{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.786046511627907,
  "eval_steps": 500,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14883720930232558,
      "grad_norm": 27.89928648381498,
      "learning_rate": 4.914814565722671e-06,
      "loss": 1.3597,
      "step": 1
    },
    {
      "epoch": 0.7441860465116279,
      "grad_norm": 2.7281963910921863,
      "learning_rate": 3.147047612756302e-06,
      "loss": 0.4932,
      "step": 5
    },
    {
      "epoch": 1.4883720930232558,
      "grad_norm": 1.0961850685485253,
      "learning_rate": 3.3493649053890325e-07,
      "loss": 0.2433,
      "step": 10
    },
    {
      "epoch": 1.786046511627907,
      "step": 12,
      "total_flos": 6195248955392.0,
      "train_loss": 0.41408979147672653,
      "train_runtime": 629.8555,
      "train_samples_per_second": 2.731,
      "train_steps_per_second": 0.019
    }
  ],
  "logging_steps": 5,
  "max_steps": 12,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6195248955392.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}