{
  "best_metric": 11.758837699890137,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.04927929037821856,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000985585807564371,
      "grad_norm": 0.03316239267587662,
      "learning_rate": 5e-05,
      "loss": 11.7676,
      "step": 1
    },
    {
      "epoch": 0.000985585807564371,
      "eval_loss": 11.767082214355469,
      "eval_runtime": 0.1538,
      "eval_samples_per_second": 325.189,
      "eval_steps_per_second": 84.549,
      "step": 1
    },
    {
      "epoch": 0.001971171615128742,
      "grad_norm": 0.03531897813081741,
      "learning_rate": 0.0001,
      "loss": 11.7667,
      "step": 2
    },
    {
      "epoch": 0.002956757422693113,
      "grad_norm": 0.03855114057660103,
      "learning_rate": 9.990365154573717e-05,
      "loss": 11.7666,
      "step": 3
    },
    {
      "epoch": 0.003942343230257484,
      "grad_norm": 0.036869846284389496,
      "learning_rate": 9.961501876182148e-05,
      "loss": 11.7682,
      "step": 4
    },
    {
      "epoch": 0.004927929037821855,
      "grad_norm": 0.03692394495010376,
      "learning_rate": 9.913533761814537e-05,
      "loss": 11.7659,
      "step": 5
    },
    {
      "epoch": 0.005913514845386226,
      "grad_norm": 0.04036902263760567,
      "learning_rate": 9.846666218300807e-05,
      "loss": 11.7664,
      "step": 6
    },
    {
      "epoch": 0.006899100652950597,
      "grad_norm": 0.038628559559583664,
      "learning_rate": 9.761185582727977e-05,
      "loss": 11.7638,
      "step": 7
    },
    {
      "epoch": 0.007884686460514968,
      "grad_norm": 0.04096132889389992,
      "learning_rate": 9.657457896300791e-05,
      "loss": 11.7663,
      "step": 8
    },
    {
      "epoch": 0.00887027226807934,
      "grad_norm": 0.04600469022989273,
      "learning_rate": 9.535927336897098e-05,
      "loss": 11.768,
      "step": 9
    },
    {
      "epoch": 0.00985585807564371,
      "grad_norm": 0.04856152832508087,
      "learning_rate": 9.397114317029975e-05,
      "loss": 11.7663,
      "step": 10
    },
    {
      "epoch": 0.010841443883208082,
      "grad_norm": 0.052747271955013275,
      "learning_rate": 9.241613255361455e-05,
      "loss": 11.7675,
      "step": 11
    },
    {
      "epoch": 0.011827029690772452,
      "grad_norm": 0.06056119129061699,
      "learning_rate": 9.070090031310558e-05,
      "loss": 11.7669,
      "step": 12
    },
    {
      "epoch": 0.012812615498336824,
      "grad_norm": 0.055393997579813004,
      "learning_rate": 8.883279133655399e-05,
      "loss": 11.762,
      "step": 13
    },
    {
      "epoch": 0.013798201305901195,
      "grad_norm": 0.044938188046216965,
      "learning_rate": 8.681980515339464e-05,
      "loss": 11.765,
      "step": 14
    },
    {
      "epoch": 0.014783787113465566,
      "grad_norm": 0.04867026209831238,
      "learning_rate": 8.467056167950311e-05,
      "loss": 11.7658,
      "step": 15
    },
    {
      "epoch": 0.015769372921029937,
      "grad_norm": 0.047632962465286255,
      "learning_rate": 8.239426430539243e-05,
      "loss": 11.7682,
      "step": 16
    },
    {
      "epoch": 0.016754958728594307,
      "grad_norm": 0.04969922825694084,
      "learning_rate": 8.000066048588211e-05,
      "loss": 11.7637,
      "step": 17
    },
    {
      "epoch": 0.01774054453615868,
      "grad_norm": 0.050760604441165924,
      "learning_rate": 7.75e-05,
      "loss": 11.7612,
      "step": 18
    },
    {
      "epoch": 0.01872613034372305,
      "grad_norm": 0.05226846784353256,
      "learning_rate": 7.490299105985507e-05,
      "loss": 11.7618,
      "step": 19
    },
    {
      "epoch": 0.01971171615128742,
      "grad_norm": 0.056723929941654205,
      "learning_rate": 7.222075445642904e-05,
      "loss": 11.7657,
      "step": 20
    },
    {
      "epoch": 0.02069730195885179,
      "grad_norm": 0.055445414036512375,
      "learning_rate": 6.946477593864228e-05,
      "loss": 11.7652,
      "step": 21
    },
    {
      "epoch": 0.021682887766416165,
      "grad_norm": 0.06418636441230774,
      "learning_rate": 6.664685702961344e-05,
      "loss": 11.7632,
      "step": 22
    },
    {
      "epoch": 0.022668473573980535,
      "grad_norm": 0.0812559649348259,
      "learning_rate": 6.377906449072578e-05,
      "loss": 11.7648,
      "step": 23
    },
    {
      "epoch": 0.023654059381544905,
      "grad_norm": 0.07854355871677399,
      "learning_rate": 6.087367864990233e-05,
      "loss": 11.7641,
      "step": 24
    },
    {
      "epoch": 0.02463964518910928,
      "grad_norm": 0.10034958273172379,
      "learning_rate": 5.794314081535644e-05,
      "loss": 11.7608,
      "step": 25
    },
    {
      "epoch": 0.02463964518910928,
