{
  "best_metric": 1.1521096229553223,
  "best_model_checkpoint": "../experiments/attribute_minig_mslacerda/run-1/checkpoint-510",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 510,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.04864864864864865,
      "eval_f1": 0.007113821138211382,
      "eval_loss": 4.620906829833984,
      "eval_precision": 0.006029285099052541,
      "eval_recall": 0.008674101610904586,
      "eval_runtime": 0.3907,
      "eval_samples_per_second": 744.791,
      "eval_steps_per_second": 94.698,
      "step": 85
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2111111111111111,
      "eval_f1": 0.04960460100647016,
      "eval_loss": 3.850735664367676,
      "eval_precision": 0.059075342465753425,
      "eval_recall": 0.04275092936802974,
      "eval_runtime": 1.6915,
      "eval_samples_per_second": 172.039,
      "eval_steps_per_second": 21.874,
      "step": 170
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.44054054054054054,
      "eval_f1": 0.18526622902990514,
      "eval_loss": 2.6320598125457764,
      "eval_precision": 0.225177304964539,
      "eval_recall": 0.15737298636926889,
      "eval_runtime": 0.3588,
      "eval_samples_per_second": 811.062,
      "eval_steps_per_second": 103.125,
      "step": 255
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5570570570570571,
      "eval_f1": 0.30614370010413056,
      "eval_loss": 1.849010944366455,
      "eval_precision": 0.34806629834254144,
      "eval_recall": 0.2732342007434944,
      "eval_runtime": 0.3664,
      "eval_samples_per_second": 794.234,
      "eval_steps_per_second": 100.985,
      "step": 340
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6555555555555556,
      "eval_f1": 0.4209836065573771,
      "eval_loss": 1.4208729267120361,
      "eval_precision": 0.44707520891364905,
      "eval_recall": 0.39776951672862454,
      "eval_runtime": 0.3604,
      "eval_samples_per_second": 807.544,
      "eval_steps_per_second": 102.677,
      "step": 425
    },
    {
      "epoch": 5.882352941176471,
      "grad_norm": 3.7843017578125,
      "learning_rate": 1.5433595543093596e-05,
      "loss": 2.9293,
      "step": 500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7318318318318319,
      "eval_f1": 0.5283259070655634,
      "eval_loss": 1.1521096229553223,
      "eval_precision": 0.5431937172774869,
      "eval_recall": 0.5142503097893433,
      "eval_runtime": 0.4301,
      "eval_samples_per_second": 676.547,
      "eval_steps_per_second": 86.021,
      "step": 510
    }
  ],
  "logging_steps": 500,
  "max_steps": 1020,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 12,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 64294017133920.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 2.06572740346022e-05,
    "num_train_epochs": 12,
    "per_device_train_batch_size": 16,
    "warmup_steps": 324,
    "weight_decay": 0.18787435700436622
  }
}