{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 405,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 1.568103313446045,
      "learning_rate": 3.777777777777778e-05,
      "loss": 2.621,
      "step": 100
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 0.561548113822937,
      "learning_rate": 2.5432098765432098e-05,
      "loss": 0.2837,
      "step": 200
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.3680315911769867,
      "learning_rate": 1.308641975308642e-05,
      "loss": 0.0772,
      "step": 300
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.5895044207572937,
      "learning_rate": 7.407407407407408e-07,
      "loss": 0.0565,
      "step": 400
    }
  ],
  "logging_steps": 100,
  "max_steps": 405,
  "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": 109626859192320.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}