{
  "best_metric": 0.7148663237442052,
  "best_model_checkpoint": "/kaggle/working/sweep_13/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": 14.776991844177246,
      "learning_rate": 1.9062500000000003e-05,
      "loss": 0.1982,
      "step": 50
    },
    {
      "epoch": 0.6289308176100629,
      "grad_norm": 5.086421012878418,
      "learning_rate": 1.6830357142857144e-05,
      "loss": 0.1704,
      "step": 100
    },
    {
      "epoch": 0.9433962264150944,
      "grad_norm": 7.991980075836182,
      "learning_rate": 1.4598214285714288e-05,
      "loss": 0.1255,
      "step": 150
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7282850779510023,
      "eval_f1_macro": 0.6393146860514117,
      "eval_loss": 0.09497806429862976,
      "eval_precision_macro": 0.6395879038155461,
      "eval_recall_macro": 0.7633928571428572,
      "eval_runtime": 2.6307,
      "eval_samples_per_second": 170.678,
      "eval_steps_per_second": 5.702,
      "step": 159
    },
    {
      "epoch": 1.2578616352201257,
      "grad_norm": 13.86682415008545,
      "learning_rate": 1.236607142857143e-05,
      "loss": 0.1204,
      "step": 200
    },
    {
      "epoch": 1.5723270440251573,
      "grad_norm": 36.624263763427734,
      "learning_rate": 1.0133928571428573e-05,
      "loss": 0.0991,
      "step": 250
    },
    {
      "epoch": 1.8867924528301887,
      "grad_norm": 14.556501388549805,
      "learning_rate": 7.901785714285715e-06,
      "loss": 0.092,
      "step": 300
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.821826280623608,
      "eval_f1_macro": 0.7148663237442052,
      "eval_loss": 0.11809030920267105,
      "eval_precision_macro": 0.6885626173236792,
      "eval_recall_macro": 0.7853693181818182,
      "eval_runtime": 2.6323,
      "eval_samples_per_second": 170.573,
      "eval_steps_per_second": 5.698,
      "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": 935341342670100.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}