{
  "best_metric": 1.713279128074646,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.07802594362625573,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015605188725251145,
      "grad_norm": 25.614656448364258,
      "learning_rate": 5e-05,
      "loss": 3.6352,
      "step": 1
    },
    {
      "epoch": 0.0015605188725251145,
      "eval_loss": 5.159157752990723,
      "eval_runtime": 284.5169,
      "eval_samples_per_second": 15.173,
      "eval_steps_per_second": 1.898,
      "step": 1
    },
    {
      "epoch": 0.003121037745050229,
      "grad_norm": 34.22014617919922,
      "learning_rate": 0.0001,
      "loss": 3.9431,
      "step": 2
    },
    {
      "epoch": 0.004681556617575344,
      "grad_norm": 49.7406120300293,
      "learning_rate": 9.989294616193017e-05,
      "loss": 4.2284,
      "step": 3
    },
    {
      "epoch": 0.006242075490100458,
      "grad_norm": 49.14342498779297,
      "learning_rate": 9.957224306869053e-05,
      "loss": 4.1624,
      "step": 4
    },
    {
      "epoch": 0.007802594362625573,
      "grad_norm": 66.93302154541016,
      "learning_rate": 9.903926402016153e-05,
      "loss": 3.7709,
      "step": 5
    },
    {
      "epoch": 0.009363113235150688,
      "grad_norm": 62.800899505615234,
      "learning_rate": 9.829629131445342e-05,
      "loss": 3.0535,
      "step": 6
    },
    {
      "epoch": 0.010923632107675801,
      "grad_norm": 49.48344039916992,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.4858,
      "step": 7
    },
    {
      "epoch": 0.012484150980200916,
      "grad_norm": 27.821107864379883,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.1809,
      "step": 8
    },
    {
      "epoch": 0.014044669852726031,
      "grad_norm": 35.124420166015625,
      "learning_rate": 9.484363707663442e-05,
      "loss": 2.0234,
      "step": 9
    },
    {
      "epoch": 0.015605188725251146,
      "grad_norm": 32.269737243652344,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.7482,
      "step": 10
    },
    {
      "epoch": 0.01716570759777626,
      "grad_norm": 17.856338500976562,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.6042,
      "step": 11
    },
    {
      "epoch": 0.018726226470301376,
      "grad_norm": 35.518592834472656,
      "learning_rate": 8.966766701456177e-05,
      "loss": 2.0972,
      "step": 12
    },
    {
      "epoch": 0.02028674534282649,
      "grad_norm": 28.791309356689453,
      "learning_rate": 8.759199037394887e-05,
      "loss": 2.4104,
      "step": 13
    },
    {
      "epoch": 0.021847264215351603,
      "grad_norm": 30.415395736694336,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.3745,
      "step": 14
    },
    {
      "epoch": 0.023407783087876718,
      "grad_norm": 27.66350555419922,
      "learning_rate": 8.296729075500344e-05,
      "loss": 2.3036,
      "step": 15
    },
    {
      "epoch": 0.024968301960401833,
      "grad_norm": 21.38483238220215,
      "learning_rate": 8.043807145043604e-05,
      "loss": 2.1492,
      "step": 16
    },
    {
      "epoch": 0.026528820832926948,
      "grad_norm": 17.575420379638672,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.9066,
      "step": 17
    },
    {
      "epoch": 0.028089339705452063,
      "grad_norm": 14.879024505615234,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.7688,
      "step": 18
    },
    {
      "epoch": 0.029649858577977178,
      "grad_norm": 11.665847778320312,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.7369,
      "step": 19
    },
    {
      "epoch": 0.031210377450502293,
      "grad_norm": 12.309723854064941,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.5185,
      "step": 20
    },
    {
      "epoch": 0.032770896323027404,
      "grad_norm": 11.682272911071777,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.6529,
      "step": 21
    },
    {
      "epoch": 0.03433141519555252,
      "grad_norm": 13.07605266571045,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.5751,
      "step": 22
    },
    {
      "epoch": 0.035891934068077634,
      "grad_norm": 11.294489860534668,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.5015,
      "step": 23
    },
    {
      "epoch": 0.03745245294060275,
      "grad_norm": 16.308387756347656,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.4213,
      "step": 24
    },
    {
      "epoch": 0.039012971813127864,
      "grad_norm": 21.209440231323242,
      "learning_rate": 5.327015646150716e-05,
      "loss": 2.236,
      "step": 25
    },
    {
      "epoch": 0.039012971813127864,
      "eval_loss": 1.7844452857971191,
