{
  "best_metric": 0.125091552734375,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.01936061566757823,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003872123133515646,
      "grad_norm": 18.16028594970703,
      "learning_rate": 5e-05,
      "loss": 3.8364,
      "step": 1
    },
    {
      "epoch": 0.0003872123133515646,
      "eval_loss": 3.8023195266723633,
      "eval_runtime": 1.0601,
      "eval_samples_per_second": 47.164,
      "eval_steps_per_second": 12.263,
      "step": 1
    },
    {
      "epoch": 0.0007744246267031292,
      "grad_norm": 22.473400115966797,
      "learning_rate": 0.0001,
      "loss": 3.4645,
      "step": 2
    },
    {
      "epoch": 0.0011616369400546938,
      "grad_norm": 19.02566146850586,
      "learning_rate": 9.990365154573717e-05,
      "loss": 2.6184,
      "step": 3
    },
    {
      "epoch": 0.0015488492534062584,
      "grad_norm": 21.600830078125,
      "learning_rate": 9.961501876182148e-05,
      "loss": 1.43,
      "step": 4
    },
    {
      "epoch": 0.001936061566757823,
      "grad_norm": 19.741262435913086,
      "learning_rate": 9.913533761814537e-05,
      "loss": 0.6431,
      "step": 5
    },
    {
      "epoch": 0.0023232738801093875,
      "grad_norm": 11.153435707092285,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.253,
      "step": 6
    },
    {
      "epoch": 0.002710486193460952,
      "grad_norm": 2.835373640060425,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.0659,
      "step": 7
    },
    {
      "epoch": 0.0030976985068125167,
      "grad_norm": 1.113729476928711,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.0182,
      "step": 8
    },
    {
      "epoch": 0.003484910820164081,
      "grad_norm": 0.1847342848777771,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.0018,
      "step": 9
    },
    {
      "epoch": 0.003872123133515646,
      "grad_norm": 0.07096876949071884,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.0006,
      "step": 10
    },
    {
      "epoch": 0.00425933544686721,
      "grad_norm": 26.590452194213867,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.835,
      "step": 11
    },
    {
      "epoch": 0.004646547760218775,
      "grad_norm": 66.93146514892578,
      "learning_rate": 9.070090031310558e-05,
      "loss": 5.1252,
      "step": 12
    },
    {
      "epoch": 0.00503376007357034,
      "grad_norm": 34.6375732421875,
      "learning_rate": 8.883279133655399e-05,
      "loss": 2.8687,
      "step": 13
    },
    {
      "epoch": 0.005420972386921904,
      "grad_norm": 0.094404436647892,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0008,
      "step": 14
    },
    {
      "epoch": 0.005808184700273469,
      "grad_norm": 0.21153391897678375,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.0016,
      "step": 15
    },
    {
      "epoch": 0.0061953970136250334,
      "grad_norm": 0.1117037683725357,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.0009,
      "step": 16
    },
    {
      "epoch": 0.006582609326976598,
      "grad_norm": 0.04247026517987251,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.0004,
      "step": 17
    },
    {
      "epoch": 0.006969821640328162,
      "grad_norm": 0.01981361396610737,
      "learning_rate": 7.75e-05,
      "loss": 0.0002,
      "step": 18
    },
    {
      "epoch": 0.007357033953679727,
      "grad_norm": 0.014555519446730614,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.0002,
      "step": 19
    },
    {
      "epoch": 0.007744246267031292,
      "grad_norm": 0.012003647163510323,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.0001,
      "step": 20
    },
    {
      "epoch": 0.008131458580382856,
      "grad_norm": 0.010216341353952885,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.0001,
      "step": 21
    },
    {
      "epoch": 0.00851867089373442,
      "grad_norm": 0.009024460799992085,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.0001,
      "step": 22
    },
    {
      "epoch": 0.008905883207085985,
      "grad_norm": 4.160756587982178,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.197,
      "step": 23
    },
    {
      "epoch": 0.00929309552043755,
      "grad_norm": 24.864112854003906,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.9827,
      "step": 24
    },
    {
      "epoch": 0.009680307833789115,
      "grad_norm": 18.88389778137207,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.3892,
      "step": 25
    },
    {
      "epoch": 0.009680307833789115,
      "eval_loss": 0.13366584479808807,
