<!-- 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. -->
Procedures_Identification_RoBERTa_fine_tuned
This model is a fine-tuned version of PlanTL-GOB-ES/roberta-base-biomedical-clinical-es on the [MedProcNER dataset] (https://temu.bsc.es/medprocner/). This is a result of the PhD dissertation of Antonio Tamayo. It achieves the following results on the evaluation set:
- Loss: 0.1820
- Precision: 0.7209
- Recall: 0.7813
- F1: 0.7499
- Accuracy: 0.9659
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: 7
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.1142 | 1.0 | 1132 | 0.1094 | 0.6387 | 0.7417 | 0.6864 | 0.9605 |
0.087 | 2.0 | 2264 | 0.1099 | 0.6829 | 0.7557 | 0.7175 | 0.9625 |
0.05 | 3.0 | 3396 | 0.1279 | 0.7134 | 0.7651 | 0.7383 | 0.9650 |
0.0308 | 4.0 | 4528 | 0.1512 | 0.6720 | 0.7885 | 0.7256 | 0.9611 |
0.0201 | 5.0 | 5660 | 0.1643 | 0.7254 | 0.7810 | 0.7521 | 0.9667 |
0.0128 | 6.0 | 6792 | 0.1798 | 0.7139 | 0.7832 | 0.7470 | 0.9656 |
0.0095 | 7.0 | 7924 | 0.1820 | 0.7209 | 0.7813 | 0.7499 | 0.9659 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3