{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 3.7809744348607595,
      "learning_rate": 3.9702372106487333e-05,
      "loss": 0.4575,
      "step": 100
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.496724878092226,
      "learning_rate": 3.8072567212170113e-05,
      "loss": 0.3252,
      "step": 200
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.3560218616246147,
      "learning_rate": 3.513425631635391e-05,
      "loss": 0.2945,
      "step": 300
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.5682843699995858,
      "learning_rate": 3.11001816042694e-05,
      "loss": 0.2756,
      "step": 400
    }
  ],
  "logging_steps": 100,
  "max_steps": 1200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 12,
  "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": 0.0,
  "train_batch_size": 26,
  "trial_name": null,
  "trial_params": null
}