trainer_state.json

{
  "best_metric": 0.9654395191585274,
  "best_model_checkpoint": "/content/drive/MyDrive/SODUCO/article_das_2022/42-experiment_2_finetuned_camembert/checkpoint-700",
  "epoch": 1.8617021276595744,
  "global_step": 700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.27,
      "eval_accuracy": 0.9666871542716656,
      "eval_f1": 0.9407993966817497,
      "eval_loss": 0.23340629041194916,
      "eval_precision": 0.9411542814032441,
      "eval_recall": 0.9404447794949115,
      "eval_runtime": 2.6624,
      "eval_samples_per_second": 250.906,
      "eval_steps_per_second": 15.776,
      "step": 100
    },
    {
      "epoch": 0.53,
      "eval_accuracy": 0.9729563614013522,
      "eval_f1": 0.9542459047260402,
      "eval_loss": 0.14227047562599182,
      "eval_precision": 0.9533483822422875,
      "eval_recall": 0.9551451187335093,
      "eval_runtime": 2.474,
      "eval_samples_per_second": 270.009,
      "eval_steps_per_second": 16.977,
      "step": 200
    },
    {
      "epoch": 0.8,
      "eval_accuracy": 0.9794714197910265,
      "eval_f1": 0.9598046581517656,
      "eval_loss": 0.10758526623249054,
      "eval_precision": 0.9565705728191688,
      "eval_recall": 0.9630606860158312,
      "eval_runtime": 2.467,
      "eval_samples_per_second": 270.769,
      "eval_steps_per_second": 17.024,
      "step": 300
    },
    {
      "epoch": 1.06,
      "eval_accuracy": 0.978119237861094,
      "eval_f1": 0.9622393387187677,
      "eval_loss": 0.10391023010015488,
      "eval_precision": 0.9591760299625468,
      "eval_recall": 0.9653222766679231,
      "eval_runtime": 2.469,
      "eval_samples_per_second": 270.56,
      "eval_steps_per_second": 17.011,
      "step": 400
    },
    {
      "epoch": 1.33,
      "learning_rate": 9e-05,
      "loss": 0.2217,
      "step": 500
    },
    {
      "epoch": 1.33,
      "eval_accuracy": 0.9776275353411186,
      "eval_f1": 0.9546053870785459,
      "eval_loss": 0.0932990312576294,
      "eval_precision": 0.954066265060241,
      "eval_recall": 0.9551451187335093,
      "eval_runtime": 2.5383,
      "eval_samples_per_second": 263.164,
      "eval_steps_per_second": 16.546,
      "step": 500
    },
    {
      "epoch": 1.6,
      "eval_accuracy": 0.9740626920712969,
      "eval_f1": 0.9599096555618294,
      "eval_loss": 0.10465865582227707,
      "eval_precision": 0.9586466165413534,
      "eval_recall": 0.9611760271390878,
      "eval_runtime": 2.4984,
      "eval_samples_per_second": 267.37,
      "eval_steps_per_second": 16.811,
      "step": 600
    },
    {
      "epoch": 1.86,
      "eval_accuracy": 0.9805777504609711,
      "eval_f1": 0.9654395191585274,
      "eval_loss": 0.08172685652971268,
      "eval_precision": 0.9621864470235867,
      "eval_recall": 0.9687146626460611,
      "eval_runtime": 2.5163,
      "eval_samples_per_second": 265.472,
      "eval_steps_per_second": 16.691,
      "step": 700
    }
  ],
  "max_steps": 5000,
  "num_train_epochs": 14,
  "total_flos": 275154731817120.0,
  "trial_name": null,
  "trial_params": null
}