BERT_token_classification_AraiEval24_Eng_single
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0059
- Precision: 0.1067
- Recall: 0.0772
- F1: 0.0896
- Accuracy: 0.8287
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.6871 | 1.0 | 2189 | 0.7831 | 0.1860 | 0.0105 | 0.0198 | 0.8498 |
0.5729 | 2.0 | 4378 | 0.7291 | 0.0959 | 0.0212 | 0.0347 | 0.8488 |
0.5172 | 3.0 | 6567 | 0.7381 | 0.0994 | 0.0474 | 0.0642 | 0.8427 |
0.412 | 4.0 | 8756 | 0.7873 | 0.1443 | 0.0571 | 0.0818 | 0.8472 |
0.3725 | 5.0 | 10945 | 0.8153 | 0.1233 | 0.0526 | 0.0737 | 0.8453 |
0.3209 | 6.0 | 13134 | 0.8651 | 0.1117 | 0.0639 | 0.0813 | 0.8392 |
0.2622 | 7.0 | 15323 | 0.9002 | 0.1280 | 0.0714 | 0.0917 | 0.8363 |
0.2399 | 8.0 | 17512 | 0.9425 | 0.1148 | 0.0788 | 0.0934 | 0.8301 |
0.2178 | 9.0 | 19701 | 0.9766 | 0.1071 | 0.0861 | 0.0955 | 0.8263 |
0.1857 | 10.0 | 21890 | 1.0059 | 0.1067 | 0.0772 | 0.0896 | 0.8287 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.13.3
- Downloads last month
- 0