{
  "best_metric": 0.6966881607229021,
  "best_model_checkpoint": "/kaggle/working/sweep_08/checkpoint-636",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 636,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.31446540880503143,
      "grad_norm": 10.8976469039917,
      "learning_rate": 9.97322623828648e-06,
      "loss": 0.3486,
      "step": 50
    },
    {
      "epoch": 0.6289308176100629,
      "grad_norm": 2.1524722576141357,
      "learning_rate": 9.303882195448461e-06,
      "loss": 0.3024,
      "step": 100
    },
    {
      "epoch": 0.9433962264150944,
      "grad_norm": 38.142704010009766,
      "learning_rate": 8.634538152610442e-06,
      "loss": 0.2815,
      "step": 150
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.14253897550111358,
      "eval_f1_macro": 0.12475633528265107,
      "eval_loss": 0.6558064818382263,
      "eval_precision_macro": 0.07126948775055679,
      "eval_recall_macro": 0.5,
      "eval_runtime": 2.6403,
      "eval_samples_per_second": 170.055,
      "eval_steps_per_second": 5.681,
      "step": 159
    },
    {
      "epoch": 1.2578616352201257,
      "grad_norm": 5.237600326538086,
      "learning_rate": 7.965194109772424e-06,
      "loss": 0.295,
      "step": 200
    },
    {
      "epoch": 1.5723270440251573,
      "grad_norm": 13.672293663024902,
      "learning_rate": 7.295850066934404e-06,
      "loss": 0.2368,
      "step": 250
    },
    {
      "epoch": 1.8867924528301887,
      "grad_norm": 13.05793285369873,
      "learning_rate": 6.626506024096386e-06,
      "loss": 0.2014,
      "step": 300
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6124721603563474,
      "eval_f1_macro": 0.5600418975537235,
      "eval_loss": 0.2551872134208679,
      "eval_precision_macro": 0.6213023625173715,
      "eval_recall_macro": 0.7479707792207793,
      "eval_runtime": 2.6406,
      "eval_samples_per_second": 170.038,
      "eval_steps_per_second": 5.681,
      "step": 318
    },
    {
      "epoch": 2.20125786163522,
      "grad_norm": 6.5023651123046875,
      "learning_rate": 5.957161981258367e-06,
      "loss": 0.1878,
      "step": 350
    },
    {
      "epoch": 2.5157232704402515,
      "grad_norm": 23.201416015625,
      "learning_rate": 5.287817938420349e-06,
      "loss": 0.1756,
      "step": 400
    },
    {
      "epoch": 2.830188679245283,
      "grad_norm": 12.81585693359375,
      "learning_rate": 4.61847389558233e-06,
      "loss": 0.1784,
      "step": 450
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.643652561247216,
      "eval_f1_macro": 0.5815275641921804,
      "eval_loss": 0.32544130086898804,
      "eval_precision_macro": 0.6241342249820874,
      "eval_recall_macro": 0.753125,
      "eval_runtime": 2.6269,
      "eval_samples_per_second": 170.921,
      "eval_steps_per_second": 5.71,
      "step": 477
    },
    {
      "epoch": 3.1446540880503147,
      "grad_norm": 152.0744171142578,
      "learning_rate": 3.949129852744311e-06,
      "loss": 0.1484,
      "step": 500
    },
    {
      "epoch": 3.459119496855346,
      "grad_norm": 15.98477840423584,
      "learning_rate": 3.2797858099062922e-06,
      "loss": 0.1869,
      "step": 550
    },
    {
      "epoch": 3.7735849056603774,
      "grad_norm": 54.855499267578125,
      "learning_rate": 2.6104417670682734e-06,
      "loss": 0.1257,
      "step": 600
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8285077951002228,
      "eval_f1_macro": 0.6966881607229021,
      "eval_loss": 0.30613085627555847,
      "eval_precision_macro": 0.6773720349563046,
      "eval_recall_macro": 0.7306412337662338,
      "eval_runtime": 2.6199,
      "eval_samples_per_second": 171.383,
      "eval_steps_per_second": 5.725,
      "step": 636
    }
  ],
  "logging_steps": 50,
  "max_steps": 795,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 1886354996127984.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}