{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9979550102249489,
  "eval_steps": 500,
  "global_step": 122,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16359918200409,
      "grad_norm": 66.81550598144531,
      "learning_rate": 1e-05,
      "loss": 0.5875,
      "step": 20
    },
    {
      "epoch": 0.32719836400818,
      "grad_norm": 26.688508987426758,
      "learning_rate": 2e-05,
      "loss": 0.3931,
      "step": 40
    },
    {
      "epoch": 0.49079754601226994,
      "grad_norm": 9.091463088989258,
      "learning_rate": 3e-05,
      "loss": 0.4112,
      "step": 60
    },
    {
      "epoch": 0.65439672801636,
      "grad_norm": 678.1345825195312,
      "learning_rate": 4e-05,
      "loss": 0.3715,
      "step": 80
    },
    {
      "epoch": 0.8179959100204499,
      "grad_norm": 85.55047607421875,
      "learning_rate": 5e-05,
      "loss": 0.2942,
      "step": 100
    },
    {
      "epoch": 0.9815950920245399,
      "grad_norm": 28.16888999938965,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.3863,
      "step": 120
    }
  ],
  "logging_steps": 20,
  "max_steps": 122,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}