{
  "best_metric": 0.6252309316442333,
  "best_model_checkpoint": "model_checkpoints/fine-tuned_blog-authorship-age/deberta-v3-small/checkpoint-858",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 858,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 16.06877326965332,
      "learning_rate": 3.341103341103341e-05,
      "loss": 0.8989,
      "step": 429
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6025336500395883,
      "eval_f1": 0.6025336500395883,
      "eval_loss": 0.8372386693954468,
      "eval_runtime": 263.0843,
      "eval_samples_per_second": 14.402,
      "eval_steps_per_second": 3.603,
      "step": 429
    },
    {
      "epoch": 2.0,
      "grad_norm": 28.210113525390625,
      "learning_rate": 1.6744366744366746e-05,
      "loss": 0.7219,
      "step": 858
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6252309316442333,
      "eval_f1": 0.6252309316442333,
      "eval_loss": 0.8790310621261597,
      "eval_runtime": 263.0807,
      "eval_samples_per_second": 14.402,
      "eval_steps_per_second": 3.603,
      "step": 858
    }
  ],
  "logging_steps": 500,
  "max_steps": 1287,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.01
      },
      "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": 908907404645376.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}