{
  "best_global_step": 4460,
  "best_metric": 0.7541867307170775,
  "best_model_checkpoint": "outputs/xlm-r-spam-multiclass/checkpoint-4460",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 4460,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8840579710144928,
      "eval_f1": 0.7137811942959001,
      "eval_loss": 0.32824984192848206,
      "eval_precision": 0.7213268089674212,
      "eval_recall": 0.7079121225013852,
      "eval_runtime": 6.3096,
      "eval_samples_per_second": 251.523,
      "eval_steps_per_second": 31.539,
      "step": 446
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8998109640831758,
      "eval_f1": 0.7168827469599752,
      "eval_loss": 0.3459770381450653,
      "eval_precision": 0.766170915898107,
      "eval_recall": 0.6893280796817796,
      "eval_runtime": 6.3083,
      "eval_samples_per_second": 251.574,
      "eval_steps_per_second": 31.546,
      "step": 892
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8954001260239446,
      "eval_f1": 0.6763034311659557,
      "eval_loss": 0.39731308817863464,
      "eval_precision": 0.8262031478191135,
      "eval_recall": 0.6389074969910031,
      "eval_runtime": 6.3127,
      "eval_samples_per_second": 251.398,
      "eval_steps_per_second": 31.524,
      "step": 1338
    },
    {
      "epoch": 3.9960740325294446,
      "grad_norm": 19.04534149169922,
      "learning_rate": 2.98821174647605e-05,
      "loss": 0.3177,
      "step": 1782
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8853182104599874,
      "eval_f1": 0.7163989909661883,
      "eval_loss": 0.3976381719112396,
      "eval_precision": 0.7937122752680099,
      "eval_recall": 0.6782555160601897,
      "eval_runtime": 6.3136,
      "eval_samples_per_second": 251.361,
      "eval_steps_per_second": 31.519,
      "step": 1784
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8972904851921865,
      "eval_f1": 0.7240696238856752,
      "eval_loss": 0.3364667296409607,
      "eval_precision": 0.7712715993723438,
      "eval_recall": 0.6967038318634298,
      "eval_runtime": 6.3147,
      "eval_samples_per_second": 251.319,
      "eval_steps_per_second": 31.514,
      "step": 2230
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8960302457466919,
      "eval_f1": 0.7365734715240861,
      "eval_loss": 0.48667919635772705,
      "eval_precision": 0.7852054664367285,
      "eval_recall": 0.7043187608758201,
      "eval_runtime": 6.3072,
      "eval_samples_per_second": 251.617,
      "eval_steps_per_second": 31.551,
      "step": 2676
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8941398865784499,
      "eval_f1": 0.7228639129437386,
      "eval_loss": 0.5003412961959839,
      "eval_precision": 0.7626306514860101,
      "eval_recall": 0.6931187683348942,
      "eval_runtime": 6.3069,
      "eval_samples_per_second": 251.627,
      "eval_steps_per_second": 31.552,
      "step": 3122
    },
    {
      "epoch": 7.991587212563096,
      "grad_norm": 23.506858825683594,
      "learning_rate": 2.9530060331377034e-05,
      "loss": 0.181,
      "step": 3564
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8922495274102079,
      "eval_f1": 0.6891123093466665,
      "eval_loss": 0.5490124821662903,
      "eval_precision": 0.7907527744447496,
      "eval_recall": 0.6356830782183417,
      "eval_runtime": 6.3039,
      "eval_samples_per_second": 251.748,
      "eval_steps_per_second": 31.568,
      "step": 3568
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8998109640831758,
      "eval_f1": 0.7136351177900458,
      "eval_loss": 0.5626631379127502,
      "eval_precision": 0.8713974148011607,
      "eval_recall": 0.6774458988028211,
      "eval_runtime": 6.3122,
      "eval_samples_per_second": 251.418,
      "eval_steps_per_second": 31.526,
      "step": 4014
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9010712035286704,
      "eval_f1": 0.7541867307170775,
      "eval_loss": 0.5149542093276978,
      "eval_precision": 0.7672635798414982,
      "eval_recall": 0.7424688289447844,
      "eval_runtime": 6.3115,
      "eval_samples_per_second": 251.446,
      "eval_steps_per_second": 31.53,
      "step": 4460
    }
  ],
  "logging_steps": 1782,
  "max_steps": 44600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}