{
  "best_metric": 0.7294516563415527,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.07809449433814916,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0031237797735259665,
      "grad_norm": 123.4577407836914,
      "learning_rate": 5e-05,
      "loss": 1.3888,
      "step": 1
    },
    {
      "epoch": 0.0031237797735259665,
      "eval_loss": 4.010549068450928,
      "eval_runtime": 62.3565,
      "eval_samples_per_second": 34.591,
      "eval_steps_per_second": 4.33,
      "step": 1
    },
    {
      "epoch": 0.006247559547051933,
      "grad_norm": 195.81715393066406,
      "learning_rate": 0.0001,
      "loss": 1.9557,
      "step": 2
    },
    {
      "epoch": 0.009371339320577899,
      "grad_norm": 181.35487365722656,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.732,
      "step": 3
    },
    {
      "epoch": 0.012495119094103866,
      "grad_norm": 148.23948669433594,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.1532,
      "step": 4
    },
    {
      "epoch": 0.015618898867629832,
      "grad_norm": 95.68206787109375,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.5112,
      "step": 5
    },
    {
      "epoch": 0.018742678641155797,
      "grad_norm": 68.1971206665039,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.3027,
      "step": 6
    },
    {
      "epoch": 0.021866458414681766,
      "grad_norm": 88.98738098144531,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.1517,
      "step": 7
    },
    {
      "epoch": 0.024990238188207732,
      "grad_norm": 62.99566650390625,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.2107,
      "step": 8
    },
    {
      "epoch": 0.028114017961733698,
      "grad_norm": 49.76944351196289,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.0489,
      "step": 9
    },
    {
      "epoch": 0.031237797735259663,
      "grad_norm": 39.21405029296875,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.9703,
      "step": 10
    },
    {
      "epoch": 0.03436157750878563,
      "grad_norm": 34.17335891723633,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.0728,
      "step": 11
    },
    {
      "epoch": 0.037485357282311595,
      "grad_norm": 36.63615417480469,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.0314,
      "step": 12
    },
    {
      "epoch": 0.04060913705583756,
      "grad_norm": 36.554229736328125,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.8873,
      "step": 13
    },
    {
      "epoch": 0.04373291682936353,
      "grad_norm": 26.738367080688477,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.6655,
      "step": 14
    },
    {
      "epoch": 0.0468566966028895,
      "grad_norm": 24.847402572631836,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.6342,
      "step": 15
    },
    {
      "epoch": 0.049980476376415464,
      "grad_norm": 26.894756317138672,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.6856,
      "step": 16
    },
    {
      "epoch": 0.05310425614994143,
      "grad_norm": 26.362733840942383,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.7546,
      "step": 17
    },
    {
      "epoch": 0.056228035923467395,
      "grad_norm": 34.913875579833984,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.8084,
      "step": 18
    },
    {
      "epoch": 0.05935181569699336,
      "grad_norm": 30.74034881591797,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.8098,
      "step": 19
    },
    {
      "epoch": 0.06247559547051933,
      "grad_norm": 36.61556625366211,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.7698,
      "step": 20
    },
    {
      "epoch": 0.0655993752440453,
      "grad_norm": 29.092626571655273,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.7357,
      "step": 21
    },
    {
      "epoch": 0.06872315501757126,
      "grad_norm": 36.90818405151367,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.8158,
      "step": 22
    },
    {
      "epoch": 0.07184693479109723,
      "grad_norm": 32.904396057128906,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.7916,
      "step": 23
    },
    {
      "epoch": 0.07497071456462319,
      "grad_norm": 33.92314529418945,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.8483,
      "step": 24
    },
    {
      "epoch": 0.07809449433814916,
      "grad_norm": 31.703176498413086,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.7899,
      "step": 25
    },
    {
      "epoch": 0.07809449433814916,
      "eval_loss": 0.7294516563415527,
      "eval_runtime": 62.4375,
      "eval_samples_per_second": 34.547,
      "eval_steps_per_second": 4.324,
      "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": 2.829010669142016e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}