balluk's picture
End of training
8700cf8
metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - sem_eval_2018_task_1
metrics:
  - f1
  - accuracy
model-index:
  - name: bert-finetuned-sem_eval-english
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: sem_eval_2018_task_1
          type: sem_eval_2018_task_1
          config: subtask5.english
          split: validation
          args: subtask5.english
        metrics:
          - name: F1
            type: f1
            value: 0.7075236671649229
          - name: Accuracy
            type: accuracy
            value: 0.28555304740406323

bert-finetuned-sem_eval-english

This model is a fine-tuned version of bert-base-uncased on the sem_eval_2018_task_1 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3008
  • F1: 0.7075
  • Roc Auc: 0.8000
  • Accuracy: 0.2856

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss F1 Roc Auc Accuracy
0.3964 1.0 855 0.3197 0.6852 0.7849 0.2810
0.2788 2.0 1710 0.3039 0.7049 0.7978 0.2912
0.2347 3.0 2565 0.3008 0.7075 0.8000 0.2856
0.2094 4.0 3420 0.3091 0.7041 0.7976 0.2856
0.1886 5.0 4275 0.3122 0.7068 0.8011 0.2810

Framework versions

  • Transformers 4.33.3
  • Pytorch 2.0.1
  • Datasets 2.14.5
  • Tokenizers 0.13.3