{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 316,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.31645569620253167,
      "grad_norm": 2.203125,
      "learning_rate": 4.700704225352113e-05,
      "loss": 1.2268,
      "step": 50
    },
    {
      "epoch": 0.6329113924050633,
      "grad_norm": 2.359375,
      "learning_rate": 3.820422535211268e-05,
      "loss": 0.7848,
      "step": 100
    },
    {
      "epoch": 0.9493670886075949,
      "grad_norm": 2.5,
      "learning_rate": 2.9401408450704227e-05,
      "loss": 0.7202,
      "step": 150
    },
    {
      "epoch": 1.2658227848101267,
      "grad_norm": 2.3125,
      "learning_rate": 2.0598591549295776e-05,
      "loss": 0.6965,
      "step": 200
    },
    {
      "epoch": 1.5822784810126582,
      "grad_norm": 2.390625,
      "learning_rate": 1.1795774647887324e-05,
      "loss": 0.6903,
      "step": 250
    },
    {
      "epoch": 1.8987341772151898,
      "grad_norm": 2.296875,
      "learning_rate": 2.9929577464788733e-06,
      "loss": 0.6684,
      "step": 300
    }
  ],
  "logging_steps": 50,
  "max_steps": 316,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 0.0,
  "train_batch_size": 512,
  "trial_name": null,
  "trial_params": null
}