{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 100.0,
  "eval_steps": 500,
  "global_step": 7000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.142857142857143,
      "grad_norm": 0.5076488852500916,
      "learning_rate": 4.642857142857143e-05,
      "loss": 2.7976,
      "step": 500
    },
    {
      "epoch": 14.285714285714286,
      "grad_norm": 0.7804142832756042,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 2.4425,
      "step": 1000
    },
    {
      "epoch": 21.428571428571427,
      "grad_norm": 0.4202755391597748,
      "learning_rate": 3.928571428571429e-05,
      "loss": 2.3161,
      "step": 1500
    },
    {
      "epoch": 28.571428571428573,
      "grad_norm": 0.5510886907577515,
      "learning_rate": 3.571428571428572e-05,
      "loss": 2.2387,
      "step": 2000
    },
    {
      "epoch": 35.714285714285715,
      "grad_norm": 0.5870991945266724,
      "learning_rate": 3.2142857142857144e-05,
      "loss": 2.1813,
      "step": 2500
    },
    {
      "epoch": 42.857142857142854,
      "grad_norm": 0.4125164747238159,
      "learning_rate": 2.857142857142857e-05,
      "loss": 2.1352,
      "step": 3000
    },
    {
      "epoch": 50.0,
      "grad_norm": 0.5036264061927795,
      "learning_rate": 2.5e-05,
      "loss": 2.101,
      "step": 3500
    },
    {
      "epoch": 57.142857142857146,
      "grad_norm": 0.5034046173095703,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 2.0721,
      "step": 4000
    },
    {
      "epoch": 64.28571428571429,
      "grad_norm": 0.437740296125412,
      "learning_rate": 1.785714285714286e-05,
      "loss": 2.0506,
      "step": 4500
    },
    {
      "epoch": 71.42857142857143,
      "grad_norm": 0.7597389221191406,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 2.0301,
      "step": 5000
    },
    {
      "epoch": 78.57142857142857,
      "grad_norm": 0.5058132410049438,
      "learning_rate": 1.0714285714285714e-05,
      "loss": 2.0155,
      "step": 5500
    },
    {
      "epoch": 85.71428571428571,
      "grad_norm": 0.5107972025871277,
      "learning_rate": 7.142857142857143e-06,
      "loss": 2.0066,
      "step": 6000
    },
    {
      "epoch": 92.85714285714286,
      "grad_norm": 0.5089341998100281,
      "learning_rate": 3.5714285714285714e-06,
      "loss": 1.9992,
      "step": 6500
    },
    {
      "epoch": 100.0,
      "grad_norm": 0.5024028420448303,
      "learning_rate": 0.0,
      "loss": 1.9957,
      "step": 7000
    }
  ],
  "logging_steps": 500,
  "max_steps": 7000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "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": 5.883762387916554e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}