{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.897196261682243,
  "eval_steps": 500,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 1.5804122686386108,
      "learning_rate": 3.6846837792542446e-05,
      "loss": 1.354,
      "step": 5
    },
    {
      "epoch": 1.5981308411214954,
      "grad_norm": 0.7447302937507629,
      "learning_rate": 8.571795511298423e-06,
      "loss": 0.9135,
      "step": 10
    },
    {
      "epoch": 1.897196261682243,
      "step": 12,
      "total_flos": 5051946423549952.0,
      "train_loss": 1.0549687445163727,
      "train_runtime": 4794.3279,
      "train_samples_per_second": 0.355,
      "train_steps_per_second": 0.003
    }
  ],
  "logging_steps": 5,
  "max_steps": 12,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5051946423549952.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}