{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "grad_norm": 0.38351285457611084,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.2186,
      "step": 10
    },
    {
      "grad_norm": 0.453412801027298,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.176,
      "step": 20
    },
    {
      "grad_norm": 0.3962445557117462,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.1279,
      "step": 30
    },
    {
      "grad_norm": 0.33287128806114197,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.0833,
      "step": 40
    },
    {
      "grad_norm": 0.34996676445007324,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.0655,
      "step": 50
    },
    {
      "grad_norm": 0.33573195338249207,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.0523,
      "step": 60
    },
    {
      "grad_norm": 0.36666247248649597,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.0321,
      "step": 70
    },
    {
      "grad_norm": 0.39881908893585205,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.0118,
      "step": 80
    },
    {
      "grad_norm": 0.40295055508613586,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.0024,
      "step": 90
    },
    {
      "grad_norm": 0.4325471818447113,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.0113,
      "step": 100
    },
    {
      "grad_norm": 0.39502644538879395,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.0233,
      "step": 110
    },
    {
      "grad_norm": 0.9289461970329285,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.9895,
      "step": 120
    },
    {
      "grad_norm": 0.8774065375328064,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.9202,
      "step": 130
    },
    {
      "grad_norm": 1.0103175640106201,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.8666,
      "step": 140
    },
    {
      "grad_norm": 1.0156214237213135,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.7999,
      "step": 150
    },
    {
      "grad_norm": 0.923975944519043,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.7333,
      "step": 160
    },
    {
      "grad_norm": 1.110439658164978,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.6969,
      "step": 170
    },
    {
      "grad_norm": 0.8177175521850586,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.6798,
      "step": 180
    },
    {
      "grad_norm": 0.762315571308136,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.6679,
      "step": 190
    },
    {
      "grad_norm": 0.8166346549987793,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.6646,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": null
}