ner_normal
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: 0.2296
- Precision: 0.7861
- Recall: 0.8096
- F1: 0.7977
- Accuracy: 0.9665
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: 5e-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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.2034 | 1.0 | 469 | 0.1266 | 0.7724 | 0.8018 | 0.7868 | 0.9640 |
0.1022 | 2.0 | 938 | 0.1222 | 0.7761 | 0.7906 | 0.7833 | 0.9649 |
0.0669 | 3.0 | 1407 | 0.1283 | 0.7751 | 0.8088 | 0.7916 | 0.9657 |
0.0419 | 4.0 | 1876 | 0.1513 | 0.7753 | 0.8074 | 0.7910 | 0.9662 |
0.0245 | 5.0 | 2345 | 0.1623 | 0.7774 | 0.8064 | 0.7916 | 0.9663 |
0.0147 | 6.0 | 2814 | 0.1819 | 0.7812 | 0.8092 | 0.7949 | 0.9661 |
0.008 | 7.0 | 3283 | 0.1990 | 0.7839 | 0.8034 | 0.7935 | 0.9659 |
0.0048 | 8.0 | 3752 | 0.2153 | 0.7857 | 0.8076 | 0.7965 | 0.9661 |
0.0029 | 9.0 | 4221 | 0.2256 | 0.7833 | 0.8084 | 0.7956 | 0.9659 |
0.0018 | 10.0 | 4690 | 0.2296 | 0.7861 | 0.8096 | 0.7977 | 0.9665 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2
- Downloads last month
- 3