{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 200,
  "global_step": 154,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16233766233766234,
      "grad_norm": 0.5663641691207886,
      "learning_rate": 0.0001920824925271838,
      "loss": 1.4646,
      "step": 25
    },
    {
      "epoch": 0.3246753246753247,
      "grad_norm": 0.37827152013778687,
      "learning_rate": 0.00015996612118590603,
      "loss": 0.9487,
      "step": 50
    },
    {
      "epoch": 0.487012987012987,
      "grad_norm": 1.0965982675552368,
      "learning_rate": 0.00011157050914243614,
      "loss": 0.8229,
      "step": 75
    },
    {
      "epoch": 0.6493506493506493,
      "grad_norm": 0.6679003834724426,
      "learning_rate": 6.0033805101491794e-05,
      "loss": 0.7703,
      "step": 100
    },
    {
      "epoch": 0.8116883116883117,
      "grad_norm": 0.7074993848800659,
      "learning_rate": 1.9346882467727325e-05,
      "loss": 0.6914,
      "step": 125
    },
    {
      "epoch": 0.974025974025974,
      "grad_norm": 0.7936781048774719,
      "learning_rate": 5.55181464516652e-07,
      "loss": 0.7349,
      "step": 150
    }
  ],
  "logging_steps": 25,
  "max_steps": 154,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.966167304092877e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}