{
  "best_metric": 0.5824584566376877,
  "best_model_checkpoint": "students_scores_model/run-3/checkpoint-564",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 564,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_f1": 0.527378071005394,
      "eval_loss": 1.0453823804855347,
      "eval_runtime": 37.8811,
      "eval_samples_per_second": 59.396,
      "eval_steps_per_second": 7.444,
      "step": 282
    },
    {
      "epoch": 1.773049645390071,
      "grad_norm": 10.149354934692383,
      "learning_rate": 1.4371191049893149e-05,
      "loss": 1.0168,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.5824584566376877,
      "eval_loss": 0.9663960337638855,
      "eval_runtime": 37.8357,
      "eval_samples_per_second": 59.468,
      "eval_steps_per_second": 7.453,
      "step": 564
    }
  ],
  "logging_steps": 500,
  "max_steps": 1410,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 4203350064691200.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 2.2267449868515756e-05,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 32,
    "weight_decay": 0.0007528832894945841
  }
}