BIO_GPT_NER_FINETUNED_C
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: 0.1466
- Precision: 0.4418
- Recall: 0.5584
- F1: 0.4933
- 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 |
|---|---|---|---|---|---|---|---|
| 0.2989 | 1.0 | 680 | 0.1687 | 0.3350 | 0.4226 | 0.3737 | 0.9474 |
| 0.1764 | 2.0 | 1360 | 0.1425 | 0.4289 | 0.5241 | 0.4717 | 0.9560 |
| 0.0942 | 3.0 | 2040 | 0.1466 | 0.4418 | 0.5584 | 0.4933 | 0.9581 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3