BulBERT-ner-wikiann_3epochs
This model is a fine-tuned version of mor40/BulBERT-chitanka-model on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2315
- Precision: 0.7856
- Recall: 0.8456
- F1: 0.8145
- Accuracy: 0.9419
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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2412 | 1.0 | 2030 | 0.2453 | 0.7370 | 0.8098 | 0.7716 | 0.9275 |
| 0.159 | 2.0 | 4060 | 0.2240 | 0.7746 | 0.8358 | 0.8040 | 0.9393 |
| 0.1014 | 3.0 | 6090 | 0.2315 | 0.7856 | 0.8456 | 0.8145 | 0.9419 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1