{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 980,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.6601235683238695,
      "las": 84.1703447453179,
      "step": 196,
      "uas": 87.77684997415403
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6943420922708889,
      "las": 85.18430156268639,
      "step": 392,
      "uas": 88.57608652431507
    },
    {
      "epoch": 2.5510204081632653,
      "grad_norm": 10.005887031555176,
      "learning_rate": 9.79591836734694e-05,
      "loss": 0.8481,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.542496694828428,
      "las": 88.15459859238935,
      "step": 588,
      "uas": 91.02151178973318
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.5330029517589581,
      "las": 88.73513857409837,
      "step": 784,
      "uas": 91.52650204779515
    }
  ],
  "logging_steps": 500,
  "max_steps": 980,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 1.078180051156992e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}