{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04423732773362493,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0044237327733624935,
      "grad_norm": 1.8688979148864746,
      "learning_rate": 4.3343653250774e-06,
      "loss": 11.7385,
      "step": 50
    },
    {
      "epoch": 0.008847465546724987,
      "grad_norm": 0.9319086074829102,
      "learning_rate": 8.757187085360461e-06,
      "loss": 10.6063,
      "step": 100
    },
    {
      "epoch": 0.013271198320087479,
      "grad_norm": 0.8681408762931824,
      "learning_rate": 1.3180008845643521e-05,
      "loss": 9.8187,
      "step": 150
    },
    {
      "epoch": 0.017694931093449974,
      "grad_norm": 0.925029456615448,
      "learning_rate": 1.7602830605926583e-05,
      "loss": 8.981,
      "step": 200
    },
    {
      "epoch": 0.022118663866812466,
      "grad_norm": 0.5568884611129761,
      "learning_rate": 2.2025652366209643e-05,
      "loss": 8.2909,
      "step": 250
    },
    {
      "epoch": 0.026542396640174958,
      "grad_norm": 0.8281100988388062,
      "learning_rate": 2.6448474126492707e-05,
      "loss": 7.8832,
      "step": 300
    },
    {
      "epoch": 0.030966129413537453,
      "grad_norm": 1.4202722311019897,
      "learning_rate": 3.0871295886775764e-05,
      "loss": 7.6402,
      "step": 350
    },
    {
      "epoch": 0.03538986218689995,
      "grad_norm": 1.0499255657196045,
      "learning_rate": 3.529411764705883e-05,
      "loss": 7.4567,
      "step": 400
    },
    {
      "epoch": 0.03981359496026244,
      "grad_norm": 1.734939694404602,
      "learning_rate": 3.9716939407341884e-05,
      "loss": 7.2858,
      "step": 450
    },
    {
      "epoch": 0.04423732773362493,
      "grad_norm": 1.6402956247329712,
      "learning_rate": 4.413976116762495e-05,
      "loss": 7.123,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 11303,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 8.9099499208704e+17,
  "train_batch_size": 20,
  "trial_name": null,
  "trial_params": null
}