{
  "best_global_step": 7188,
  "best_metric": 0.7064367615901695,
  "best_model_checkpoint": "results_marbert_augmented_x4/checkpoint-7188",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 7188,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.5444260835647583,
      "learning_rate": 1.600222593210907e-05,
      "loss": 0.7759682342750069,
      "step": 1797
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7147613762486127,
      "eval_f1_macro": 0.6661366194710371,
      "eval_loss": 1.170723795890808,
      "eval_runtime": 60.3414,
      "eval_samples_per_second": 14.932,
      "eval_steps_per_second": 3.745,
      "step": 1797
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.1501867771148682,
      "learning_rate": 1.200222593210907e-05,
      "loss": 0.45686454964002504,
      "step": 3594
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7380688124306326,
      "eval_f1_macro": 0.6947959820612603,
      "eval_loss": 1.496320128440857,
      "eval_runtime": 60.2764,
      "eval_samples_per_second": 14.948,
      "eval_steps_per_second": 3.749,
      "step": 3594
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.019423065707087517,
      "learning_rate": 8.002225932109071e-06,
      "loss": 0.2114539212761286,
      "step": 5391
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7480577136514983,
      "eval_f1_macro": 0.7020636607249949,
      "eval_loss": 1.839005708694458,
      "eval_runtime": 60.3712,
      "eval_samples_per_second": 14.924,
      "eval_steps_per_second": 3.744,
      "step": 5391
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.0047567361034452915,
      "learning_rate": 4.002225932109071e-06,
      "loss": 0.10288739934124148,
      "step": 7188
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7391786903440621,
      "eval_f1_macro": 0.7064367615901695,
      "eval_loss": 2.0361692905426025,
      "eval_runtime": 61.9584,
      "eval_samples_per_second": 14.542,
      "eval_steps_per_second": 3.648,
      "step": 7188
    }
  ],
  "logging_steps": 500,
  "max_steps": 8985,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.001
      },
      "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": 1241138880600192.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}