{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.028238616307800918,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005647723261560184,
      "grad_norm": 0.0,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0005647723261560184,
      "eval_loss": NaN,
      "eval_runtime": 822.1371,
      "eval_samples_per_second": 14.51,
      "eval_steps_per_second": 1.815,
      "step": 1
    },
    {
      "epoch": 0.0011295446523120368,
      "grad_norm": 0.0,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.001694316978468055,
      "grad_norm": 0.0,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0022590893046240735,
      "grad_norm": 0.0,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0028238616307800918,
      "grad_norm": 0.0,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00338863395693611,
      "grad_norm": 0.0,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.003953406283092128,
      "grad_norm": 0.0,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.004518178609248147,
      "grad_norm": 0.0,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.005082950935404165,
      "grad_norm": 0.0,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0056477232615601836,
      "grad_norm": 0.0,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.006212495587716202,
      "grad_norm": 0.0,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.00677726791387222,
      "grad_norm": 0.0,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.007342040240028239,
      "grad_norm": 0.0,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.007906812566184257,
      "grad_norm": 0.0,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.008471584892340275,
      "grad_norm": 0.0,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.009036357218496294,
      "grad_norm": 0.0,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.009601129544652313,
      "grad_norm": 0.0,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.01016590187080833,
      "grad_norm": 0.0,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.010730674196964348,
      "grad_norm": 0.0,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.011295446523120367,
      "grad_norm": 0.0,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.011860218849276386,
      "grad_norm": 0.0,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.012424991175432405,
      "grad_norm": 0.0,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.012989763501588421,
      "grad_norm": 0.0,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.01355453582774444,
      "grad_norm": 0.0,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.014119308153900459,
      "grad_norm": 0.0,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.014119308153900459,
      "eval_loss": NaN,
      "eval_runtime": 821.1961,
      "eval_samples_per_second": 14.526,
      "eval_steps_per_second": 1.817,
      "step": 25
    },
    {
      "epoch": 0.014684080480056478,
      "grad_norm": 0.0,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.015248852806212496,
      "grad_norm": 0.0,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.015813625132368513,
      "grad_norm": 0.0,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.016378397458524534,
      "grad_norm": 0.0,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.01694316978468055,
      "grad_norm": 0.0,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.017507942110836568,
      "grad_norm": 0.0,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.018072714436992588,
      "grad_norm": 0.0,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.018637486763148605,
      "grad_norm": 0.0,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.019202259089304625,
      "grad_norm": 0.0,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.019767031415460642,
      "grad_norm": 0.0,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.02033180374161666,
      "grad_norm": 0.0,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.02089657606777268,
      "grad_norm": 0.0,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.021461348393928697,
      "grad_norm": 0.0,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.022026120720084717,
      "grad_norm": 0.0,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.022590893046240734,
      "grad_norm": 0.0,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.02315566537239675,
      "grad_norm": 0.0,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.02372043769855277,
      "grad_norm": 0.0,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.02428521002470879,
      "grad_norm": 0.0,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.02484998235086481,
      "grad_norm": 0.0,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.025414754677020826,
      "grad_norm": 0.0,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.025979527003176843,
      "grad_norm": 0.0,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.026544299329332863,
      "grad_norm": 0.0,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.02710907165548888,
      "grad_norm": 0.0,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.0276738439816449,
      "grad_norm": 0.0,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.028238616307800918,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.028238616307800918,
      "eval_loss": NaN,
      "eval_runtime": 821.5363,
      "eval_samples_per_second": 14.52,
      "eval_steps_per_second": 1.816,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.174479344467968e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}