{
  "best_metric": 11.91208553314209,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.2290950744558992,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004581901489117984,
      "grad_norm": 0.07584026455879211,
      "learning_rate": 5e-05,
      "loss": 11.9187,
      "step": 1
    },
    {
      "epoch": 0.004581901489117984,
      "eval_loss": 11.921486854553223,
      "eval_runtime": 2.8768,
      "eval_samples_per_second": 510.988,
      "eval_steps_per_second": 63.96,
      "step": 1
    },
    {
      "epoch": 0.009163802978235968,
      "grad_norm": 0.0752248540520668,
      "learning_rate": 0.0001,
      "loss": 11.9227,
      "step": 2
    },
    {
      "epoch": 0.013745704467353952,
      "grad_norm": 0.07713150978088379,
      "learning_rate": 9.989294616193017e-05,
      "loss": 11.9223,
      "step": 3
    },
    {
      "epoch": 0.018327605956471937,
      "grad_norm": 0.07691174745559692,
      "learning_rate": 9.957224306869053e-05,
      "loss": 11.9244,
      "step": 4
    },
    {
      "epoch": 0.022909507445589918,
      "grad_norm": 0.08752486854791641,
      "learning_rate": 9.903926402016153e-05,
      "loss": 11.9218,
      "step": 5
    },
    {
      "epoch": 0.027491408934707903,
      "grad_norm": 0.0786953940987587,
      "learning_rate": 9.829629131445342e-05,
      "loss": 11.9259,
      "step": 6
    },
    {
      "epoch": 0.032073310423825885,
      "grad_norm": 0.08299648016691208,
      "learning_rate": 9.73465064747553e-05,
      "loss": 11.9239,
      "step": 7
    },
    {
      "epoch": 0.03665521191294387,
      "grad_norm": 0.09089986234903336,
      "learning_rate": 9.619397662556435e-05,
      "loss": 11.9184,
      "step": 8
    },
    {
      "epoch": 0.041237113402061855,
      "grad_norm": 0.09789414703845978,
      "learning_rate": 9.484363707663442e-05,
      "loss": 11.9226,
      "step": 9
    },
    {
      "epoch": 0.045819014891179836,
      "grad_norm": 0.0758046805858612,
      "learning_rate": 9.330127018922194e-05,
      "loss": 11.9194,
      "step": 10
    },
    {
      "epoch": 0.050400916380297825,
      "grad_norm": 0.11443702131509781,
      "learning_rate": 9.157348061512727e-05,
      "loss": 11.9188,
      "step": 11
    },
    {
      "epoch": 0.054982817869415807,
      "grad_norm": 0.1439603716135025,
      "learning_rate": 8.966766701456177e-05,
      "loss": 11.9181,
      "step": 12
    },
    {
      "epoch": 0.05956471935853379,
      "grad_norm": 0.12971708178520203,
      "learning_rate": 8.759199037394887e-05,
      "loss": 11.9198,
      "step": 13
    },
    {
      "epoch": 0.06414662084765177,
      "grad_norm": 0.12059250473976135,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.9241,
      "step": 14
    },
    {
      "epoch": 0.06872852233676977,
      "grad_norm": 0.11569193750619888,
      "learning_rate": 8.296729075500344e-05,
      "loss": 11.9231,
      "step": 15
    },
    {
      "epoch": 0.07331042382588775,
      "grad_norm": 0.11735488474369049,
      "learning_rate": 8.043807145043604e-05,
      "loss": 11.9209,
      "step": 16
    },
    {
      "epoch": 0.07789232531500573,
      "grad_norm": 0.11398056894540787,
      "learning_rate": 7.777851165098012e-05,
      "loss": 11.9175,
      "step": 17
    },
    {
      "epoch": 0.08247422680412371,
      "grad_norm": 0.11920252442359924,
      "learning_rate": 7.500000000000001e-05,
      "loss": 11.9221,
      "step": 18
    },
    {
      "epoch": 0.08705612829324169,
      "grad_norm": 0.12020166218280792,
      "learning_rate": 7.211443451095007e-05,
      "loss": 11.9225,
      "step": 19
    },
    {
      "epoch": 0.09163802978235967,
      "grad_norm": 0.1328224092721939,
      "learning_rate": 6.91341716182545e-05,
      "loss": 11.9192,
      "step": 20
    },
    {
      "epoch": 0.09621993127147767,
      "grad_norm": 0.12654143571853638,
      "learning_rate": 6.607197326515808e-05,
      "loss": 11.9227,
      "step": 21
    },
    {
      "epoch": 0.10080183276059565,
      "grad_norm": 0.12327836453914642,
      "learning_rate": 6.294095225512603e-05,
      "loss": 11.9178,
      "step": 22
    },
    {
      "epoch": 0.10538373424971363,
      "grad_norm": 0.1363614797592163,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 11.9215,
      "step": 23
    },
    {
      "epoch": 0.10996563573883161,
      "grad_norm": 0.16435925662517548,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 11.9148,
      "step": 24
    },
    {
      "epoch": 0.1145475372279496,
      "grad_norm": 0.23081736266613007,
      "learning_rate": 5.327015646150716e-05,
      "loss": 11.9124,
      "step": 25
    },
    {
      "epoch": 0.1145475372279496,
      "eval_loss": 11.914839744567871,