      "eval_runtime": 284.2939,
      "eval_samples_per_second": 15.185,
      "eval_steps_per_second": 1.899,
      "step": 25
    },
    {
      "epoch": 0.04057349068565298,
      "grad_norm": 11.710362434387207,
      "learning_rate": 5e-05,
      "loss": 2.1715,
      "step": 26
    },
    {
      "epoch": 0.042134009558178094,
      "grad_norm": 14.576261520385742,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 2.0575,
      "step": 27
    },
    {
      "epoch": 0.043694528430703206,
      "grad_norm": 13.412975311279297,
      "learning_rate": 4.347369038899744e-05,
      "loss": 1.9133,
      "step": 28
    },
    {
      "epoch": 0.045255047303228324,
      "grad_norm": 11.340127944946289,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 1.819,
      "step": 29
    },
    {
      "epoch": 0.046815566175753436,
      "grad_norm": 11.435134887695312,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.8139,
      "step": 30
    },
    {
      "epoch": 0.048376085048278554,
      "grad_norm": 10.115267753601074,
      "learning_rate": 3.392802673484193e-05,
      "loss": 1.7239,
      "step": 31
    },
    {
      "epoch": 0.049936603920803666,
      "grad_norm": 7.939040660858154,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.5591,
      "step": 32
    },
    {
      "epoch": 0.051497122793328784,
      "grad_norm": 8.323566436767578,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 1.5233,
      "step": 33
    },
    {
      "epoch": 0.053057641665853895,
      "grad_norm": 8.962291717529297,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.6057,
      "step": 34
    },
    {
      "epoch": 0.054618160538379014,
      "grad_norm": 11.388747215270996,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.3288,
      "step": 35
    },
    {
      "epoch": 0.056178679410904125,
      "grad_norm": 9.159733772277832,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 1.467,
      "step": 36
    },
    {
      "epoch": 0.05773919828342924,
      "grad_norm": 18.99442481994629,
      "learning_rate": 1.703270924499656e-05,
      "loss": 1.8765,
      "step": 37
    },
    {
      "epoch": 0.059299717155954355,
      "grad_norm": 25.547096252441406,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.1997,
      "step": 38
    },
    {
      "epoch": 0.06086023602847947,
      "grad_norm": 7.026412487030029,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 2.0025,
      "step": 39
    },
    {
      "epoch": 0.062420754901004585,
      "grad_norm": 7.772118091583252,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 2.0808,
      "step": 40
    },
    {
      "epoch": 0.0639812737735297,
      "grad_norm": 6.68425989151001,
      "learning_rate": 8.426519384872733e-06,
      "loss": 1.8221,
      "step": 41
    },
    {
      "epoch": 0.06554179264605481,
      "grad_norm": 6.783787250518799,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.8117,
      "step": 42
    },
    {
      "epoch": 0.06710231151857993,
      "grad_norm": 8.404589653015137,
      "learning_rate": 5.156362923365588e-06,
      "loss": 1.8148,
      "step": 43
    },
    {
      "epoch": 0.06866283039110505,
      "grad_norm": 6.892530918121338,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.6587,
      "step": 44
    },
    {
      "epoch": 0.07022334926363016,
      "grad_norm": 6.792155742645264,
      "learning_rate": 2.653493525244721e-06,
      "loss": 1.6503,
      "step": 45
    },
    {
      "epoch": 0.07178386813615527,
      "grad_norm": 8.016270637512207,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.515,
      "step": 46
    },
    {
      "epoch": 0.07334438700868039,
      "grad_norm": 10.944890975952148,
      "learning_rate": 9.607359798384785e-07,
      "loss": 1.457,
      "step": 47
    },
    {
      "epoch": 0.0749049058812055,
      "grad_norm": 9.899993896484375,
      "learning_rate": 4.277569313094809e-07,
      "loss": 1.4708,
      "step": 48
    },
    {
      "epoch": 0.07646542475373061,
      "grad_norm": 12.46395492553711,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 1.5409,
      "step": 49
    },
    {
      "epoch": 0.07802594362625573,
      "grad_norm": 30.2358341217041,
      "learning_rate": 0.0,
      "loss": 2.1207,
      "step": 50
    },
    {
      "epoch": 0.07802594362625573,
      "eval_loss": 1.713279128074646,
      "eval_runtime": 284.2744,
      "eval_samples_per_second": 15.186,
      "eval_steps_per_second": 1.9,
      "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": 1.0937288838086656e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}