{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 25.306283950805664,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 9.5671,
      "step": 10
    },
    {
      "epoch": 0.4,
      "grad_norm": 20.41864013671875,
      "learning_rate": 8.000000000000001e-07,
      "loss": 9.1661,
      "step": 20
    },
    {
      "epoch": 0.6,
      "grad_norm": 16.571876525878906,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 8.5779,
      "step": 30
    },
    {
      "epoch": 0.8,
      "grad_norm": 11.903717041015625,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 8.6565,
      "step": 40
    },
    {
      "epoch": 1.0,
      "grad_norm": 11.543700218200684,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 7.799,
      "step": 50
    },
    {
      "epoch": 1.2,
      "grad_norm": 9.900014877319336,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 7.1091,
      "step": 60
    },
    {
      "epoch": 1.4,
      "grad_norm": 9.66036605834961,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 6.9738,
      "step": 70
    },
    {
      "epoch": 1.6,
      "grad_norm": 10.709378242492676,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 6.6687,
      "step": 80
    },
    {
      "epoch": 1.8,
      "grad_norm": 12.942888259887695,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 6.7592,
      "step": 90
    },
    {
      "epoch": 2.0,
      "grad_norm": 13.488504409790039,
      "learning_rate": 4.000000000000001e-06,
      "loss": 6.3509,
      "step": 100
    },
    {
      "epoch": 2.2,
      "grad_norm": 16.680503845214844,
      "learning_rate": 4.4e-06,
      "loss": 5.9777,
      "step": 110
    },
    {
      "epoch": 2.4,
      "grad_norm": 23.38302993774414,
      "learning_rate": 4.800000000000001e-06,
      "loss": 5.6314,
      "step": 120
    },
    {
      "epoch": 2.6,
      "grad_norm": 23.684436798095703,
      "learning_rate": 5.2e-06,
      "loss": 5.0907,
      "step": 130
    },
    {
      "epoch": 2.8,
      "grad_norm": 21.124048233032227,
      "learning_rate": 5.600000000000001e-06,
      "loss": 4.4654,
      "step": 140
    },
    {
      "epoch": 3.0,
      "grad_norm": 19.794771194458008,
      "learning_rate": 6e-06,
      "loss": 4.3731,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 150,
  "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": 319986538905600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}