{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.022983222247759137,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007661074082586378,
      "grad_norm": 65.09761810302734,
      "learning_rate": 3.676752202221372e-07,
      "loss": 4.3011,
      "step": 100
    },
    {
      "epoch": 0.015322148165172756,
      "grad_norm": 23.898212432861328,
      "learning_rate": 7.506702412868633e-07,
      "loss": 2.9855,
      "step": 200
    },
    {
      "epoch": 0.022983222247759137,
      "grad_norm": 36.721336364746094,
      "learning_rate": 1.1336652623515894e-06,
      "loss": 2.4857,
      "step": 300
    }
  ],
  "logging_steps": 100,
  "max_steps": 26106,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "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": 1,
  "trial_name": null,
  "trial_params": null
}