      "eval_runtime": 2.8732,
      "eval_samples_per_second": 511.624,
      "eval_steps_per_second": 64.04,
      "step": 25
    },
    {
      "epoch": 0.11912943871706758,
      "grad_norm": 0.16134200990200043,
      "learning_rate": 5e-05,
      "loss": 11.9197,
      "step": 26
    },
    {
      "epoch": 0.12371134020618557,
      "grad_norm": 0.158481165766716,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 11.9138,
      "step": 27
    },
    {
      "epoch": 0.12829324169530354,
      "grad_norm": 0.1592647284269333,
      "learning_rate": 4.347369038899744e-05,
      "loss": 11.9196,
      "step": 28
    },
    {
      "epoch": 0.13287514318442153,
      "grad_norm": 0.15275534987449646,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 11.9188,
      "step": 29
    },
    {
      "epoch": 0.13745704467353953,
      "grad_norm": 0.15314823389053345,
      "learning_rate": 3.705904774487396e-05,
      "loss": 11.9199,
      "step": 30
    },
    {
      "epoch": 0.1420389461626575,
      "grad_norm": 0.16423438489437103,
      "learning_rate": 3.392802673484193e-05,
      "loss": 11.9197,
      "step": 31
    },
    {
      "epoch": 0.1466208476517755,
      "grad_norm": 0.15110012888908386,
      "learning_rate": 3.086582838174551e-05,
      "loss": 11.9171,
      "step": 32
    },
    {
      "epoch": 0.15120274914089346,
      "grad_norm": 0.17143234610557556,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 11.9123,
      "step": 33
    },
    {
      "epoch": 0.15578465063001146,
      "grad_norm": 0.16207261383533478,
      "learning_rate": 2.500000000000001e-05,
      "loss": 11.9178,
      "step": 34
    },
    {
      "epoch": 0.16036655211912945,
      "grad_norm": 0.16787561774253845,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 11.9114,
      "step": 35
    },
    {
      "epoch": 0.16494845360824742,
      "grad_norm": 0.19097645580768585,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 11.9204,
      "step": 36
    },
    {
      "epoch": 0.16953035509736541,
      "grad_norm": 0.2223094403743744,
      "learning_rate": 1.703270924499656e-05,
      "loss": 11.9158,
      "step": 37
    },
    {
      "epoch": 0.17411225658648338,
      "grad_norm": 0.19997051358222961,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 11.9104,
      "step": 38
    },
    {
      "epoch": 0.17869415807560138,
      "grad_norm": 0.16807907819747925,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 11.9125,
      "step": 39
    },
    {
      "epoch": 0.18327605956471935,
      "grad_norm": 0.1751074492931366,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 11.9143,
      "step": 40
    },
    {
      "epoch": 0.18785796105383734,
      "grad_norm": 0.1698293536901474,
      "learning_rate": 8.426519384872733e-06,
      "loss": 11.9209,
      "step": 41
    },
    {
      "epoch": 0.19243986254295534,
      "grad_norm": 0.17257924377918243,
      "learning_rate": 6.698729810778065e-06,
      "loss": 11.9169,
      "step": 42
    },
    {
      "epoch": 0.1970217640320733,
      "grad_norm": 0.16474071145057678,
      "learning_rate": 5.156362923365588e-06,
      "loss": 11.9164,
      "step": 43
    },
    {
      "epoch": 0.2016036655211913,
      "grad_norm": 0.18104451894760132,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 11.9139,
      "step": 44
    },
    {
      "epoch": 0.20618556701030927,
      "grad_norm": 0.1774343103170395,
      "learning_rate": 2.653493525244721e-06,
      "loss": 11.9098,
      "step": 45
    },
    {
      "epoch": 0.21076746849942726,
      "grad_norm": 0.16952289640903473,
      "learning_rate": 1.70370868554659e-06,
      "loss": 11.9117,
      "step": 46
    },
    {
      "epoch": 0.21534936998854526,
      "grad_norm": 0.17071495950222015,
      "learning_rate": 9.607359798384785e-07,
      "loss": 11.9087,
      "step": 47
    },
    {
      "epoch": 0.21993127147766323,
      "grad_norm": 0.19405154883861542,
      "learning_rate": 4.277569313094809e-07,
      "loss": 11.9147,
      "step": 48
    },
    {
      "epoch": 0.22451317296678122,
      "grad_norm": 0.2187425047159195,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 11.9134,
      "step": 49
    },
    {
      "epoch": 0.2290950744558992,
      "grad_norm": 0.2702491879463196,
      "learning_rate": 0.0,
      "loss": 11.9107,
      "step": 50
    },
    {
      "epoch": 0.2290950744558992,
      "eval_loss": 11.91208553314209,
      "eval_runtime": 2.8843,
      "eval_samples_per_second": 509.649,
      "eval_steps_per_second": 63.793,
      "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": 1042494259200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}