{
  "best_metric": 4.218059539794922,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 1.4351687388987566,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.056838365896980464,
      "grad_norm": 2.2364661693573,
      "learning_rate": 5e-05,
      "loss": 4.171,
      "step": 1
    },
    {
      "epoch": 0.056838365896980464,
      "eval_loss": 5.347789287567139,
      "eval_runtime": 0.6382,
      "eval_samples_per_second": 78.342,
      "eval_steps_per_second": 20.369,
      "step": 1
    },
    {
      "epoch": 0.11367673179396093,
      "grad_norm": 1.7895739078521729,
      "learning_rate": 0.0001,
      "loss": 4.8151,
      "step": 2
    },
    {
      "epoch": 0.1705150976909414,
      "grad_norm": 2.7331533432006836,
      "learning_rate": 9.990365154573717e-05,
      "loss": 5.1544,
      "step": 3
    },
    {
      "epoch": 0.22735346358792186,
      "grad_norm": 1.7573771476745605,
      "learning_rate": 9.961501876182148e-05,
      "loss": 5.347,
      "step": 4
    },
    {
      "epoch": 0.2841918294849023,
      "grad_norm": 1.0575058460235596,
      "learning_rate": 9.913533761814537e-05,
      "loss": 4.1473,
      "step": 5
    },
    {
      "epoch": 0.3410301953818828,
      "grad_norm": 0.7738857269287109,
      "learning_rate": 9.846666218300807e-05,
      "loss": 4.4641,
      "step": 6
    },
    {
      "epoch": 0.3978685612788632,
      "grad_norm": 2.7124485969543457,
      "learning_rate": 9.761185582727977e-05,
      "loss": 4.7569,
      "step": 7
    },
    {
      "epoch": 0.4547069271758437,
      "grad_norm": 1.5827847719192505,
      "learning_rate": 9.657457896300791e-05,
      "loss": 5.0478,
      "step": 8
    },
    {
      "epoch": 0.5115452930728241,
      "grad_norm": 0.872265636920929,
      "learning_rate": 9.535927336897098e-05,
      "loss": 3.977,
      "step": 9
    },
    {
      "epoch": 0.5683836589698046,
      "grad_norm": 0.7036884427070618,
      "learning_rate": 9.397114317029975e-05,
      "loss": 4.2225,
      "step": 10
    },
    {
      "epoch": 0.6252220248667851,
      "grad_norm": 0.9477807879447937,
      "learning_rate": 9.241613255361455e-05,
      "loss": 4.5216,
      "step": 11
    },
    {
      "epoch": 0.6820603907637656,
      "grad_norm": 1.073500156402588,
      "learning_rate": 9.070090031310558e-05,
      "loss": 4.6968,
      "step": 12
    },
    {
      "epoch": 0.738898756660746,
      "grad_norm": 0.6695452332496643,
      "learning_rate": 8.883279133655399e-05,
      "loss": 3.9704,
      "step": 13
    },
    {
      "epoch": 0.7957371225577264,
      "grad_norm": 0.652845025062561,
      "learning_rate": 8.681980515339464e-05,
      "loss": 4.1003,
      "step": 14
    },
    {
      "epoch": 0.8525754884547069,
      "grad_norm": 0.7173386812210083,
      "learning_rate": 8.467056167950311e-05,
      "loss": 4.2267,
      "step": 15
    },
    {
      "epoch": 0.9094138543516874,
      "grad_norm": 0.9569276571273804,
      "learning_rate": 8.239426430539243e-05,
      "loss": 4.4941,
      "step": 16
    },
    {
      "epoch": 0.9662522202486679,
      "grad_norm": 1.4495911598205566,
      "learning_rate": 8.000066048588211e-05,
      "loss": 4.9847,
      "step": 17
    },
    {
      "epoch": 1.0373001776198933,
      "grad_norm": 1.1459908485412598,
      "learning_rate": 7.75e-05,
      "loss": 6.802,
      "step": 18
    },
    {
      "epoch": 1.0941385435168738,
      "grad_norm": 1.0883979797363281,
      "learning_rate": 7.490299105985507e-05,
      "loss": 3.8296,
      "step": 19
    },
    {
      "epoch": 1.1509769094138544,
      "grad_norm": 0.8071144223213196,
      "learning_rate": 7.222075445642904e-05,
      "loss": 4.2843,
      "step": 20
    },
    {
      "epoch": 1.2078152753108349,
      "grad_norm": 1.0637041330337524,
      "learning_rate": 6.946477593864228e-05,
      "loss": 4.4735,
      "step": 21
    },
    {
      "epoch": 1.2646536412078153,
      "grad_norm": 1.1672452688217163,
      "learning_rate": 6.664685702961344e-05,
      "loss": 3.841,
      "step": 22
    },
    {
      "epoch": 1.3214920071047958,
      "grad_norm": 0.76850825548172,
      "learning_rate": 6.377906449072578e-05,
      "loss": 3.951,
      "step": 23
    },
    {
      "epoch": 1.3783303730017762,
      "grad_norm": 0.9217700362205505,
      "learning_rate": 6.087367864990233e-05,
      "loss": 4.1167,
      "step": 24
    },
    {
      "epoch": 1.4351687388987566,
      "grad_norm": 0.8780374526977539,
      "learning_rate": 5.794314081535644e-05,
      "loss": 4.2914,
      "step": 25
    },
    {
      "epoch": 1.4351687388987566,
      "eval_loss": 4.218059539794922,
      "eval_runtime": 0.6531,
      "eval_samples_per_second": 76.553,
      "eval_steps_per_second": 19.904,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 5686862177894400.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}