{
  "best_metric": 0.7168468468468467,
  "best_model_checkpoint": "/kaggle/working/sweep_00/checkpoint-318",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 318,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.31446540880503143,
      "grad_norm": 3.313129186630249,
      "learning_rate": 1.9062500000000003e-05,
      "loss": 0.3197,
      "step": 50
    },
    {
      "epoch": 0.6289308176100629,
      "grad_norm": 1.1465544700622559,
      "learning_rate": 1.6830357142857144e-05,
      "loss": 0.3181,
      "step": 100
    },
    {
      "epoch": 0.9433962264150944,
      "grad_norm": 1.2599937915802002,
      "learning_rate": 1.4598214285714288e-05,
      "loss": 0.2352,
      "step": 150
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.41870824053452116,
      "eval_f1_macro": 0.3996495919590576,
      "eval_loss": 0.22780387103557587,
      "eval_precision_macro": 0.5538023679417122,
      "eval_recall_macro": 0.595900974025974,
      "eval_runtime": 2.6324,
      "eval_samples_per_second": 170.568,
      "eval_steps_per_second": 5.698,
      "step": 159
    },
    {
      "epoch": 1.2578616352201257,
      "grad_norm": 1.463349461555481,
      "learning_rate": 1.236607142857143e-05,
      "loss": 0.2283,
      "step": 200
    },
    {
      "epoch": 1.5723270440251573,
      "grad_norm": 7.018613815307617,
      "learning_rate": 1.0133928571428573e-05,
      "loss": 0.1923,
      "step": 250
    },
    {
      "epoch": 1.8867924528301887,
      "grad_norm": 6.164895534515381,
      "learning_rate": 7.901785714285715e-06,
      "loss": 0.2143,
      "step": 300
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.844097995545657,
      "eval_f1_macro": 0.7168468468468467,
      "eval_loss": 0.19291774928569794,
      "eval_precision_macro": 0.6978962818003913,
      "eval_recall_macro": 0.7462459415584415,
      "eval_runtime": 2.6241,
      "eval_samples_per_second": 171.103,
      "eval_steps_per_second": 5.716,
      "step": 318
    }
  ],
  "logging_steps": 50,
  "max_steps": 477,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 980116646450268.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}