{
  "best_metric": 0.06207295507192612,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.9645909645909647,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03907203907203907,
      "grad_norm": 4.342593193054199,
      "learning_rate": 5e-05,
      "loss": 2.9731,
      "step": 1
    },
    {
      "epoch": 0.03907203907203907,
      "eval_loss": 3.825854778289795,
      "eval_runtime": 3.0175,
      "eval_samples_per_second": 16.57,
      "eval_steps_per_second": 4.308,
      "step": 1
    },
    {
      "epoch": 0.07814407814407814,
      "grad_norm": 4.329413414001465,
      "learning_rate": 0.0001,
      "loss": 2.8601,
      "step": 2
    },
    {
      "epoch": 0.11721611721611722,
      "grad_norm": 4.38667106628418,
      "learning_rate": 9.990365154573717e-05,
      "loss": 2.769,
      "step": 3
    },
    {
      "epoch": 0.1562881562881563,
      "grad_norm": 3.8900246620178223,
      "learning_rate": 9.961501876182148e-05,
      "loss": 2.1385,
      "step": 4
    },
    {
      "epoch": 0.19536019536019536,
      "grad_norm": 3.678853750228882,
      "learning_rate": 9.913533761814537e-05,
      "loss": 1.9752,
      "step": 5
    },
    {
      "epoch": 0.23443223443223443,
      "grad_norm": 4.750513553619385,
      "learning_rate": 9.846666218300807e-05,
      "loss": 2.2588,
      "step": 6
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 3.6628079414367676,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.9933,
      "step": 7
    },
    {
      "epoch": 0.3125763125763126,
      "grad_norm": 4.424605369567871,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.4886,
      "step": 8
    },
    {
      "epoch": 0.3516483516483517,
      "grad_norm": 1.0797154903411865,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.1462,
      "step": 9
    },
    {
      "epoch": 0.3907203907203907,
      "grad_norm": 1.7442551851272583,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.217,
      "step": 10
    },
    {
      "epoch": 0.4297924297924298,
      "grad_norm": 1.6925084590911865,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.1901,
      "step": 11
    },
    {
      "epoch": 0.46886446886446886,
      "grad_norm": 3.2824654579162598,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.2443,
      "step": 12
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 2.0940823554992676,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.127,
      "step": 13
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.7476776838302612,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.1301,
      "step": 14
    },
    {
      "epoch": 0.5860805860805861,
      "grad_norm": 0.8936842679977417,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.1412,
      "step": 15
    },
    {
      "epoch": 0.6251526251526252,
      "grad_norm": 1.3796156644821167,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.1416,
      "step": 16
    },
    {
      "epoch": 0.6642246642246642,
      "grad_norm": 0.7006492614746094,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.1111,
      "step": 17
    },
    {
      "epoch": 0.7032967032967034,
      "grad_norm": 0.7903730869293213,
      "learning_rate": 7.75e-05,
      "loss": 0.0685,
      "step": 18
    },
    {
      "epoch": 0.7423687423687424,
      "grad_norm": 0.6418982148170471,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.1016,
      "step": 19
    },
    {
      "epoch": 0.7814407814407814,
      "grad_norm": 0.6355842351913452,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.0779,
      "step": 20
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.4654819071292877,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.0757,
      "step": 21
    },
    {
      "epoch": 0.8595848595848596,
      "grad_norm": 0.5091500878334045,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.0628,
      "step": 22
    },
    {
      "epoch": 0.8986568986568987,
      "grad_norm": 0.33425307273864746,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.0648,
      "step": 23
    },
    {
      "epoch": 0.9377289377289377,
      "grad_norm": 0.5528669357299805,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.1092,
      "step": 24
    },
    {
      "epoch": 0.9768009768009768,
      "grad_norm": 0.08286019414663315,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.0024,
      "step": 25
    },
    {
      "epoch": 0.9768009768009768,
      "eval_loss": 0.08785244822502136,
      "eval_runtime": 2.9575,
      "eval_samples_per_second": 16.906,
      "eval_steps_per_second": 4.396,
      "step": 25
    },
    {
      "epoch": 1.0268620268620268,
      "grad_norm": 0.5360961556434631,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.1334,
      "step": 26
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.38586679100990295,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.0611,
      "step": 27
    },
    {
      "epoch": 1.105006105006105,
      "grad_norm": 0.2803765833377838,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.071,
      "step": 28
    },
    {
      "epoch": 1.144078144078144,
      "grad_norm": 0.26485010981559753,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.0692,
      "step": 29
    },
    {
      "epoch": 1.1831501831501832,
      "grad_norm": 0.28996384143829346,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.0566,
      "step": 30
    },
    {
      "epoch": 1.2222222222222223,
      "grad_norm": 0.47175368666648865,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.0565,
      "step": 31
    },
    {
      "epoch": 1.2612942612942613,
      "grad_norm": 0.29181963205337524,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.0338,
      "step": 32
    },
    {
      "epoch": 1.3003663003663004,
      "grad_norm": 0.32808589935302734,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.0561,
      "step": 33
    },
    {
      "epoch": 1.3394383394383396,
      "grad_norm": 0.2767590582370758,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.0465,
      "step": 34
    },
    {
      "epoch": 1.3785103785103785,
      "grad_norm": 0.3915354609489441,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.062,
      "step": 35
    },
    {
      "epoch": 1.4175824175824177,
      "grad_norm": 0.24747319519519806,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.059,
      "step": 36
    },
    {
      "epoch": 1.4566544566544566,
      "grad_norm": 0.1756383627653122,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.0318,
      "step": 37
    },
    {
      "epoch": 1.4957264957264957,
      "grad_norm": 0.1586117446422577,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.024,
      "step": 38
    },
    {
      "epoch": 1.5347985347985347,
      "grad_norm": 0.22885628044605255,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.0441,
      "step": 39
    },
    {
      "epoch": 1.5738705738705738,
      "grad_norm": 0.18986821174621582,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.0354,
      "step": 40
    },
    {
      "epoch": 1.612942612942613,
      "grad_norm": 0.30566394329071045,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.0535,
      "step": 41
    },
    {
      "epoch": 1.652014652014652,
      "grad_norm": 0.23684832453727722,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.0529,
      "step": 42
    },
    {
      "epoch": 1.691086691086691,
      "grad_norm": 0.23424597084522247,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.0356,
      "step": 43
    },
    {
      "epoch": 1.7301587301587302,
      "grad_norm": 0.28173795342445374,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.0224,
      "step": 44
    },
    {
      "epoch": 1.7692307692307692,
      "grad_norm": 0.22328241169452667,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.0311,
      "step": 45
    },
    {
      "epoch": 1.8083028083028083,
      "grad_norm": 0.2587464451789856,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.0451,
      "step": 46
    },
    {
      "epoch": 1.8473748473748475,
      "grad_norm": 0.31801164150238037,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.0679,
      "step": 47
    },
    {
      "epoch": 1.8864468864468864,
      "grad_norm": 0.29504692554473877,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.0622,
      "step": 48
    },
    {
      "epoch": 1.9255189255189256,
      "grad_norm": 0.18160757422447205,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.047,
      "step": 49
    },
    {
      "epoch": 1.9645909645909647,
      "grad_norm": 0.13465796411037445,
      "learning_rate": 1e-05,
      "loss": 0.0238,
      "step": 50
    },
    {
      "epoch": 1.9645909645909647,
      "eval_loss": 0.06207295507192612,
      "eval_runtime": 2.9728,
      "eval_samples_per_second": 16.819,
      "eval_steps_per_second": 4.373,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 5.32019209568256e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}