{
  "best_metric": 0.7258392067853303,
  "best_model_checkpoint": "v5_FacebookAI-roberta-finetuned_0.6/checkpoint-6720",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 8400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2976190476190476,
      "grad_norm": 4.1533942222595215,
      "learning_rate": 1.880952380952381e-05,
      "loss": 0.3069,
      "step": 500
    },
    {
      "epoch": 0.5952380952380952,
      "grad_norm": 2.221773862838745,
      "learning_rate": 1.761904761904762e-05,
      "loss": 0.2462,
      "step": 1000
    },
    {
      "epoch": 0.8928571428571429,
      "grad_norm": 2.764221668243408,
      "learning_rate": 1.642857142857143e-05,
      "loss": 0.2377,
      "step": 1500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.4998697577494139,
      "eval_f1": 0.6606451612903226,
      "eval_loss": 0.23182548582553864,
      "eval_roc_auc": 0.769734788870904,
      "eval_runtime": 27.2673,
      "eval_samples_per_second": 140.791,
      "eval_steps_per_second": 17.603,
      "step": 1680
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 5.783968448638916,
      "learning_rate": 1.523809523809524e-05,
      "loss": 0.2231,
      "step": 2000
    },
    {
      "epoch": 1.4880952380952381,
      "grad_norm": 2.9908080101013184,
      "learning_rate": 1.4047619047619048e-05,
      "loss": 0.2093,
      "step": 2500
    },
    {
      "epoch": 1.7857142857142856,
      "grad_norm": 2.847262382507324,
      "learning_rate": 1.2857142857142859e-05,
      "loss": 0.2095,
      "step": 3000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5480593904662673,
      "eval_f1": 0.7181280907007599,
      "eval_loss": 0.21270480751991272,
      "eval_roc_auc": 0.8134747296545921,
      "eval_runtime": 27.2424,
      "eval_samples_per_second": 140.92,
      "eval_steps_per_second": 17.62,
      "step": 3360
    },
    {
      "epoch": 2.0833333333333335,
      "grad_norm": 5.025007724761963,
      "learning_rate": 1.1666666666666668e-05,
      "loss": 0.2001,
      "step": 3500
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 3.802976608276367,
      "learning_rate": 1.0476190476190477e-05,
      "loss": 0.1811,
      "step": 4000
    },
    {
      "epoch": 2.678571428571429,
      "grad_norm": 5.3271260261535645,
      "learning_rate": 9.285714285714288e-06,
      "loss": 0.1771,
      "step": 4500
    },
    {
      "epoch": 2.9761904761904763,
      "grad_norm": 3.496102809906006,
      "learning_rate": 8.095238095238097e-06,
      "loss": 0.181,
      "step": 5000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5527481114873665,
      "eval_f1": 0.7126801856828732,
      "eval_loss": 0.2160826325416565,
      "eval_roc_auc": 0.8077876952054592,
      "eval_runtime": 27.2021,
      "eval_samples_per_second": 141.129,
      "eval_steps_per_second": 17.646,
      "step": 5040
    },
    {
      "epoch": 3.2738095238095237,
      "grad_norm": 6.713701248168945,
      "learning_rate": 6.9047619047619055e-06,
      "loss": 0.1559,
      "step": 5500
    },
    {
      "epoch": 3.571428571428571,
      "grad_norm": 3.177034378051758,
      "learning_rate": 5.7142857142857145e-06,
      "loss": 0.1553,
      "step": 6000
    },
    {
      "epoch": 3.869047619047619,
      "grad_norm": 4.837090492248535,
      "learning_rate": 4.523809523809524e-06,
      "loss": 0.1577,
      "step": 6500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5662933055483199,
      "eval_f1": 0.7258392067853303,
      "eval_loss": 0.2207617312669754,
      "eval_roc_auc": 0.8198539129062529,
      "eval_runtime": 27.1734,
      "eval_samples_per_second": 141.278,
      "eval_steps_per_second": 17.664,
      "step": 6720
    },
    {
      "epoch": 4.166666666666667,
      "grad_norm": 4.641733169555664,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.1449,
      "step": 7000
    },
    {
      "epoch": 4.464285714285714,
      "grad_norm": 7.923290729522705,
      "learning_rate": 2.1428571428571427e-06,
      "loss": 0.137,
      "step": 7500
    },
    {
      "epoch": 4.761904761904762,
      "grad_norm": 6.048860549926758,
      "learning_rate": 9.523809523809525e-07,
      "loss": 0.1334,
      "step": 8000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5626465225319094,
      "eval_f1": 0.7250504331316008,
      "eval_loss": 0.22809843719005585,
      "eval_roc_auc": 0.8208790401374375,
      "eval_runtime": 27.4047,
      "eval_samples_per_second": 140.086,
      "eval_steps_per_second": 17.515,
      "step": 8400
    }
  ],
  "logging_steps": 500,
  "max_steps": 8400,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4420464168960000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}