|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: Yepes_5e-05_0404_ES6 |
|
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. --> |
|
|
|
# Yepes_5e-05_0404_ES6 |
|
|
|
This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0941 |
|
- Precision: 0.6541 |
|
- Recall: 0.5210 |
|
- F1: 0.5800 |
|
- Accuracy: 0.9813 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- training_steps: 2000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.5973 | 0.43 | 25 | 0.1959 | 0.0 | 0.0 | 0.0 | 0.9705 | |
|
| 0.1831 | 0.86 | 50 | 0.1374 | 0.0 | 0.0 | 0.0 | 0.9705 | |
|
| 0.1271 | 1.29 | 75 | 0.1182 | 0.2786 | 0.1677 | 0.2093 | 0.9735 | |
|
| 0.13 | 1.72 | 100 | 0.1116 | 0.4057 | 0.2964 | 0.3426 | 0.9772 | |
|
| 0.1008 | 2.16 | 125 | 0.1013 | 0.4491 | 0.2904 | 0.3527 | 0.9781 | |
|
| 0.0807 | 2.59 | 150 | 0.0992 | 0.4214 | 0.3533 | 0.3844 | 0.9775 | |
|
| 0.0893 | 3.02 | 175 | 0.0855 | 0.4937 | 0.3503 | 0.4098 | 0.9789 | |
|
| 0.0656 | 3.45 | 200 | 0.0978 | 0.5509 | 0.3563 | 0.4327 | 0.9803 | |
|
| 0.0723 | 3.88 | 225 | 0.0816 | 0.4925 | 0.3922 | 0.4367 | 0.9798 | |
|
| 0.0683 | 4.31 | 250 | 0.0789 | 0.6389 | 0.4132 | 0.5018 | 0.9815 | |
|
| 0.0518 | 4.74 | 275 | 0.0838 | 0.5639 | 0.3832 | 0.4563 | 0.9797 | |
|
| 0.0534 | 5.17 | 300 | 0.0853 | 0.7129 | 0.4461 | 0.5488 | 0.9817 | |
|
| 0.0489 | 5.6 | 325 | 0.0824 | 0.6239 | 0.4222 | 0.5036 | 0.9814 | |
|
| 0.0442 | 6.03 | 350 | 0.0751 | 0.5789 | 0.4940 | 0.5331 | 0.9799 | |
|
| 0.0353 | 6.47 | 375 | 0.1195 | 0.6812 | 0.4222 | 0.5213 | 0.9803 | |
|
| 0.0401 | 6.9 | 400 | 0.0875 | 0.5339 | 0.5419 | 0.5379 | 0.9767 | |
|
| 0.0341 | 7.33 | 425 | 0.0994 | 0.6693 | 0.5090 | 0.5782 | 0.9815 | |
|
| 0.0266 | 7.76 | 450 | 0.0951 | 0.6693 | 0.5150 | 0.5821 | 0.9815 | |
|
| 0.0234 | 8.19 | 475 | 0.0979 | 0.6824 | 0.4760 | 0.5608 | 0.9817 | |
|
| 0.0224 | 8.62 | 500 | 0.0941 | 0.6541 | 0.5210 | 0.5800 | 0.9813 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.4 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.2 |
|
|
