{
  "best_metric": 0.7137496471405029,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.024351637647631805,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00048703275295263604,
      "grad_norm": 0.9668720960617065,
      "learning_rate": 2e-05,
      "loss": 0.7861,
      "step": 1
    },
    {
      "epoch": 0.00048703275295263604,
      "eval_loss": 0.8942872285842896,
      "eval_runtime": 52.1362,
      "eval_samples_per_second": 66.345,
      "eval_steps_per_second": 8.305,
      "step": 1
    },
    {
      "epoch": 0.0009740655059052721,
      "grad_norm": 1.109323501586914,
      "learning_rate": 4e-05,
      "loss": 0.7208,
      "step": 2
    },
    {
      "epoch": 0.0014610982588579083,
      "grad_norm": 0.8979827165603638,
      "learning_rate": 6e-05,
      "loss": 0.7672,
      "step": 3
    },
    {
      "epoch": 0.0019481310118105442,
      "grad_norm": 0.7457740306854248,
      "learning_rate": 8e-05,
      "loss": 0.7396,
      "step": 4
    },
    {
      "epoch": 0.0024351637647631805,
      "grad_norm": 0.9767470955848694,
      "learning_rate": 0.0001,
      "loss": 0.788,
      "step": 5
    },
    {
      "epoch": 0.0029221965177158166,
      "grad_norm": 0.928979754447937,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.7996,
      "step": 6
    },
    {
      "epoch": 0.0034092292706684527,
      "grad_norm": 0.7546679377555847,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.7589,
      "step": 7
    },
    {
      "epoch": 0.0038962620236210883,
      "grad_norm": 0.757028341293335,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.9003,
      "step": 8
    },
    {
      "epoch": 0.004383294776573725,
      "grad_norm": 0.7388772964477539,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.7762,
      "step": 9
    },
    {
      "epoch": 0.004870327529526361,
      "grad_norm": 0.713144063949585,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.745,
      "step": 10
    },
    {
      "epoch": 0.005357360282478997,
      "grad_norm": 0.6719604134559631,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.7749,
      "step": 11
    },
    {
      "epoch": 0.005844393035431633,
      "grad_norm": 0.6307094693183899,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.6938,
      "step": 12
    },
    {
      "epoch": 0.006331425788384269,
      "grad_norm": 0.6746920943260193,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.8753,
      "step": 13
    },
    {
      "epoch": 0.006818458541336905,
      "grad_norm": 0.6357215642929077,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7801,
      "step": 14
    },
    {
      "epoch": 0.0073054912942895405,
      "grad_norm": 0.7156640291213989,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.7304,
      "step": 15
    },
    {
      "epoch": 0.007792524047242177,
      "grad_norm": 0.7125033140182495,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.7382,
      "step": 16
    },
    {
      "epoch": 0.008279556800194814,
      "grad_norm": 0.7216728925704956,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.7764,
      "step": 17
    },
    {
      "epoch": 0.00876658955314745,
      "grad_norm": 0.6608908176422119,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.7247,
      "step": 18
    },
    {
      "epoch": 0.009253622306100086,
      "grad_norm": 0.7499627470970154,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.796,
      "step": 19
    },
    {
      "epoch": 0.009740655059052722,
      "grad_norm": 0.6988794803619385,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.7523,
      "step": 20
    },
    {
      "epoch": 0.010227687812005358,
      "grad_norm": 0.7267606854438782,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.7685,
      "step": 21
    },
    {
      "epoch": 0.010714720564957994,
      "grad_norm": 0.6517067551612854,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.7143,
      "step": 22
    },
    {
      "epoch": 0.01120175331791063,
      "grad_norm": 0.6588945984840393,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7267,
      "step": 23
    },
    {
      "epoch": 0.011688786070863266,
      "grad_norm": 0.6455866694450378,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.771,
      "step": 24
    },
    {
      "epoch": 0.012175818823815902,
      "grad_norm": 0.6290040016174316,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.7143,
      "step": 25
    },
    {
      "epoch": 0.012175818823815902,
      "eval_loss": 0.7276486754417419,
      "eval_runtime": 52.1205,
