{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.035895365010992955,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007179073002198591,
      "grad_norm": NaN,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0007179073002198591,
      "eval_loss": NaN,
      "eval_runtime": 0.7466,
      "eval_samples_per_second": 66.968,
      "eval_steps_per_second": 17.412,
      "step": 1
    },
    {
      "epoch": 0.0014358146004397182,
      "grad_norm": NaN,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0021537219006595772,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0028716292008794365,
      "grad_norm": NaN,
      "learning_rate": 9.997376600647783e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0035895365010992957,
      "grad_norm": NaN,
      "learning_rate": 9.989509461357426e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0043074438013191545,
      "grad_norm": NaN,
      "learning_rate": 9.976407754861426e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.005025351101539014,
      "grad_norm": NaN,
      "learning_rate": 9.958086757163489e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.005743258401758873,
      "grad_norm": NaN,
      "learning_rate": 9.934567829727386e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.006461165701978732,
      "grad_norm": NaN,
      "learning_rate": 9.905878394570453e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.007179073002198591,
      "grad_norm": NaN,
      "learning_rate": 9.872051902290737e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.007896980302418451,
      "grad_norm": NaN,
      "learning_rate": 9.833127793065098e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.008614887602638309,
      "grad_norm": NaN,
      "learning_rate": 9.789151450663723e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.009332794902858169,
      "grad_norm": NaN,
      "learning_rate": 9.740174149534693e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.010050702203078028,
      "grad_norm": NaN,
      "learning_rate": 9.686252995020249e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.010768609503297886,
      "grad_norm": NaN,
      "learning_rate": 9.627450856774539e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.011486516803517746,
      "grad_norm": NaN,
      "learning_rate": 9.563836295460398e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.012204424103737605,
      "grad_norm": NaN,
      "learning_rate": 9.495483482810688e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.012922331403957463,
      "grad_norm": NaN,
      "learning_rate": 9.422472115147382e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.013640238704177323,
      "grad_norm": NaN,
      "learning_rate": 9.3448873204592e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.014358146004397183,
      "grad_norm": NaN,
      "learning_rate": 9.2628195591462e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.01507605330461704,
      "grad_norm": NaN,
      "learning_rate": 9.176364518546989e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.015793960604836902,
      "grad_norm": NaN,
      "learning_rate": 9.08562300137157e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.016511867905056758,
      "grad_norm": NaN,
      "learning_rate": 8.990700808169889e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.017229775205276618,
      "grad_norm": NaN,
      "learning_rate": 8.891708613973126e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.017947682505496478,
      "grad_norm": NaN,
      "learning_rate": 8.788761839251559e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.017947682505496478,
      "eval_loss": NaN,
      "eval_runtime": 0.7392,
      "eval_samples_per_second": 67.636,
      "eval_steps_per_second": 17.585,
      "step": 25
    },
    {
      "epoch": 0.018665589805716337,
      "grad_norm": NaN,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.019383497105936197,
      "grad_norm": NaN,
      "learning_rate": 8.571489144483944e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.020101404406156057,
      "grad_norm": NaN,
      "learning_rate": 8.457416554680877e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.020819311706375913,
      "grad_norm": NaN,
      "learning_rate": 8.339895749467238e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.021537219006595772,
      "grad_norm": NaN,
      "learning_rate": 8.219063752844926e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.022255126306815632,
      "grad_norm": NaN,
      "learning_rate": 8.095061449516903e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.02297303360703549,
      "grad_norm": NaN,
      "learning_rate": 7.968033420621935e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.02369094090725535,
      "grad_norm": NaN,
      "learning_rate": 7.838127775159452e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.02440884820747521,
      "grad_norm": NaN,
      "learning_rate": 7.705495977301078e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.025126755507695067,
      "grad_norm": NaN,
      "learning_rate": 7.570292669790186e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.025844662807914927,
      "grad_norm": NaN,
      "learning_rate": 7.43267549363537e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.026562570108134786,
      "grad_norm": NaN,
      "learning_rate": 7.292804904308087e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.027280477408354646,
      "grad_norm": NaN,
      "learning_rate": 7.150843984658754e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.027998384708574506,
      "grad_norm": NaN,
      "learning_rate": 7.006958254769438e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.028716292008794365,
      "grad_norm": NaN,
      "learning_rate": 6.861315478964841e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.029434199309014225,
      "grad_norm": NaN,
      "learning_rate": 6.714085470206609e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.03015210660923408,
      "grad_norm": NaN,
      "learning_rate": 6.56543989209901e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.03087001390945394,
      "grad_norm": NaN,
      "learning_rate": 6.415552058736854e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.031587921209673804,
      "grad_norm": NaN,
      "learning_rate": 6.264596732629e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.03230582850989366,
      "grad_norm": NaN,
      "learning_rate": 6.112749920933111e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.033023735810113516,
      "grad_norm": NaN,
      "learning_rate": 5.960188670239154e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.033741643110333376,
      "grad_norm": NaN,
      "learning_rate": 5.80709086014102e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.034459550410553236,
      "grad_norm": NaN,
      "learning_rate": 5.653634995836856e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.035177457710773095,
      "grad_norm": NaN,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.035895365010992955,
      "grad_norm": NaN,
      "learning_rate": 5.346365004163145e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.035895365010992955,
      "eval_loss": NaN,
      "eval_runtime": 0.7524,
      "eval_samples_per_second": 66.453,
      "eval_steps_per_second": 17.278,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 95,
  "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": 1
      }
    },
    "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": 1,
  "trial_name": null,
  "trial_params": null
}