|
--- |
|
base_model: bert-base-cased |
|
license: apache-2.0 |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: bert-finetuned-ner4 |
|
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. --> |
|
|
|
# bert-finetuned-ner4 |
|
|
|
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: 0.0913 |
|
- Precision: 0.8712 |
|
- Recall: 0.8979 |
|
- F1: 0.8844 |
|
- Accuracy: 0.9850 |
|
|
|
## 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: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.0612 | 1.0 | 2489 | 0.0625 | 0.8264 | 0.8552 | 0.8405 | 0.9816 | |
|
| 0.0351 | 2.0 | 4978 | 0.0643 | 0.8474 | 0.8716 | 0.8594 | 0.9831 | |
|
| 0.0189 | 3.0 | 7467 | 0.0651 | 0.8585 | 0.8995 | 0.8785 | 0.9843 | |
|
| 0.0105 | 4.0 | 9956 | 0.0811 | 0.8690 | 0.8943 | 0.8815 | 0.9847 | |
|
| 0.0047 | 5.0 | 12445 | 0.0913 | 0.8712 | 0.8979 | 0.8844 | 0.9850 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
