biogpt-finetuned-ner
This model is a fine-tuned version of microsoft/biogpt on the ncbi_disease dataset. It achieves the following results on the evaluation set:
- Loss: 0.1728
- Precision: 0.4700
- Recall: 0.5769
- F1: 0.5180
- Accuracy: 0.9581
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 |
|---|---|---|---|---|---|---|---|
| 0.1029 | 1.0 | 679 | 0.1493 | 0.4228 | 0.5845 | 0.4907 | 0.9554 |
| 0.076 | 2.0 | 1358 | 0.1756 | 0.4138 | 0.5705 | 0.4797 | 0.9533 |
| 0.0516 | 3.0 | 2037 | 0.1728 | 0.4700 | 0.5769 | 0.5180 | 0.9581 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3