<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
bert-finetuned-n2c2-ner
This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2116
- Precision: 0.9059
- Recall: 0.8858
- F1: 0.8958
- Accuracy: 0.9758
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: 4
- eval_batch_size: 4
- 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 |
|---|---|---|---|---|---|---|---|
| 0.0545 | 1.0 | 10469 | 0.1255 | 0.8929 | 0.8933 | 0.8931 | 0.9762 |
| 0.0639 | 2.0 | 20938 | 0.1136 | 0.8933 | 0.8784 | 0.8858 | 0.9747 |
| 0.0452 | 3.0 | 31407 | 0.1221 | 0.8864 | 0.8991 | 0.8927 | 0.9753 |
| 0.0284 | 4.0 | 41876 | 0.1453 | 0.9003 | 0.8821 | 0.8911 | 0.9756 |
| 0.0269 | 5.0 | 52345 | 0.1587 | 0.9011 | 0.8934 | 0.8972 | 0.9765 |
| 0.0202 | 6.0 | 62814 | 0.1756 | 0.9190 | 0.8660 | 0.8917 | 0.9755 |
| 0.0153 | 7.0 | 73283 | 0.1818 | 0.9063 | 0.8831 | 0.8945 | 0.9757 |
| 0.0119 | 8.0 | 83752 | 0.2012 | 0.9163 | 0.8744 | 0.8948 | 0.9760 |
| 0.0122 | 9.0 | 94221 | 0.1986 | 0.9001 | 0.8908 | 0.8954 | 0.9757 |
| 0.0073 | 10.0 | 104690 | 0.2116 | 0.9059 | 0.8858 | 0.8958 | 0.9758 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.8.1+cu111
- Datasets 2.13.1
- Tokenizers 0.13.3
