|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: ner-2 |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# ner-2 |
|
|
|
This model is a fine-tuned version of [PlanTL-GOB-ES/bsc-bio-ehr-es-pharmaconer](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es-pharmaconer) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1791 |
|
- Precision: 0.5224 |
|
- Recall: 0.6222 |
|
- F1: 0.5680 |
|
- Accuracy: 0.9631 |
|
|
|
## 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: 7e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 30 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 29 | 0.2584 | 0.0 | 0.0 | 0.0 | 0.9365 | |
|
| No log | 2.0 | 58 | 0.2386 | 0.1364 | 0.0133 | 0.0243 | 0.9458 | |
|
| No log | 3.0 | 87 | 0.2312 | 0.2368 | 0.04 | 0.0684 | 0.9466 | |
|
| No log | 4.0 | 116 | 0.1806 | 0.2809 | 0.2222 | 0.2481 | 0.9422 | |
|
| No log | 5.0 | 145 | 0.1446 | 0.4453 | 0.2711 | 0.3370 | 0.9558 | |
|
| No log | 6.0 | 174 | 0.1575 | 0.3778 | 0.3022 | 0.3358 | 0.9493 | |
|
| No log | 7.0 | 203 | 0.1255 | 0.5081 | 0.4178 | 0.4585 | 0.9601 | |
|
| No log | 8.0 | 232 | 0.1290 | 0.4599 | 0.4844 | 0.4719 | 0.9596 | |
|
| No log | 9.0 | 261 | 0.1383 | 0.4844 | 0.4844 | 0.4844 | 0.9597 | |
|
| No log | 10.0 | 290 | 0.1534 | 0.4313 | 0.6133 | 0.5064 | 0.9519 | |
|
| No log | 11.0 | 319 | 0.1575 | 0.4423 | 0.6133 | 0.5140 | 0.9560 | |
|
| No log | 12.0 | 348 | 0.1437 | 0.5888 | 0.5156 | 0.5498 | 0.9670 | |
|
| No log | 13.0 | 377 | 0.1605 | 0.5 | 0.5911 | 0.5418 | 0.9589 | |
|
| No log | 14.0 | 406 | 0.1529 | 0.5459 | 0.5289 | 0.5372 | 0.9640 | |
|
| No log | 15.0 | 435 | 0.1569 | 0.5097 | 0.5867 | 0.5455 | 0.9618 | |
|
| No log | 16.0 | 464 | 0.1656 | 0.4980 | 0.5644 | 0.5292 | 0.9607 | |
|
| No log | 17.0 | 493 | 0.1602 | 0.5583 | 0.5956 | 0.5763 | 0.9622 | |
|
| 0.0843 | 18.0 | 522 | 0.1767 | 0.4897 | 0.6356 | 0.5532 | 0.9589 | |
|
| 0.0843 | 19.0 | 551 | 0.1642 | 0.5551 | 0.6044 | 0.5787 | 0.9641 | |
|
| 0.0843 | 20.0 | 580 | 0.1635 | 0.6418 | 0.5733 | 0.6056 | 0.9679 | |
|
| 0.0843 | 21.0 | 609 | 0.1706 | 0.5423 | 0.6267 | 0.5814 | 0.9635 | |
|
| 0.0843 | 22.0 | 638 | 0.1691 | 0.5437 | 0.6089 | 0.5744 | 0.9638 | |
|
| 0.0843 | 23.0 | 667 | 0.1743 | 0.5357 | 0.6 | 0.5660 | 0.9631 | |
|
| 0.0843 | 24.0 | 696 | 0.1800 | 0.5176 | 0.6533 | 0.5776 | 0.9627 | |
|
| 0.0843 | 25.0 | 725 | 0.1789 | 0.5 | 0.6 | 0.5455 | 0.9620 | |
|
| 0.0843 | 26.0 | 754 | 0.1754 | 0.5388 | 0.5867 | 0.5617 | 0.9638 | |
|
| 0.0843 | 27.0 | 783 | 0.1797 | 0.5164 | 0.6311 | 0.5680 | 0.9627 | |
|
| 0.0843 | 28.0 | 812 | 0.1816 | 0.5321 | 0.6267 | 0.5755 | 0.9633 | |
|
| 0.0843 | 29.0 | 841 | 0.1793 | 0.5222 | 0.6267 | 0.5697 | 0.9631 | |
|
| 0.0843 | 30.0 | 870 | 0.1791 | 0.5224 | 0.6222 | 0.5680 | 0.9631 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |
|
|