      "eval_runtime": 0.5865,
      "eval_samples_per_second": 85.25,
      "eval_steps_per_second": 22.165,
      "step": 25
    },
    {
      "epoch": 0.01006752014714068,
      "grad_norm": 15.704390525817871,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.4165,
      "step": 26
    },
    {
      "epoch": 0.010454732460492243,
      "grad_norm": 13.66524600982666,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.1935,
      "step": 27
    },
    {
      "epoch": 0.010841944773843808,
      "grad_norm": 7.263870716094971,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.0652,
      "step": 28
    },
    {
      "epoch": 0.011229157087195372,
      "grad_norm": 0.8715264797210693,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.0094,
      "step": 29
    },
    {
      "epoch": 0.011616369400546937,
      "grad_norm": 0.25349822640419006,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.0031,
      "step": 30
    },
    {
      "epoch": 0.012003581713898502,
      "grad_norm": 0.12796880304813385,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.0017,
      "step": 31
    },
    {
      "epoch": 0.012390794027250067,
      "grad_norm": 0.08409107476472855,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.0011,
      "step": 32
    },
    {
      "epoch": 0.012778006340601632,
      "grad_norm": 0.06334452331066132,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.0008,
      "step": 33
    },
    {
      "epoch": 0.013165218653953197,
      "grad_norm": 0.04625517874956131,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.0006,
      "step": 34
    },
    {
      "epoch": 0.01355243096730476,
      "grad_norm": 0.034825753420591354,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.0004,
      "step": 35
    },
    {
      "epoch": 0.013939643280656324,
      "grad_norm": 3.619255542755127,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.3384,
      "step": 36
    },
    {
      "epoch": 0.01432685559400789,
      "grad_norm": 10.225979804992676,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.9736,
      "step": 37
    },
    {
      "epoch": 0.014714067907359454,
      "grad_norm": 8.408079147338867,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 1.1675,
      "step": 38
    },
    {
      "epoch": 0.015101280220711019,
      "grad_norm": 0.10028885304927826,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.0011,
      "step": 39
    },
    {
      "epoch": 0.015488492534062584,
      "grad_norm": 0.1408945918083191,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.0016,
      "step": 40
    },
    {
      "epoch": 0.015875704847414147,
      "grad_norm": 0.1793322116136551,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.002,
      "step": 41
    },
    {
      "epoch": 0.01626291716076571,
      "grad_norm": 0.20124785602092743,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.0023,
      "step": 42
    },
    {
      "epoch": 0.016650129474117276,
      "grad_norm": 0.20105940103530884,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.0024,
      "step": 43
    },
    {
      "epoch": 0.01703734178746884,
      "grad_norm": 0.18423613905906677,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.0022,
      "step": 44
    },
    {
      "epoch": 0.017424554100820406,
      "grad_norm": 0.15948553383350372,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.002,
      "step": 45
    },
    {
      "epoch": 0.01781176641417197,
      "grad_norm": 0.1380118727684021,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.0017,
      "step": 46
    },
    {
      "epoch": 0.018198978727523536,
      "grad_norm": 0.1117352768778801,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.0014,
      "step": 47
    },
    {
      "epoch": 0.0185861910408751,
      "grad_norm": 0.09928926080465317,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.0013,
      "step": 48
    },
    {
      "epoch": 0.018973403354226665,
      "grad_norm": 7.759567737579346,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.5652,
      "step": 49
    },
    {
      "epoch": 0.01936061566757823,
      "grad_norm": 7.83549165725708,
      "learning_rate": 1e-05,
      "loss": 0.5574,
      "step": 50
    },
    {
      "epoch": 0.01936061566757823,
      "eval_loss": 0.125091552734375,
      "eval_runtime": 0.5635,
      "eval_samples_per_second": 88.738,
      "eval_steps_per_second": 23.072,
      "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": 2.95300912644096e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}