{
  "best_metric": 0.08995594084262848,
  "best_model_checkpoint": "./fine_tuned_wp/checkpoint-400",
  "epoch": 0.1426126640045636,
  "eval_steps": 100,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02852253280091272,
      "grad_norm": 197.712646484375,
      "learning_rate": 1.9809849781327252e-05,
      "loss": 0.844,
      "step": 100
    },
    {
      "epoch": 0.02852253280091272,
      "eval_accuracy": 0.8626444159178434,
      "eval_loss": 0.360164076089859,
      "eval_runtime": 261.7294,
      "eval_samples_per_second": 11.905,
      "eval_steps_per_second": 1.49,
      "step": 100
    },
    {
      "epoch": 0.05704506560182544,
      "grad_norm": 0.009975558146834373,
      "learning_rate": 1.96196995626545e-05,
      "loss": 0.4928,
      "step": 200
    },
    {
      "epoch": 0.05704506560182544,
      "eval_accuracy": 0.9165596919127086,
      "eval_loss": 0.3830508291721344,
      "eval_runtime": 261.8903,
      "eval_samples_per_second": 11.898,
      "eval_steps_per_second": 1.489,
      "step": 200
    },
    {
      "epoch": 0.08556759840273816,
      "grad_norm": 0.34520554542541504,
      "learning_rate": 1.9429549343981745e-05,
      "loss": 0.2699,
      "step": 300
    },
    {
      "epoch": 0.08556759840273816,
      "eval_accuracy": 0.9682284980744544,
      "eval_loss": 0.25395825505256653,
      "eval_runtime": 261.714,
      "eval_samples_per_second": 11.906,
      "eval_steps_per_second": 1.49,
      "step": 300
    },
    {
      "epoch": 0.11409013120365089,
      "grad_norm": 0.1104673519730568,
      "learning_rate": 1.9239399125308995e-05,
      "loss": 0.2095,
      "step": 400
    },
    {
      "epoch": 0.11409013120365089,
      "eval_accuracy": 0.9752888318356868,
      "eval_loss": 0.08995594084262848,
      "eval_runtime": 261.7715,
      "eval_samples_per_second": 11.904,
      "eval_steps_per_second": 1.49,
      "step": 400
    },
    {
      "epoch": 0.1426126640045636,
      "grad_norm": 27.196149826049805,
      "learning_rate": 1.9049248906636245e-05,
      "loss": 0.1506,
      "step": 500
    },
    {
      "epoch": 0.1426126640045636,
      "eval_accuracy": 0.9801026957637997,
      "eval_loss": 0.09910330921411514,
      "eval_runtime": 261.6697,
      "eval_samples_per_second": 11.908,
      "eval_steps_per_second": 1.49,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 10518,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.610150313984e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}