      "eval_loss": 11.762114524841309,
      "eval_runtime": 0.1601,
      "eval_samples_per_second": 312.289,
      "eval_steps_per_second": 81.195,
      "step": 25
    },
    {
      "epoch": 0.02562523099667365,
      "grad_norm": 0.06491614878177643,
      "learning_rate": 5.500000000000001e-05,
      "loss": 11.7642,
      "step": 26
    },
    {
      "epoch": 0.02661081680423802,
      "grad_norm": 0.06239859759807587,
      "learning_rate": 5.205685918464356e-05,
      "loss": 11.7607,
      "step": 27
    },
    {
      "epoch": 0.02759640261180239,
      "grad_norm": 0.06446800380945206,
      "learning_rate": 4.912632135009769e-05,
      "loss": 11.7627,
      "step": 28
    },
    {
      "epoch": 0.028581988419366763,
      "grad_norm": 0.07301193475723267,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 11.7614,
      "step": 29
    },
    {
      "epoch": 0.029567574226931133,
      "grad_norm": 0.06827574968338013,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 11.7594,
      "step": 30
    },
    {
      "epoch": 0.030553160034495503,
      "grad_norm": 0.06913921236991882,
      "learning_rate": 4.053522406135775e-05,
      "loss": 11.7581,
      "step": 31
    },
    {
      "epoch": 0.03153874584205987,
      "grad_norm": 0.08095534145832062,
      "learning_rate": 3.777924554357096e-05,
      "loss": 11.7569,
      "step": 32
    },
    {
      "epoch": 0.03252433164962425,
      "grad_norm": 0.07958046346902847,
      "learning_rate": 3.509700894014496e-05,
      "loss": 11.7622,
      "step": 33
    },
    {
      "epoch": 0.033509917457188614,
      "grad_norm": 0.08830973505973816,
      "learning_rate": 3.250000000000001e-05,
      "loss": 11.763,
      "step": 34
    },
    {
      "epoch": 0.03449550326475299,
      "grad_norm": 0.09469051659107208,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 11.7601,
      "step": 35
    },
    {
      "epoch": 0.03548108907231736,
      "grad_norm": 0.09495487809181213,
      "learning_rate": 2.760573569460757e-05,
      "loss": 11.7612,
      "step": 36
    },
    {
      "epoch": 0.03646667487988173,
      "grad_norm": 0.09853039681911469,
      "learning_rate": 2.53294383204969e-05,
      "loss": 11.7619,
      "step": 37
    },
    {
      "epoch": 0.0374522606874461,
      "grad_norm": 0.0928775817155838,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 11.7562,
      "step": 38
    },
    {
      "epoch": 0.038437846495010475,
      "grad_norm": 0.08328034728765488,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 11.7608,
      "step": 39
    },
    {
      "epoch": 0.03942343230257484,
      "grad_norm": 0.08076374232769012,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 11.7634,
      "step": 40
    },
    {
      "epoch": 0.040409018110139215,
      "grad_norm": 0.07809954881668091,
      "learning_rate": 1.758386744638546e-05,
      "loss": 11.7596,
      "step": 41
    },
    {
      "epoch": 0.04139460391770358,
      "grad_norm": 0.09155470132827759,
      "learning_rate": 1.602885682970026e-05,
      "loss": 11.7622,
      "step": 42
    },
    {
      "epoch": 0.042380189725267955,
      "grad_norm": 0.08296317607164383,
      "learning_rate": 1.464072663102903e-05,
      "loss": 11.7583,
      "step": 43
    },
    {
      "epoch": 0.04336577553283233,
      "grad_norm": 0.08634920418262482,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 11.7581,
      "step": 44
    },
    {
      "epoch": 0.044351361340396696,
      "grad_norm": 0.08652149140834808,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 11.7608,
      "step": 45
    },
    {
      "epoch": 0.04533694714796107,
      "grad_norm": 0.08408989012241364,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 11.7577,
      "step": 46
    },
    {
      "epoch": 0.04632253295552544,
      "grad_norm": 0.09810920059680939,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 11.7598,
      "step": 47
    },
    {
      "epoch": 0.04730811876308981,
      "grad_norm": 0.09459834545850754,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 11.7593,
      "step": 48
    },
    {
      "epoch": 0.04829370457065418,
      "grad_norm": 0.11204507201910019,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 11.758,
      "step": 49
    },
    {
      "epoch": 0.04927929037821856,
      "grad_norm": 0.10605693608522415,
      "learning_rate": 1e-05,
      "loss": 11.7611,
      "step": 50
    },
    {
      "epoch": 0.04927929037821856,
      "eval_loss": 11.758837699890137,
      "eval_runtime": 0.1569,
      "eval_samples_per_second": 318.582,
      "eval_steps_per_second": 82.831,
      "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": 164193424113664.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}