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: 0.3129
- F1: 0.7081
- Roc Auc: 0.8031
- Accuracy: 0.2675
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.4084 | 1.0 | 855 | 0.3155 | 0.6932 | 0.7890 | 0.2754 |
| 0.2826 | 2.0 | 1710 | 0.3029 | 0.6965 | 0.7877 | 0.2765 |
| 0.2412 | 3.0 | 2565 | 0.3082 | 0.7081 | 0.8021 | 0.2731 |
| 0.213 | 4.0 | 3420 | 0.3125 | 0.6992 | 0.7960 | 0.2619 |
| 0.1924 | 5.0 | 4275 | 0.3129 | 0.7081 | 0.8031 | 0.2675 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1