      "eval_samples_per_second": 66.365,
      "eval_steps_per_second": 8.308,
      "step": 25
    },
    {
      "epoch": 0.012662851576768538,
      "grad_norm": 0.6263149976730347,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.8059,
      "step": 26
    },
    {
      "epoch": 0.013149884329721175,
      "grad_norm": 0.649336576461792,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.714,
      "step": 27
    },
    {
      "epoch": 0.01363691708267381,
      "grad_norm": 0.6983732581138611,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.7714,
      "step": 28
    },
    {
      "epoch": 0.014123949835626447,
      "grad_norm": 0.6310800909996033,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.7492,
      "step": 29
    },
    {
      "epoch": 0.014610982588579081,
      "grad_norm": 0.6215700507164001,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.6541,
      "step": 30
    },
    {
      "epoch": 0.015098015341531717,
      "grad_norm": 0.7055749893188477,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.6742,
      "step": 31
    },
    {
      "epoch": 0.015585048094484353,
      "grad_norm": 0.634620189666748,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6968,
      "step": 32
    },
    {
      "epoch": 0.01607208084743699,
      "grad_norm": 0.6823827028274536,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.7632,
      "step": 33
    },
    {
      "epoch": 0.016559113600389627,
      "grad_norm": 0.6950632929801941,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.7368,
      "step": 34
    },
    {
      "epoch": 0.017046146353342263,
      "grad_norm": 0.7879264950752258,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.8233,
      "step": 35
    },
    {
      "epoch": 0.0175331791062949,
      "grad_norm": 0.6341107487678528,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.6603,
      "step": 36
    },
    {
      "epoch": 0.018020211859247535,
      "grad_norm": 0.6985974311828613,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.6774,
      "step": 37
    },
    {
      "epoch": 0.01850724461220017,
      "grad_norm": 0.7165974378585815,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.7472,
      "step": 38
    },
    {
      "epoch": 0.018994277365152808,
      "grad_norm": 0.7006275057792664,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.6472,
      "step": 39
    },
    {
      "epoch": 0.019481310118105444,
      "grad_norm": 0.6504078507423401,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.7263,
      "step": 40
    },
    {
      "epoch": 0.01996834287105808,
      "grad_norm": 0.6661069989204407,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.6685,
      "step": 41
    },
    {
      "epoch": 0.020455375624010716,
      "grad_norm": 0.7080692648887634,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.6859,
      "step": 42
    },
    {
      "epoch": 0.020942408376963352,
      "grad_norm": 0.7681254744529724,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.6853,
      "step": 43
    },
    {
      "epoch": 0.021429441129915988,
      "grad_norm": 0.7165603637695312,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.6546,
      "step": 44
    },
    {
      "epoch": 0.021916473882868624,
      "grad_norm": 0.7238483428955078,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.7094,
      "step": 45
    },
    {
      "epoch": 0.02240350663582126,
      "grad_norm": 0.7569670677185059,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.669,
      "step": 46
    },
    {
      "epoch": 0.022890539388773896,
      "grad_norm": 0.7207056879997253,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.6464,
      "step": 47
    },
    {
      "epoch": 0.023377572141726533,
      "grad_norm": 0.7816201448440552,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.6456,
      "step": 48
    },
    {
      "epoch": 0.02386460489467917,
      "grad_norm": 0.8748300671577454,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.7031,
      "step": 49
    },
    {
      "epoch": 0.024351637647631805,
      "grad_norm": 0.933390200138092,
      "learning_rate": 0.0,
      "loss": 0.5756,
      "step": 50
    },
    {
      "epoch": 0.024351637647631805,
      "eval_loss": 0.7137496471405029,
      "eval_runtime": 52.1712,
      "eval_samples_per_second": 66.301,
      "eval_steps_per_second": 8.3,
      "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": 3603404933824512.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}