{
  "best_metric": 0.987703144062033,
  "best_model_checkpoint": "./model/checkpoint-2224",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 2224,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8992805755395683,
      "grad_norm": 15.831398963928223,
      "learning_rate": 2.731834532374101e-05,
      "loss": 0.1341,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9858275687531635,
      "eval_f1": 0.9858428119593087,
      "eval_loss": 0.06046506017446518,
      "eval_precision": 0.9858980040864742,
      "eval_recall": 0.9858275687531635,
      "eval_runtime": 123.5336,
      "eval_samples_per_second": 47.979,
      "eval_steps_per_second": 1.506,
      "step": 556
    },
    {
      "epoch": 1.7985611510791366,
      "grad_norm": 0.1419404149055481,
      "learning_rate": 2.4620503597122304e-05,
      "loss": 0.0458,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9844778133963219,
      "eval_f1": 0.9844685311325714,
      "eval_loss": 0.06095171347260475,
      "eval_precision": 0.984470890080927,
      "eval_recall": 0.9844778133963219,
      "eval_runtime": 324.024,
      "eval_samples_per_second": 18.292,
      "eval_steps_per_second": 0.574,
      "step": 1112
    },
    {
      "epoch": 2.697841726618705,
      "grad_norm": 0.0644543468952179,
      "learning_rate": 2.1928057553956834e-05,
      "loss": 0.0255,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9856588493335583,
      "eval_f1": 0.9856725274058569,
      "eval_loss": 0.06607956439256668,
      "eval_precision": 0.985717476255087,
      "eval_recall": 0.9856588493335583,
      "eval_runtime": 23.8528,
      "eval_samples_per_second": 248.482,
      "eval_steps_per_second": 7.798,
      "step": 1668
    },
    {
      "epoch": 3.597122302158273,
      "grad_norm": 0.006873908918350935,
      "learning_rate": 1.923021582733813e-05,
      "loss": 0.0098,
      "step": 2000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9876834823688206,
      "eval_f1": 0.987703144062033,
      "eval_loss": 0.06861425936222076,
      "eval_precision": 0.9878126950690342,
      "eval_recall": 0.9876834823688206,
      "eval_runtime": 123.3642,
      "eval_samples_per_second": 48.045,
      "eval_steps_per_second": 1.508,
      "step": 2224
    }
  ],
  "logging_steps": 500,
  "max_steps": 5560,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.656985150205952e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}