{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0017359498727114757,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00034718997454229514,
      "grad_norm": 0.8856930732727051,
      "learning_rate": 0.00019999994169931,
      "loss": 2.4069,
      "step": 100
    },
    {
      "epoch": 0.0006943799490845903,
      "grad_norm": 0.8890424966812134,
      "learning_rate": 0.0001999997644357777,
      "loss": 2.3882,
      "step": 200
    },
    {
      "epoch": 0.0010415699236268853,
      "grad_norm": 0.8619076013565063,
      "learning_rate": 0.00019999946820366553,
      "loss": 2.4208,
      "step": 300
    },
    {
      "epoch": 0.0013887598981691806,
      "grad_norm": 0.8981874585151672,
      "learning_rate": 0.00019999905300332595,
      "loss": 2.3859,
      "step": 400
    },
    {
      "epoch": 0.0017359498727114757,
      "grad_norm": 1.1088451147079468,
      "learning_rate": 0.0001999985188352529,
      "loss": 2.4031,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 288027,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3740660968730624e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}