{
  "best_metric": 1.3475680351257324,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.010664960273022984,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00021329920546045967,
      "grad_norm": 0.3518493175506592,
      "learning_rate": 2e-05,
      "loss": 1.5048,
      "step": 1
    },
    {
      "epoch": 0.00021329920546045967,
      "eval_loss": 1.6526618003845215,
      "eval_runtime": 68.0524,
      "eval_samples_per_second": 116.028,
      "eval_steps_per_second": 14.504,
      "step": 1
    },
    {
      "epoch": 0.00042659841092091935,
      "grad_norm": 0.37711623311042786,
      "learning_rate": 4e-05,
      "loss": 1.6258,
      "step": 2
    },
    {
      "epoch": 0.0006398976163813789,
      "grad_norm": 0.46083304286003113,
      "learning_rate": 6e-05,
      "loss": 1.455,
      "step": 3
    },
    {
      "epoch": 0.0008531968218418387,
      "grad_norm": 0.3543514609336853,
      "learning_rate": 8e-05,
      "loss": 1.5023,
      "step": 4
    },
    {
      "epoch": 0.0010664960273022983,
      "grad_norm": 0.37860745191574097,
      "learning_rate": 0.0001,
      "loss": 1.65,
      "step": 5
    },
    {
      "epoch": 0.0012797952327627579,
      "grad_norm": 0.36095869541168213,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.5162,
      "step": 6
    },
    {
      "epoch": 0.0014930944382232176,
      "grad_norm": 0.3695549964904785,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.6217,
      "step": 7
    },
    {
      "epoch": 0.0017063936436836774,
      "grad_norm": 0.29503822326660156,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.4592,
      "step": 8
    },
    {
      "epoch": 0.001919692849144137,
      "grad_norm": 0.34321287274360657,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.666,
      "step": 9
    },
    {
      "epoch": 0.0021329920546045967,
      "grad_norm": 0.32609957456588745,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.6691,
      "step": 10
    },
    {
      "epoch": 0.002346291260065056,
      "grad_norm": 0.3041098415851593,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.454,
      "step": 11
    },
    {
      "epoch": 0.0025595904655255157,
      "grad_norm": 0.2885935306549072,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.4091,
      "step": 12
    },
    {
      "epoch": 0.0027728896709859757,
      "grad_norm": 0.3000114858150482,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.5466,
      "step": 13
    },
    {
      "epoch": 0.0029861888764464353,
      "grad_norm": 0.29724496603012085,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.7197,
      "step": 14
    },
    {
      "epoch": 0.003199488081906895,
      "grad_norm": 0.28608736395835876,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.498,
      "step": 15
    },
    {
      "epoch": 0.0034127872873673548,
      "grad_norm": 0.2988593280315399,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.6518,
      "step": 16
    },
    {
      "epoch": 0.0036260864928278143,
      "grad_norm": 0.3114907145500183,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.5352,
      "step": 17
    },
    {
      "epoch": 0.003839385698288274,
      "grad_norm": 0.30663079023361206,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.7605,
      "step": 18
    },
    {
      "epoch": 0.004052684903748734,
      "grad_norm": 0.32326745986938477,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.6032,
      "step": 19
    },
    {
      "epoch": 0.004265984109209193,
      "grad_norm": 0.3428397476673126,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.5863,
      "step": 20
    },
    {
      "epoch": 0.004479283314669653,
      "grad_norm": 0.35635122656822205,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.61,
      "step": 21
    },
    {
      "epoch": 0.004692582520130112,
      "grad_norm": 0.3345847725868225,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.5189,
      "step": 22
    },
    {
      "epoch": 0.004905881725590572,
      "grad_norm": 0.3318396508693695,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.4464,
      "step": 23
    },
    {
      "epoch": 0.0051191809310510315,
      "grad_norm": 0.3057437539100647,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.3289,
      "step": 24
    },
    {
      "epoch": 0.005332480136511492,
      "grad_norm": 0.3709765374660492,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.5021,
      "step": 25
    },
    {
      "epoch": 0.005332480136511492,
      "eval_loss": 1.3771291971206665,
      "eval_runtime": 68.0252,
      "eval_samples_per_second": 116.075,
