{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0085381863368976e-05,
  "eval_steps": 3,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.3361793954456326e-05,
      "grad_norm": 12.711153984069824,
      "learning_rate": 2e-05,
      "loss": 2.1096,
      "step": 1
    },
    {
      "epoch": 1.3361793954456326e-05,
      "eval_loss": 2.254793405532837,
      "eval_runtime": 551.6423,
      "eval_samples_per_second": 57.124,
      "eval_steps_per_second": 28.562,
      "step": 1
    },
    {
      "epoch": 2.6723587908912652e-05,
      "grad_norm": 15.669854164123535,
      "learning_rate": 4e-05,
      "loss": 1.9175,
      "step": 2
    },
    {
      "epoch": 4.0085381863368976e-05,
      "grad_norm": 13.797361373901367,
      "learning_rate": 6e-05,
      "loss": 2.0773,
      "step": 3
    },
    {
      "epoch": 4.0085381863368976e-05,
      "eval_loss": 2.1823835372924805,
      "eval_runtime": 549.2666,
      "eval_samples_per_second": 57.371,
      "eval_steps_per_second": 28.686,
      "step": 3
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 76737593475072.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}