{
  "best_metric": 0.3793780505657196,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.021443122118580467,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008577248847432186,
      "grad_norm": 12.92812728881836,
      "learning_rate": 5e-05,
      "loss": 13.7551,
      "step": 1
    },
    {
      "epoch": 0.0008577248847432186,
      "eval_loss": 13.996685981750488,
      "eval_runtime": 108.0832,
      "eval_samples_per_second": 72.675,
      "eval_steps_per_second": 9.086,
      "step": 1
    },
    {
      "epoch": 0.0017154497694864372,
      "grad_norm": 13.094124794006348,
      "learning_rate": 0.0001,
      "loss": 13.8213,
      "step": 2
    },
    {
      "epoch": 0.002573174654229656,
      "grad_norm": 12.58607292175293,
      "learning_rate": 9.989294616193017e-05,
      "loss": 13.2913,
      "step": 3
    },
    {
      "epoch": 0.0034308995389728744,
      "grad_norm": 13.859800338745117,
      "learning_rate": 9.957224306869053e-05,
      "loss": 12.6391,
      "step": 4
    },
    {
      "epoch": 0.004288624423716093,
      "grad_norm": 14.470093727111816,
      "learning_rate": 9.903926402016153e-05,
      "loss": 11.7805,
      "step": 5
    },
    {
      "epoch": 0.005146349308459312,
      "grad_norm": 17.368301391601562,
      "learning_rate": 9.829629131445342e-05,
      "loss": 10.0526,
      "step": 6
    },
    {
      "epoch": 0.00600407419320253,
      "grad_norm": 16.13571548461914,
      "learning_rate": 9.73465064747553e-05,
      "loss": 8.6898,
      "step": 7
    },
    {
      "epoch": 0.006861799077945749,
      "grad_norm": 10.188413619995117,
      "learning_rate": 9.619397662556435e-05,
      "loss": 7.4542,
      "step": 8
    },
    {
      "epoch": 0.0077195239626889674,
      "grad_norm": 8.34696102142334,
      "learning_rate": 9.484363707663442e-05,
      "loss": 6.6271,
      "step": 9
    },
    {
      "epoch": 0.008577248847432186,
      "grad_norm": 8.511825561523438,
      "learning_rate": 9.330127018922194e-05,
      "loss": 6.3326,
      "step": 10
    },
    {
      "epoch": 0.009434973732175405,
      "grad_norm": 9.587252616882324,
      "learning_rate": 9.157348061512727e-05,
      "loss": 5.8083,
      "step": 11
    },
    {
      "epoch": 0.010292698616918623,
      "grad_norm": 8.795230865478516,
      "learning_rate": 8.966766701456177e-05,
      "loss": 5.1104,
      "step": 12
    },
    {
      "epoch": 0.011150423501661842,
      "grad_norm": 9.211018562316895,
      "learning_rate": 8.759199037394887e-05,
      "loss": 4.5715,
      "step": 13
    },
    {
      "epoch": 0.01200814838640506,
      "grad_norm": 10.63537883758545,
      "learning_rate": 8.535533905932738e-05,
      "loss": 4.1549,
      "step": 14
    },
    {
      "epoch": 0.012865873271148279,
      "grad_norm": 10.278818130493164,
      "learning_rate": 8.296729075500344e-05,
      "loss": 3.3195,
      "step": 15
    },
    {
      "epoch": 0.013723598155891498,
      "grad_norm": 10.10770034790039,
      "learning_rate": 8.043807145043604e-05,
      "loss": 2.3518,
      "step": 16
    },
    {
      "epoch": 0.014581323040634716,
      "grad_norm": 9.630901336669922,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.6606,
      "step": 17
    },
    {
      "epoch": 0.015439047925377935,
      "grad_norm": 12.14709758758545,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.5045,
      "step": 18
    },
    {
      "epoch": 0.016296772810121155,
      "grad_norm": 19.266517639160156,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.6638,
      "step": 19
    },
    {
      "epoch": 0.017154497694864372,
      "grad_norm": 23.16864776611328,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.0759,
      "step": 20
    },
    {
      "epoch": 0.018012222579607592,
      "grad_norm": 20.27104377746582,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.5276,
      "step": 21
    },
    {
      "epoch": 0.01886994746435081,
      "grad_norm": 14.844281196594238,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.1807,
      "step": 22
    },
    {
      "epoch": 0.01972767234909403,
      "grad_norm": 7.327539443969727,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.7838,
      "step": 23
    },
    {
      "epoch": 0.020585397233837247,
      "grad_norm": 3.2017087936401367,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.4805,
      "step": 24
    },
    {
      "epoch": 0.021443122118580467,
      "grad_norm": 2.8846960067749023,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.48,
      "step": 25
    },
    {
      "epoch": 0.021443122118580467,
      "eval_loss": 0.3793780505657196,
      "eval_runtime": 107.9345,
      "eval_samples_per_second": 72.776,
      "eval_steps_per_second": 9.098,
      "step": 25
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.367151308931072e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}