{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 3597,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4170141784820684,
      "grad_norm": 3.641329050064087,
      "learning_rate": 4.307756463719766e-05,
      "loss": 1.5757,
      "step": 500
    },
    {
      "epoch": 0.8340283569641368,
      "grad_norm": 3.4498984813690186,
      "learning_rate": 3.6127328329163196e-05,
      "loss": 0.9216,
      "step": 1000
    },
    {
      "epoch": 1.2510425354462051,
      "grad_norm": 2.5553345680236816,
      "learning_rate": 2.9177092021128722e-05,
      "loss": 0.714,
      "step": 1500
    },
    {
      "epoch": 1.6680567139282736,
      "grad_norm": 2.445970296859741,
      "learning_rate": 2.2226855713094245e-05,
      "loss": 0.6235,
      "step": 2000
    },
    {
      "epoch": 2.085070892410342,
      "grad_norm": 2.6258559226989746,
      "learning_rate": 1.5276619405059772e-05,
      "loss": 0.5609,
      "step": 2500
    },
    {
      "epoch": 2.5020850708924103,
      "grad_norm": 2.441476583480835,
      "learning_rate": 8.326383097025299e-06,
      "loss": 0.4957,
      "step": 3000
    },
    {
      "epoch": 2.9190992493744785,
      "grad_norm": 1.937845230102539,
      "learning_rate": 1.3761467889908258e-06,
      "loss": 0.478,
      "step": 3500
    }
  ],
  "logging_steps": 500,
  "max_steps": 3597,
  "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": 1949901747388416.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}