{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0034680677660441487,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00034680677660441485,
      "grad_norm": 8.286304473876953,
      "learning_rate": 2.6999999999999996e-06,
      "loss": 36.023321533203124,
      "step": 10
    },
    {
      "epoch": 0.0006936135532088297,
      "grad_norm": 5.303624153137207,
      "learning_rate": 5.7e-06,
      "loss": 35.81325988769531,
      "step": 20
    },
    {
      "epoch": 0.0010404203298132447,
      "grad_norm": 14.0803861618042,
      "learning_rate": 8.7e-06,
      "loss": 35.61415100097656,
      "step": 30
    },
    {
      "epoch": 0.0013872271064176594,
      "grad_norm": 42.10546875,
      "learning_rate": 1.17e-05,
      "loss": 35.36910400390625,
      "step": 40
    },
    {
      "epoch": 0.0017340338830220744,
      "grad_norm": 43.37276840209961,
      "learning_rate": 1.47e-05,
      "loss": 34.86077880859375,
      "step": 50
    },
    {
      "epoch": 0.0020808406596264893,
      "grad_norm": Infinity,
      "learning_rate": 1.7699999999999997e-05,
      "loss": 34.67452697753906,
      "step": 60
    },
    {
      "epoch": 0.002427647436230904,
      "grad_norm": 86.09446716308594,
      "learning_rate": 2.04e-05,
      "loss": 34.29078979492188,
      "step": 70
    },
    {
      "epoch": 0.002774454212835319,
      "grad_norm": 43.50123977661133,
      "learning_rate": 2.34e-05,
      "loss": 33.816766357421876,
      "step": 80
    },
    {
      "epoch": 0.0031212609894397335,
      "grad_norm": 104.7258529663086,
      "learning_rate": 2.6399999999999995e-05,
      "loss": 33.36159057617188,
      "step": 90
    },
    {
      "epoch": 0.0034680677660441487,
      "grad_norm": 66.46515655517578,
      "learning_rate": 2.91e-05,
      "loss": 33.181732177734375,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 100000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 621991349452800.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}