distilbert-finetuned-pos-tag
This model is a fine-tuned version of distilbert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0467
- F1: 0.9664
- Accuracy: 0.9885
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
|---|---|---|---|---|---|
| 0.0497 | 1.0 | 5376 | 0.0459 | 0.9614 | 0.9868 |
| 0.03 | 2.0 | 10752 | 0.0462 | 0.9648 | 0.9879 |
| 0.0169 | 3.0 | 16128 | 0.0467 | 0.9664 | 0.9885 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1