
      "grad_norm": 0.03610365837812424,
      "learning_rate": 6.377906449072578e-05,
      "loss": 10.3737,
      "step": 23
    },
    {
      "epoch": 0.027546628407460545,
      "grad_norm": 0.043039996176958084,
      "learning_rate": 6.087367864990233e-05,
      "loss": 10.3739,
      "step": 24
    },
    {
      "epoch": 0.028694404591104734,
      "grad_norm": 0.04014543443918228,
      "learning_rate": 5.794314081535644e-05,
      "loss": 10.374,
      "step": 25
    },
    {
      "epoch": 0.028694404591104734,
      "eval_loss": 10.374122619628906,
      "eval_runtime": 0.0973,
      "eval_samples_per_second": 514.095,
      "eval_steps_per_second": 133.665,
      "step": 25
    },
    {
      "epoch": 0.029842180774748924,
      "grad_norm": 0.03204667568206787,
      "learning_rate": 5.500000000000001e-05,
      "loss": 10.3744,
      "step": 26
    },
    {
      "epoch": 0.030989956958393114,
      "grad_norm": 0.03463904932141304,
      "learning_rate": 5.205685918464356e-05,
      "loss": 10.375,
      "step": 27
    },
    {
      "epoch": 0.0321377331420373,
      "grad_norm": 0.0373113639652729,
      "learning_rate": 4.912632135009769e-05,
      "loss": 10.3748,
      "step": 28
    },
    {
      "epoch": 0.033285509325681494,
      "grad_norm": 0.038027435541152954,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 10.3747,
      "step": 29
    },
    {
      "epoch": 0.03443328550932568,
      "grad_norm": 0.04169121012091637,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 10.3736,
      "step": 30
    },
    {
      "epoch": 0.03558106169296987,
      "grad_norm": 0.043524134904146194,
      "learning_rate": 4.053522406135775e-05,
      "loss": 10.373,
      "step": 31
    },
    {
      "epoch": 0.03672883787661406,
      "grad_norm": 0.04519710689783096,
      "learning_rate": 3.777924554357096e-05,
      "loss": 10.3734,
      "step": 32
    },
    {
      "epoch": 0.03787661406025825,
      "grad_norm": 0.04633459076285362,
      "learning_rate": 3.509700894014496e-05,
      "loss": 10.3719,
      "step": 33
    },
    {
      "epoch": 0.03902439024390244,
      "grad_norm": 0.050218332558870316,
      "learning_rate": 3.250000000000001e-05,
      "loss": 10.3713,
      "step": 34
    },
    {
      "epoch": 0.040172166427546625,
      "grad_norm": 0.049278732389211655,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 10.3723,
      "step": 35
    },
    {
      "epoch": 0.04131994261119082,
      "grad_norm": 0.04763339087367058,
      "learning_rate": 2.760573569460757e-05,
      "loss": 10.3733,
      "step": 36
    },
    {
      "epoch": 0.042467718794835005,
      "grad_norm": 0.0534612238407135,
      "learning_rate": 2.53294383204969e-05,
      "loss": 10.3728,
      "step": 37
    },
    {
      "epoch": 0.0436154949784792,
      "grad_norm": 0.044117774814367294,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 10.3734,
      "step": 38
    },
    {
      "epoch": 0.044763271162123384,
      "grad_norm": 0.0443359836935997,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 10.3731,
      "step": 39
    },
    {
      "epoch": 0.04591104734576758,
      "grad_norm": 0.047672707587480545,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 10.3736,
      "step": 40
    },
    {
      "epoch": 0.047058823529411764,
      "grad_norm": 0.04800671711564064,
      "learning_rate": 1.758386744638546e-05,
      "loss": 10.3732,
      "step": 41
    },
    {
      "epoch": 0.04820659971305596,
      "grad_norm": 0.04492698982357979,
      "learning_rate": 1.602885682970026e-05,
      "loss": 10.372,
      "step": 42
    },
    {
      "epoch": 0.049354375896700144,
      "grad_norm": 0.05303284153342247,
      "learning_rate": 1.464072663102903e-05,
      "loss": 10.3719,
      "step": 43
    },
    {
      "epoch": 0.05050215208034433,
      "grad_norm": 0.055283885449171066,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 10.3719,
      "step": 44
    },
    {
      "epoch": 0.05164992826398852,
      "grad_norm": 0.05048627033829689,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 10.3714,
      "step": 45
    },
    {
      "epoch": 0.05279770444763271,
      "grad_norm": 0.058030229061841965,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 10.3722,
      "step": 46
    },
    {
      "epoch": 0.0539454806312769,
      "grad_norm": 0.05614259093999863,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 10.3701,
      "step": 47
    },
    {
      "epoch": 0.05509325681492109,
      "grad_norm": 0.06042291969060898,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 10.3713,
      "step": 48
    },
    {
      "epoch": 0.05624103299856528,
      "grad_norm": 0.05883251503109932,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 10.3707,
      "step": 49
    },
    {
      "epoch": 0.05738880918220947,
      "grad_norm": 0.05974884703755379,
      "learning_rate": 1e-05,
      "loss": 10.3726,
      "step": 50
    },
    {
      "epoch": 0.05738880918220947,
      "eval_loss": 10.372344017028809,
      "eval_runtime": 0.1035,
      "eval_samples_per_second": 482.877,
      "eval_steps_per_second": 125.548,
      "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": 42781424615424.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}