{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.0005402083853846621,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.7010419269233105e-05,
      "grad_norm": NaN,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 2.7010419269233105e-05,
      "eval_loss": NaN,
      "eval_runtime": 788.5748,
      "eval_samples_per_second": 19.769,
      "eval_steps_per_second": 9.885,
      "step": 1
    },
    {
      "epoch": 5.402083853846621e-05,
      "grad_norm": NaN,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 8.103125780769932e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-06,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00010804167707693242,
      "grad_norm": NaN,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00013505209634616554,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00013505209634616554,
      "eval_loss": NaN,
      "eval_runtime": 991.3273,
      "eval_samples_per_second": 15.725,
      "eval_steps_per_second": 7.863,
      "step": 5
    },
    {
      "epoch": 0.00016206251561539864,
      "grad_norm": NaN,
      "learning_rate": 1.2e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00018907293488463174,
      "grad_norm": NaN,
      "learning_rate": 1.4e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00021608335415386484,
      "grad_norm": NaN,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.00024309377342309797,
      "grad_norm": NaN,
      "learning_rate": 1.8e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0002701041926923311,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0002701041926923311,
      "eval_loss": NaN,
      "eval_runtime": 995.7585,
      "eval_samples_per_second": 15.655,
      "eval_steps_per_second": 7.828,
      "step": 10
    },
    {
      "epoch": 0.0002971146119615642,
      "grad_norm": NaN,
      "learning_rate": 1.9781476007338058e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.0003241250312307973,
      "grad_norm": NaN,
      "learning_rate": 1.913545457642601e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0003511354505000304,
      "grad_norm": NaN,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.0003781458697692635,
      "grad_norm": NaN,
      "learning_rate": 1.6691306063588583e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.0004051562890384966,
      "grad_norm": NaN,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0004051562890384966,
      "eval_loss": NaN,
      "eval_runtime": 1031.2888,
      "eval_samples_per_second": 15.116,
      "eval_steps_per_second": 7.559,
      "step": 15
    },
    {
      "epoch": 0.0004321667083077297,
      "grad_norm": NaN,
      "learning_rate": 1.3090169943749475e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.00045917712757696284,
      "grad_norm": NaN,
      "learning_rate": 1.1045284632676535e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.00048618754684619594,
      "grad_norm": NaN,
      "learning_rate": 8.954715367323468e-06,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.000513197966115429,
      "grad_norm": NaN,
      "learning_rate": 6.909830056250527e-06,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.0005402083853846621,
      "grad_norm": NaN,
      "learning_rate": 5.000000000000003e-06,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0005402083853846621,
      "eval_loss": NaN,
      "eval_runtime": 2933.0218,
      "eval_samples_per_second": 5.315,
      "eval_steps_per_second": 2.658,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1241819979448320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}