|
--- |
|
license: apache-2.0 |
|
base_model: bert-base-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- recall |
|
- precision |
|
model-index: |
|
- name: biobert-biocause-trainer-oversample |
|
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. --> |
|
|
|
# biobert-biocause-trainer-oversample |
|
|
|
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7149 |
|
- Accuracy: 0.8457 |
|
- F1: 0.6735 |
|
- Recall: 0.6226 |
|
- Precision: 0.7333 |
|
|
|
## 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: 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: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:| |
|
| 0.5227 | 0.07 | 25 | 0.5550 | 0.7765 | 0.2320 | 0.1321 | 0.9545 | |
|
| 0.6695 | 0.14 | 50 | 0.5736 | 0.7315 | 0.5640 | 0.6792 | 0.4821 | |
|
| 0.5501 | 0.22 | 75 | 0.5333 | 0.7621 | 0.5595 | 0.5912 | 0.5311 | |
|
| 0.5193 | 0.29 | 100 | 0.4489 | 0.8119 | 0.48 | 0.3396 | 0.8182 | |
|
| 0.5462 | 0.36 | 125 | 0.3952 | 0.8392 | 0.6269 | 0.5283 | 0.7706 | |
|
| 0.4863 | 0.43 | 150 | 0.4829 | 0.8232 | 0.6541 | 0.6541 | 0.6541 | |
|
| 0.4607 | 0.5 | 175 | 0.4429 | 0.8360 | 0.5641 | 0.4151 | 0.88 | |
|
| 0.4302 | 0.58 | 200 | 0.4701 | 0.8103 | 0.6529 | 0.6981 | 0.6133 | |
|
| 0.3965 | 0.65 | 225 | 0.5427 | 0.8071 | 0.6685 | 0.7610 | 0.5961 | |
|
| 0.3838 | 0.72 | 250 | 0.4431 | 0.8296 | 0.6624 | 0.6541 | 0.6710 | |
|
| 0.4917 | 0.79 | 275 | 0.6932 | 0.7203 | 0.6027 | 0.8302 | 0.4731 | |
|
| 0.3751 | 0.86 | 300 | 0.4731 | 0.7781 | 0.6330 | 0.7484 | 0.5484 | |
|
| 0.3926 | 0.94 | 325 | 0.4237 | 0.8424 | 0.6975 | 0.7107 | 0.6848 | |
|
| 0.3654 | 1.01 | 350 | 0.3528 | 0.8521 | 0.7032 | 0.6855 | 0.7219 | |
|
| 0.2255 | 1.08 | 375 | 0.6046 | 0.8392 | 0.6835 | 0.6792 | 0.6879 | |
|
| 0.4107 | 1.15 | 400 | 0.4417 | 0.8569 | 0.6716 | 0.5723 | 0.8125 | |
|
| 0.3405 | 1.22 | 425 | 0.4378 | 0.8376 | 0.6667 | 0.6352 | 0.7014 | |
|
| 0.2532 | 1.3 | 450 | 0.5072 | 0.8264 | 0.6824 | 0.7296 | 0.6409 | |
|
| 0.2366 | 1.37 | 475 | 0.5545 | 0.8232 | 0.6667 | 0.6918 | 0.6433 | |
|
| 0.2102 | 1.44 | 500 | 0.5370 | 0.8633 | 0.6996 | 0.6226 | 0.7984 | |
|
| 0.1455 | 1.51 | 525 | 0.6646 | 0.8553 | 0.6980 | 0.6541 | 0.7482 | |
|
| 0.2918 | 1.59 | 550 | 0.6595 | 0.8296 | 0.6826 | 0.7170 | 0.6514 | |
|
| 0.2585 | 1.66 | 575 | 0.6265 | 0.8392 | 0.6753 | 0.6541 | 0.6980 | |
|
| 0.3427 | 1.73 | 600 | 0.5371 | 0.8376 | 0.6892 | 0.7044 | 0.6747 | |
|
| 0.1538 | 1.8 | 625 | 0.6054 | 0.8585 | 0.6788 | 0.5849 | 0.8087 | |
|
| 0.2565 | 1.87 | 650 | 0.5814 | 0.8601 | 0.6926 | 0.6164 | 0.7903 | |
|
| 0.255 | 1.95 | 675 | 0.5811 | 0.8489 | 0.6968 | 0.6792 | 0.7152 | |
|
| 0.2814 | 2.02 | 700 | 0.5238 | 0.8489 | 0.6846 | 0.6415 | 0.7338 | |
|
| 0.0351 | 2.09 | 725 | 0.6550 | 0.8505 | 0.7010 | 0.6855 | 0.7171 | |
|
| 0.0849 | 2.16 | 750 | 0.7147 | 0.8473 | 0.6780 | 0.6289 | 0.7353 | |
|
| 0.145 | 2.23 | 775 | 0.8233 | 0.8344 | 0.7014 | 0.7610 | 0.6505 | |
|
| 0.0889 | 2.31 | 800 | 0.7376 | 0.8505 | 0.7103 | 0.7170 | 0.7037 | |
|
| 0.0968 | 2.38 | 825 | 0.7388 | 0.8521 | 0.6783 | 0.6101 | 0.7638 | |
|
| 0.1507 | 2.45 | 850 | 0.7317 | 0.8537 | 0.6762 | 0.5975 | 0.7787 | |
|
| 0.134 | 2.52 | 875 | 0.7362 | 0.8392 | 0.6795 | 0.6667 | 0.6928 | |
|
| 0.1088 | 2.59 | 900 | 0.6987 | 0.8457 | 0.68 | 0.6415 | 0.7234 | |
|
| 0.0854 | 2.67 | 925 | 0.7236 | 0.8553 | 0.6897 | 0.6289 | 0.7634 | |
|
| 0.136 | 2.74 | 950 | 0.7118 | 0.8473 | 0.6844 | 0.6478 | 0.7254 | |
|
| 0.0571 | 2.81 | 975 | 0.7155 | 0.8473 | 0.6780 | 0.6289 | 0.7353 | |
|
| 0.1579 | 2.88 | 1000 | 0.7195 | 0.8521 | 0.6913 | 0.6478 | 0.7410 | |
|
| 0.1093 | 2.95 | 1025 | 0.7146 | 0.8473 | 0.6780 | 0.6289 | 0.7353 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.3.1 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.15.1 |
|
|
