|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: Yepes_5e-05_0404_ES6_strict_tok |
|
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_strict_tok |
|
|
|
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: 0.0986 |
|
- Precision: 0.7635 |
|
- Recall: 0.4641 |
|
- F1: 0.5773 |
|
- Accuracy: 0.9811 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.6203 | 0.43 | 25 | 0.2206 | 0.0 | 0.0 | 0.0 | 0.9663 | |
|
| 0.2394 | 0.86 | 50 | 0.1770 | 0.0 | 0.0 | 0.0 | 0.9663 | |
|
| 0.1771 | 1.29 | 75 | 0.1435 | 0.0 | 0.0 | 0.0 | 0.9663 | |
|
| 0.1761 | 1.72 | 100 | 0.1277 | 0.2656 | 0.2036 | 0.2305 | 0.9722 | |
|
| 0.1386 | 2.16 | 125 | 0.1152 | 0.4471 | 0.2275 | 0.3016 | 0.9742 | |
|
| 0.1227 | 2.59 | 150 | 0.1401 | 0.3871 | 0.3234 | 0.3524 | 0.9623 | |
|
| 0.1188 | 3.02 | 175 | 0.0922 | 0.6331 | 0.3204 | 0.4254 | 0.9778 | |
|
| 0.0897 | 3.45 | 200 | 0.1012 | 0.6416 | 0.3323 | 0.4379 | 0.9773 | |
|
| 0.099 | 3.88 | 225 | 0.0885 | 0.5671 | 0.3922 | 0.4637 | 0.9780 | |
|
| 0.1172 | 4.31 | 250 | 0.0858 | 0.5938 | 0.4551 | 0.5153 | 0.9761 | |
|
| 0.0693 | 4.74 | 275 | 0.0899 | 0.8072 | 0.4012 | 0.536 | 0.9785 | |
|
| 0.0686 | 5.17 | 300 | 0.0986 | 0.7635 | 0.4641 | 0.5773 | 0.9811 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.4 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |
|
|
