{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "grad_norm": 0.06216534227132797,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.0637,
      "step": 10
    },
    {
      "grad_norm": 0.024572907015681267,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.0544,
      "step": 20
    },
    {
      "grad_norm": 0.08026651293039322,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.062,
      "step": 30
    },
    {
      "grad_norm": 0.0559636652469635,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.0507,
      "step": 40
    },
    {
      "grad_norm": 0.028828831389546394,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.0524,
      "step": 50
    },
    {
      "grad_norm": 0.028848476707935333,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.0528,
      "step": 60
    },
    {
      "grad_norm": 0.05331048369407654,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.0421,
      "step": 70
    },
    {
      "grad_norm": 0.06458555161952972,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.0586,
      "step": 80
    },
    {
      "grad_norm": 0.05882468819618225,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.0451,
      "step": 90
    },
    {
      "grad_norm": 0.04416602477431297,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.0563,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 100,
  "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": 8,
  "trial_name": null,
  "trial_params": null
}