{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.4497751124437781,
  "eval_steps": 50,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005997001499250375,
      "grad_norm": NaN,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.005997001499250375,
      "eval_loss": NaN,
      "eval_runtime": 16.1656,
      "eval_samples_per_second": 17.383,
      "eval_steps_per_second": 4.392,
      "step": 1
    },
    {
      "epoch": 0.01199400299850075,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.017991004497751123,
      "grad_norm": NaN,
      "learning_rate": 1.5e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0239880059970015,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.029985007496251874,
      "grad_norm": NaN,
      "learning_rate": 2.5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.035982008995502246,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.041979010494752625,
      "grad_norm": NaN,
      "learning_rate": 3.5e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.047976011994003,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.053973013493253376,
      "grad_norm": NaN,
      "learning_rate": 4.5e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.05997001499250375,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.06596701649175413,
      "grad_norm": NaN,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.07196401799100449,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.07796101949025487,
      "grad_norm": NaN,
      "learning_rate": 6.500000000000001e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.08395802098950525,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.08995502248875563,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.095952023988006,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.10194902548725637,
      "grad_norm": NaN,
      "learning_rate": 8.5e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.10794602698650675,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.11394302848575712,
      "grad_norm": NaN,
      "learning_rate": 9.5e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.1199400299850075,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.12593703148425786,
      "grad_norm": NaN,
      "learning_rate": 9.991845519630678e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.13193403298350825,
      "grad_norm": NaN,
      "learning_rate": 9.967408676742751e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.13793103448275862,
      "grad_norm": NaN,
      "learning_rate": 9.926769179238466e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.14392803598200898,
      "grad_norm": NaN,
      "learning_rate": 9.870059584711668e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.14992503748125938,
      "grad_norm": NaN,
      "learning_rate": 9.797464868072488e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.15592203898050974,
      "grad_norm": NaN,
      "learning_rate": 9.709221818197624e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.1619190404797601,
      "grad_norm": NaN,
      "learning_rate": 9.60561826557425e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.1679160419790105,
      "grad_norm": NaN,
      "learning_rate": 9.486992143456792e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": NaN,
      "learning_rate": 9.353730385598887e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.17991004497751126,
      "grad_norm": NaN,
      "learning_rate": 9.206267664155907e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.18590704647676162,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.191904047976012,
      "grad_norm": NaN,
      "learning_rate": 8.870708053195413e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.19790104947526238,
      "grad_norm": NaN,
      "learning_rate": 8.683705689382024e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.20389805097451275,
      "grad_norm": NaN,
      "learning_rate": 8.484687843276469e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.2098950524737631,
      "grad_norm": NaN,
      "learning_rate": 8.274303669726426e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.2158920539730135,
      "grad_norm": NaN,
      "learning_rate": 8.053239398177191e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.22188905547226387,
      "grad_norm": NaN,
      "learning_rate": 7.822216094333847e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.22788605697151423,
      "grad_norm": NaN,
      "learning_rate": 7.58198730819481e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.23388305847076463,
      "grad_norm": NaN,
      "learning_rate": 7.333336616128369e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.239880059970015,
      "grad_norm": NaN,
      "learning_rate": 7.077075065009433e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.24587706146926536,
      "grad_norm": NaN,
      "learning_rate": 6.814038526753205e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.2518740629685157,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.25787106446776614,
      "grad_norm": NaN,
      "learning_rate": 6.271091670967436e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.2638680659670165,
      "grad_norm": NaN,
      "learning_rate": 5.992952333228728e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.2698650674662669,
      "grad_norm": NaN,
      "learning_rate": 5.7115741913664264e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.27586206896551724,
      "grad_norm": NaN,
      "learning_rate": 5.427875042394199e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.2818590704647676,
      "grad_norm": NaN,
      "learning_rate": 5.142780253968481e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.28785607196401797,
      "grad_norm": NaN,
      "learning_rate": 4.85721974603152e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.2938530734632684,
      "grad_norm": NaN,
      "learning_rate": 4.5721249576058027e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.29985007496251875,
      "grad_norm": NaN,
      "learning_rate": 4.288425808633575e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.29985007496251875,
      "eval_loss": NaN,
      "eval_runtime": 15.6379,
      "eval_samples_per_second": 17.969,
      "eval_steps_per_second": 4.54,
      "step": 50
    },
    {
      "epoch": 0.3058470764617691,
      "grad_norm": NaN,
      "learning_rate": 4.007047666771274e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.3118440779610195,
      "grad_norm": NaN,
      "learning_rate": 3.728908329032567e-05,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.31784107946026985,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.3238380809595202,
      "grad_norm": NaN,
      "learning_rate": 3.1859614732467954e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.32983508245877063,
      "grad_norm": NaN,
      "learning_rate": 2.9229249349905684e-05,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.335832083958021,
      "grad_norm": NaN,
      "learning_rate": 2.6666633838716314e-05,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.34182908545727136,
      "grad_norm": NaN,
      "learning_rate": 2.418012691805191e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": NaN,
      "learning_rate": 2.1777839056661554e-05,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.3538230884557721,
      "grad_norm": NaN,
      "learning_rate": 1.946760601822809e-05,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.3598200899550225,
      "grad_norm": NaN,
      "learning_rate": 1.725696330273575e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.3658170914542729,
      "grad_norm": NaN,
      "learning_rate": 1.5153121567235335e-05,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.37181409295352325,
      "grad_norm": NaN,
      "learning_rate": 1.3162943106179749e-05,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.3778110944527736,
      "grad_norm": NaN,
      "learning_rate": 1.1292919468045877e-05,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.383808095952024,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.38980509745127434,
      "grad_norm": NaN,
      "learning_rate": 7.937323358440935e-06,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.39580209895052476,
      "grad_norm": NaN,
      "learning_rate": 6.462696144011149e-06,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.4017991004497751,
      "grad_norm": NaN,
      "learning_rate": 5.13007856543209e-06,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.4077961019490255,
      "grad_norm": NaN,
      "learning_rate": 3.9438173442575e-06,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.41379310344827586,
      "grad_norm": NaN,
      "learning_rate": 2.9077818180237693e-06,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.4197901049475262,
      "grad_norm": NaN,
      "learning_rate": 2.0253513192751373e-06,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.4257871064467766,
      "grad_norm": NaN,
      "learning_rate": 1.2994041528833266e-06,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.431784107946027,
      "grad_norm": NaN,
      "learning_rate": 7.323082076153509e-07,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.43778110944527737,
      "grad_norm": NaN,
      "learning_rate": 3.2591323257248893e-07,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.44377811094452774,
      "grad_norm": NaN,
      "learning_rate": 8.15448036932176e-08,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.4497751124437781,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": 4.0821709602816e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}