{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1566,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9578544061302682,
      "grad_norm": 0.41256571593460695,
      "learning_rate": 9.746738799459564e-06,
      "loss": 0.1281,
      "step": 500
    },
    {
      "epoch": 1.9157088122605364,
      "grad_norm": 0.4425150351660631,
      "learning_rate": 7.750337764947452e-06,
      "loss": 0.0865,
      "step": 1000
    },
    {
      "epoch": 2.873563218390805,
      "grad_norm": 0.36155039991831844,
      "learning_rate": 4.569217733808774e-06,
      "loss": 0.0702,
      "step": 1500
    }
  ],
  "logging_steps": 500,
  "max_steps": 2610,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": -2610,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 78973184901120.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}