distilbert-base-uncased-finetuned-pos
This model is a fine-tuned version of distilbert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3165
- Precision: 0.9109
- Recall: 0.9144
- F1: 0.9126
- Accuracy: 0.9246
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: 16
- eval_batch_size: 16
- 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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.7941 | 1.0 | 878 | 0.3504 | 0.8995 | 0.9026 | 0.9011 | 0.9176 |
| 0.2533 | 2.0 | 1756 | 0.3216 | 0.9091 | 0.9104 | 0.9098 | 0.9233 |
| 0.2047 | 3.0 | 2634 | 0.3165 | 0.9109 | 0.9144 | 0.9126 | 0.9246 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6