trainer_state.json

{
  "best_metric": 0.688748846434271,
  "best_model_checkpoint": "output-no-git/EN-OUTPUT/ON_FS_OUT/XLNetFalseTrue-0-1/TrueFalse-0/train_from_dev_and_test_short.csv/1/checkpoint-18",
  "epoch": 6.0,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7060086131095886,
      "eval_f1": 0.6763806868584463,
      "eval_f1_binary": 0.7742998352553541,
      "eval_f1_weighted": 0.697813633503263,
      "eval_loss": 0.6087642312049866,
      "eval_runtime": 1.8252,
      "eval_samples_per_second": 255.31,
      "eval_steps_per_second": 32.325,
      "step": 3
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7038626670837402,
      "eval_f1": 0.6863881086142323,
      "eval_f1_binary": 0.7604166666666667,
      "eval_f1_weighted": 0.702591784411117,
      "eval_loss": 0.5733329057693481,
      "eval_runtime": 1.8207,
      "eval_samples_per_second": 255.939,
      "eval_steps_per_second": 32.404,
      "step": 6
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7145922780036926,
      "eval_f1": 0.6748046823760278,
      "eval_f1_binary": 0.7885532591414944,
      "eval_f1_weighted": 0.6997024395221171,
      "eval_loss": 0.5822879672050476,
      "eval_runtime": 1.8268,
      "eval_samples_per_second": 255.088,
      "eval_steps_per_second": 32.297,
      "step": 9
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6995708346366882,
      "eval_f1": 0.6317370001580527,
      "eval_f1_binary": 0.7897897897897898,
      "eval_f1_weighted": 0.6663322459572741,
      "eval_loss": 0.652556300163269,
      "eval_runtime": 1.8238,
      "eval_samples_per_second": 255.509,
      "eval_steps_per_second": 32.35,
      "step": 12
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.725321888923645,
      "eval_f1": 0.6831548529661737,
      "eval_f1_binary": 0.7987421383647799,
      "eval_f1_weighted": 0.7084550742336797,
      "eval_loss": 0.6597227454185486,
      "eval_runtime": 1.8184,
      "eval_samples_per_second": 256.267,
      "eval_steps_per_second": 32.446,
      "step": 15
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7188841104507446,
      "eval_f1": 0.688748846434271,
      "eval_f1_binary": 0.7855973813420623,
      "eval_f1_weighted": 0.7099474527874785,
      "eval_loss": 0.6554996371269226,
      "eval_runtime": 1.8291,
      "eval_samples_per_second": 254.774,
      "eval_steps_per_second": 32.257,
      "step": 18
    }
  ],
  "max_steps": 27,
  "num_train_epochs": 9,
  "total_flos": 37176876481536.0,
  "trial_name": null,
  "trial_params": null
}