|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: bert-base-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: bertNer-biobert |
|
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. --> |
|
|
|
# bertNer-biobert |
|
|
|
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1284 |
|
- Precision: 0.9471 |
|
- Recall: 0.9630 |
|
- F1: 0.9550 |
|
- Accuracy: 0.9758 |
|
|
|
## 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: 2e-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: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.1851 | 1.0 | 1224 | 0.1186 | 0.9202 | 0.9550 | 0.9373 | 0.9670 | |
|
| 0.1188 | 2.0 | 2448 | 0.1061 | 0.9349 | 0.9684 | 0.9514 | 0.9737 | |
|
| 0.0789 | 3.0 | 3672 | 0.1051 | 0.9381 | 0.9710 | 0.9543 | 0.9755 | |
|
| 0.0569 | 4.0 | 4896 | 0.1062 | 0.9403 | 0.9712 | 0.9555 | 0.9761 | |
|
| 0.0492 | 5.0 | 6120 | 0.1174 | 0.9403 | 0.9646 | 0.9523 | 0.9734 | |
|
| 0.0405 | 6.0 | 7344 | 0.1220 | 0.9426 | 0.9638 | 0.9531 | 0.9739 | |
|
| 0.0355 | 7.0 | 8568 | 0.1175 | 0.9446 | 0.9651 | 0.9548 | 0.9756 | |
|
| 0.0296 | 8.0 | 9792 | 0.1239 | 0.9446 | 0.9660 | 0.9552 | 0.9757 | |
|
| 0.0224 | 9.0 | 11016 | 0.1247 | 0.9474 | 0.9640 | 0.9556 | 0.9760 | |
|
| 0.0219 | 10.0 | 12240 | 0.1284 | 0.9471 | 0.9630 | 0.9550 | 0.9758 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.1 |
|
- Pytorch 2.4.0 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.20.0 |
|
|
