|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: prueba5 |
|
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. --> |
|
|
|
# prueba5 |
|
|
|
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: 0.2442 |
|
- Precision: 0.5258 |
|
- Recall: 0.5574 |
|
- F1: 0.5411 |
|
- Accuracy: 0.9609 |
|
|
|
## 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: 2.75e-05 |
|
- train_batch_size: 16 |
|
- 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 | 57 | 0.2341 | 0.0 | 0.0 | 0.0 | 0.9488 | |
|
| No log | 2.0 | 114 | 0.2411 | 0.0 | 0.0 | 0.0 | 0.9488 | |
|
| No log | 3.0 | 171 | 0.2150 | 0.0385 | 0.0055 | 0.0096 | 0.9410 | |
|
| No log | 4.0 | 228 | 0.1885 | 0.25 | 0.0929 | 0.1355 | 0.9500 | |
|
| No log | 5.0 | 285 | 0.1730 | 0.3830 | 0.1967 | 0.2599 | 0.9524 | |
|
| No log | 6.0 | 342 | 0.1591 | 0.5098 | 0.2842 | 0.3649 | 0.9581 | |
|
| No log | 7.0 | 399 | 0.1665 | 0.5405 | 0.3279 | 0.4082 | 0.9609 | |
|
| No log | 8.0 | 456 | 0.1856 | 0.5294 | 0.4918 | 0.5099 | 0.9604 | |
|
| 0.1706 | 9.0 | 513 | 0.1727 | 0.5 | 0.5191 | 0.5094 | 0.9611 | |
|
| 0.1706 | 10.0 | 570 | 0.1717 | 0.5669 | 0.4863 | 0.5235 | 0.9639 | |
|
| 0.1706 | 11.0 | 627 | 0.1913 | 0.5024 | 0.5628 | 0.5309 | 0.9601 | |
|
| 0.1706 | 12.0 | 684 | 0.1793 | 0.515 | 0.5628 | 0.5379 | 0.9619 | |
|
| 0.1706 | 13.0 | 741 | 0.2009 | 0.5679 | 0.5027 | 0.5333 | 0.9618 | |
|
| 0.1706 | 14.0 | 798 | 0.2043 | 0.5333 | 0.5683 | 0.5503 | 0.9604 | |
|
| 0.1706 | 15.0 | 855 | 0.2052 | 0.5486 | 0.5246 | 0.5363 | 0.9629 | |
|
| 0.1706 | 16.0 | 912 | 0.2234 | 0.5183 | 0.5410 | 0.5294 | 0.9581 | |
|
| 0.1706 | 17.0 | 969 | 0.2157 | 0.5424 | 0.5246 | 0.5333 | 0.9616 | |
|
| 0.0202 | 18.0 | 1026 | 0.2207 | 0.5025 | 0.5574 | 0.5285 | 0.9596 | |
|
| 0.0202 | 19.0 | 1083 | 0.2297 | 0.5025 | 0.5410 | 0.5211 | 0.9573 | |
|
| 0.0202 | 20.0 | 1140 | 0.2264 | 0.5131 | 0.5355 | 0.5241 | 0.9593 | |
|
| 0.0202 | 21.0 | 1197 | 0.2300 | 0.5181 | 0.5464 | 0.5319 | 0.9593 | |
|
| 0.0202 | 22.0 | 1254 | 0.2348 | 0.5241 | 0.5355 | 0.5297 | 0.9604 | |
|
| 0.0202 | 23.0 | 1311 | 0.2372 | 0.5196 | 0.5792 | 0.5478 | 0.9588 | |
|
| 0.0202 | 24.0 | 1368 | 0.2349 | 0.5319 | 0.5464 | 0.5391 | 0.9613 | |
|
| 0.0202 | 25.0 | 1425 | 0.2353 | 0.5312 | 0.5574 | 0.544 | 0.9619 | |
|
| 0.0202 | 26.0 | 1482 | 0.2388 | 0.5489 | 0.5519 | 0.5504 | 0.9614 | |
|
| 0.0044 | 27.0 | 1539 | 0.2396 | 0.5243 | 0.5301 | 0.5272 | 0.9618 | |
|
| 0.0044 | 28.0 | 1596 | 0.2442 | 0.5152 | 0.5574 | 0.5354 | 0.9603 | |
|
| 0.0044 | 29.0 | 1653 | 0.2444 | 0.5178 | 0.5574 | 0.5368 | 0.9604 | |
|
| 0.0044 | 30.0 | 1710 | 0.2442 | 0.5258 | 0.5574 | 0.5411 | 0.9609 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.4 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.2 |
|
|
