{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9995129079396006,
  "eval_steps": 500,
  "global_step": 3078,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4870920603994155,
      "grad_norm": 0.14726775884628296,
      "learning_rate": 0.00019316938294480988,
      "loss": 1.958,
      "step": 500
    },
    {
      "epoch": 0.974184120798831,
      "grad_norm": 0.14507216215133667,
      "learning_rate": 0.00016145696457272202,
      "loss": 1.7738,
      "step": 1000
    },
    {
      "epoch": 1.4617632732586459,
      "grad_norm": 0.17004884779453278,
      "learning_rate": 0.00011243098608364038,
      "loss": 1.6493,
      "step": 1500
    },
    {
      "epoch": 1.9488553336580614,
      "grad_norm": 0.19309113919734955,
      "learning_rate": 5.990296960148566e-05,
      "loss": 1.6013,
      "step": 2000
    },
    {
      "epoch": 2.4364344861178764,
      "grad_norm": 0.21260130405426025,
      "learning_rate": 1.8671025926443465e-05,
      "loss": 1.4963,
      "step": 2500
    },
    {
      "epoch": 2.9235265465172917,
      "grad_norm": 0.20603960752487183,
      "learning_rate": 3.509538621403463e-07,
      "loss": 1.4776,
      "step": 3000
    }
  ],
  "logging_steps": 500,
  "max_steps": 3078,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.8237978362196787e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}