{
  "best_global_step": 1575,
  "best_metric": 0.8496918262939779,
  "best_model_checkpoint": "outputs/runs/phobert-v2/checkpoint-1575",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1575,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9968253968253968,
      "grad_norm": 2.4804160594940186,
      "learning_rate": 4.999432333543028e-06,
      "loss": 0.4526,
      "step": 314
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8164201131452264,
      "eval_f1": 0.7853495674013324,
      "eval_loss": 0.4426233768463135,
      "eval_precision": 0.8663001235103381,
      "eval_recall": 0.770170816778579,
      "eval_runtime": 1.5259,
      "eval_samples_per_second": 852.584,
      "eval_steps_per_second": 26.869,
      "step": 315
    },
    {
      "epoch": 1.9936507936507937,
      "grad_norm": 1.944218635559082,
      "learning_rate": 4.996525669931999e-06,
      "loss": 0.327,
      "step": 628
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8541234758775783,
      "eval_f1": 0.8430146273656823,
      "eval_loss": 0.33350232243537903,
      "eval_precision": 0.8554774499016723,
      "eval_recall": 0.8356591040632221,
      "eval_runtime": 1.5323,
      "eval_samples_per_second": 849.025,
      "eval_steps_per_second": 26.756,
      "step": 630
    },
    {
      "epoch": 2.9904761904761905,
      "grad_norm": 2.595008134841919,
      "learning_rate": 4.991155236893945e-06,
      "loss": 0.3035,
      "step": 942
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8560560806774659,
      "eval_f1": 0.8452619099119734,
      "eval_loss": 0.3418947756290436,
      "eval_precision": 0.8571341137073532,
      "eval_recall": 0.8381164023293842,
      "eval_runtime": 1.534,
      "eval_samples_per_second": 848.099,
      "eval_steps_per_second": 26.727,
      "step": 945
    },
    {
      "epoch": 3.9873015873015873,
      "grad_norm": 3.5686192512512207,
      "learning_rate": 4.983326334397891e-06,
      "loss": 0.2892,
      "step": 1256
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.850943462525036,
      "eval_f1": 0.8350973607034302,
      "eval_loss": 0.37049615383148193,
      "eval_precision": 0.8672179930404993,
      "eval_recall": 0.8223564834127113,
      "eval_runtime": 1.5367,
      "eval_samples_per_second": 846.62,
      "eval_steps_per_second": 26.681,
      "step": 1260
    },
    {
      "epoch": 4.984126984126984,
      "grad_norm": 4.157222270965576,
      "learning_rate": 4.97304668862541e-06,
      "loss": 0.2811,
      "step": 1570
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8591833866263748,
      "eval_f1": 0.8496918262939779,
      "eval_loss": 0.3258833885192871,
      "eval_precision": 0.857585126065477,
      "eval_recall": 0.8443036944948177,
      "eval_runtime": 1.5387,
      "eval_samples_per_second": 845.533,
      "eval_steps_per_second": 26.646,
      "step": 1575
    }
  ],
  "logging_steps": 314,
  "max_steps": 31500,
  "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": 1645189704599040.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}