{
  "best_metric": 0.07815606147050858,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.3472222222222222,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013888888888888888,
      "grad_norm": 14.678104400634766,
      "learning_rate": 2e-05,
      "loss": 1.6601,
      "step": 1
    },
    {
      "epoch": 0.013888888888888888,
      "eval_loss": 1.8588101863861084,
      "eval_runtime": 2.2491,
      "eval_samples_per_second": 53.798,
      "eval_steps_per_second": 7.114,
      "step": 1
    },
    {
      "epoch": 0.027777777777777776,
      "grad_norm": 11.50792121887207,
      "learning_rate": 4e-05,
      "loss": 1.3641,
      "step": 2
    },
    {
      "epoch": 0.041666666666666664,
      "grad_norm": 10.706708908081055,
      "learning_rate": 6e-05,
      "loss": 1.1007,
      "step": 3
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 6.061966896057129,
      "learning_rate": 8e-05,
      "loss": 0.7176,
      "step": 4
    },
    {
      "epoch": 0.06944444444444445,
      "grad_norm": 4.465976715087891,
      "learning_rate": 0.0001,
      "loss": 0.4978,
      "step": 5
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 4.962102890014648,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.2926,
      "step": 6
    },
    {
      "epoch": 0.09722222222222222,
      "grad_norm": 2.4147729873657227,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.1882,
      "step": 7
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 1.8495898246765137,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.0569,
      "step": 8
    },
    {
      "epoch": 0.125,
      "grad_norm": 1.4623396396636963,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.068,
      "step": 9
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 1.641226053237915,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0416,
      "step": 10
    },
    {
      "epoch": 0.1527777777777778,
      "grad_norm": 1.797526240348816,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0415,
      "step": 11
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 1.114608883857727,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0226,
      "step": 12
    },
    {
      "epoch": 0.18055555555555555,
      "grad_norm": 0.24899643659591675,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.0028,
      "step": 13
    },
    {
      "epoch": 0.19444444444444445,
      "grad_norm": 1.512805461883545,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0317,
      "step": 14
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 3.5684399604797363,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0349,
      "step": 15
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 5.321943283081055,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.0123,
      "step": 16
    },
    {
      "epoch": 0.2361111111111111,
      "grad_norm": 7.596778392791748,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.032,
      "step": 17
    },
    {
      "epoch": 0.25,
      "grad_norm": 6.081374645233154,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.5406,
      "step": 18
    },
    {
      "epoch": 0.2638888888888889,
      "grad_norm": 2.198094129562378,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.0196,
      "step": 19
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 0.18695461750030518,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0018,
      "step": 20
    },
    {
      "epoch": 0.2916666666666667,
      "grad_norm": 4.97247314453125,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0449,
      "step": 21
    },
    {
      "epoch": 0.3055555555555556,
      "grad_norm": 2.904404640197754,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.105,
      "step": 22
    },
    {
      "epoch": 0.3194444444444444,
      "grad_norm": 2.324169397354126,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0151,
      "step": 23
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.05707435682415962,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0008,
      "step": 24
    },
    {
      "epoch": 0.3472222222222222,
      "grad_norm": 0.8039947748184204,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0061,
      "step": 25
    },
    {
      "epoch": 0.3472222222222222,
      "eval_loss": 0.07815606147050858,
      "eval_runtime": 2.2734,
      "eval_samples_per_second": 53.224,
      "eval_steps_per_second": 7.038,
      "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": 5,
        "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": 5164738874966016.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}