{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.05411210283637047,
      "eval_runtime": 9.4136,
      "eval_samples_per_second": 17.209,
      "eval_steps_per_second": 1.169,
      "step": 6
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 9.417199765317891,
      "learning_rate": 5e-06,
      "loss": 0.9325,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.0529806949198246,
      "eval_runtime": 9.0112,
      "eval_samples_per_second": 17.978,
      "eval_steps_per_second": 1.221,
      "step": 12
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.05126175656914711,
      "eval_runtime": 8.5514,
      "eval_samples_per_second": 18.944,
      "eval_steps_per_second": 1.286,
      "step": 18
    },
    {
      "epoch": 3.0,
      "step": 18,
      "total_flos": 5.580414715219149e+16,
      "train_loss": 0.8848204612731934,
      "train_runtime": 1687.8657,
      "train_samples_per_second": 5.457,
      "train_steps_per_second": 0.011
    }
  ],
  "logging_steps": 10,
  "max_steps": 18,
  "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": 5.580414715219149e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}