      "eval_steps_per_second": 14.509,
      "step": 25
    },
    {
      "epoch": 0.0055457793419719514,
      "grad_norm": 0.3569680452346802,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.497,
      "step": 26
    },
    {
      "epoch": 0.005759078547432411,
      "grad_norm": 0.3587609827518463,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.4024,
      "step": 27
    },
    {
      "epoch": 0.0059723777528928705,
      "grad_norm": 0.3989461362361908,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.5467,
      "step": 28
    },
    {
      "epoch": 0.00618567695835333,
      "grad_norm": 0.3418835699558258,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.4541,
      "step": 29
    },
    {
      "epoch": 0.00639897616381379,
      "grad_norm": 0.3659650981426239,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.5464,
      "step": 30
    },
    {
      "epoch": 0.006612275369274249,
      "grad_norm": 0.4786025285720825,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.6205,
      "step": 31
    },
    {
      "epoch": 0.0068255745747347095,
      "grad_norm": 0.4017328917980194,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.3343,
      "step": 32
    },
    {
      "epoch": 0.007038873780195169,
      "grad_norm": 0.5265333652496338,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.8905,
      "step": 33
    },
    {
      "epoch": 0.007252172985655629,
      "grad_norm": 0.3608676791191101,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.3683,
      "step": 34
    },
    {
      "epoch": 0.007465472191116088,
      "grad_norm": 0.4353957772254944,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.6015,
      "step": 35
    },
    {
      "epoch": 0.007678771396576548,
      "grad_norm": 0.3937820792198181,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.2824,
      "step": 36
    },
    {
      "epoch": 0.007892070602037008,
      "grad_norm": 0.39776891469955444,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.9932,
      "step": 37
    },
    {
      "epoch": 0.008105369807497468,
      "grad_norm": 0.42103254795074463,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.0356,
      "step": 38
    },
    {
      "epoch": 0.008318669012957927,
      "grad_norm": 0.4416367709636688,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.1976,
      "step": 39
    },
    {
      "epoch": 0.008531968218418387,
      "grad_norm": 0.35231977701187134,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.0434,
      "step": 40
    },
    {
      "epoch": 0.008745267423878846,
      "grad_norm": 0.41201403737068176,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.9915,
      "step": 41
    },
    {
      "epoch": 0.008958566629339306,
      "grad_norm": 0.4073962867259979,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.1811,
      "step": 42
    },
    {
      "epoch": 0.009171865834799765,
      "grad_norm": 0.365858256816864,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.8872,
      "step": 43
    },
    {
      "epoch": 0.009385165040260225,
      "grad_norm": 0.36499106884002686,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.1054,
      "step": 44
    },
    {
      "epoch": 0.009598464245720684,
      "grad_norm": 0.33799082040786743,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.1389,
      "step": 45
    },
    {
      "epoch": 0.009811763451181144,
      "grad_norm": 0.3514730632305145,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.1157,
      "step": 46
    },
    {
      "epoch": 0.010025062656641603,
      "grad_norm": 0.3646899163722992,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.088,
      "step": 47
    },
    {
      "epoch": 0.010238361862102063,
      "grad_norm": 0.38466212153434753,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.08,
      "step": 48
    },
    {
      "epoch": 0.010451661067562523,
      "grad_norm": 0.4186328053474426,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.1221,
      "step": 49
    },
    {
      "epoch": 0.010664960273022984,
      "grad_norm": 0.5278308987617493,
      "learning_rate": 0.0,
      "loss": 0.9967,
      "step": 50
    },
    {
      "epoch": 0.010664960273022984,
      "eval_loss": 1.3475680351257324,
      "eval_runtime": 67.9728,
      "eval_samples_per_second": 116.164,
      "eval_steps_per_second": 14.521,
      "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": 5,
        "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": 1087757459914752.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}