{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.6,
  "eval_steps": 500,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 1.4149662256240845,
      "learning_rate": 1e-05,
      "loss": 18.2498,
      "step": 50
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.4043880701065063,
      "learning_rate": 1e-05,
      "loss": 18.0021,
      "step": 100
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.4164069890975952,
      "learning_rate": 1e-05,
      "loss": 17.9685,
      "step": 150
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.4041774272918701,
      "learning_rate": 1e-05,
      "loss": 18.0499,
      "step": 200
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.4155642986297607,
      "learning_rate": 1e-05,
      "loss": 17.9921,
      "step": 250
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.4139286279678345,
      "learning_rate": 1e-05,
      "loss": 18.1205,
      "step": 300
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.4146976470947266,
      "learning_rate": 1e-05,
      "loss": 17.9707,
      "step": 350
    },
    {
      "epoch": 3.2,
      "grad_norm": 1.4064240455627441,
      "learning_rate": 1e-05,
      "loss": 17.7803,
      "step": 400
    },
    {
      "epoch": 3.6,
      "grad_norm": 1.4109365940093994,
      "learning_rate": 1e-05,
      "loss": 17.942,
      "step": 450
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.4187476634979248,
      "learning_rate": 1e-05,
      "loss": 18.2641,
      "step": 500
    },
    {
      "epoch": 4.4,
      "grad_norm": 1.4360158443450928,
      "learning_rate": 1e-05,
      "loss": 18.1461,
      "step": 550
    },
    {
      "epoch": 4.8,
      "grad_norm": 1.4155607223510742,
      "learning_rate": 1e-05,
      "loss": 17.9742,
      "step": 600
    },
    {
      "epoch": 5.2,
      "grad_norm": 1.4008636474609375,
      "learning_rate": 1e-05,
      "loss": 18.1381,
      "step": 650
    },
    {
      "epoch": 5.6,
      "grad_norm": 1.2298083305358887,
      "learning_rate": 1e-05,
      "loss": 18.0335,
      "step": 700
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.2354425191879272,
      "learning_rate": 1e-05,
      "loss": 18.43,
      "step": 750
    },
    {
      "epoch": 6.4,
      "grad_norm": 0.9361160397529602,
      "learning_rate": 1e-05,
      "loss": 18.6396,
      "step": 800
    },
    {
      "epoch": 6.8,
      "grad_norm": 0.8434619307518005,
      "learning_rate": 1e-05,
      "loss": 18.4734,
      "step": 850
    },
    {
      "epoch": 7.2,
      "grad_norm": 1.1784098148345947,
      "learning_rate": 1e-05,
      "loss": 18.7698,
      "step": 900
    },
    {
      "epoch": 7.6,
      "grad_norm": 0.8885198831558228,
      "learning_rate": 1e-05,
      "loss": 18.7858,
      "step": 950
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.7891300916671753,
      "learning_rate": 1e-05,
      "loss": 19.0307,
      "step": 1000
    },
    {
      "epoch": 8.4,
      "grad_norm": 0.6751607656478882,
      "learning_rate": 1e-05,
      "loss": 19.2952,
      "step": 1050
    },
    {
      "epoch": 8.8,
      "grad_norm": 1.021397590637207,
      "learning_rate": 1e-05,
      "loss": 19.2364,
      "step": 1100
    },
    {
      "epoch": 9.2,
      "grad_norm": 0.6844053268432617,
      "learning_rate": 1e-05,
      "loss": 19.7009,
      "step": 1150
    },
    {
      "epoch": 9.6,
      "grad_norm": 0.801950991153717,
      "learning_rate": 1e-05,
      "loss": 19.7684,
      "step": 1200
    }
  ],
  "logging_steps": 50,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 40,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}