|
--- |
|
license: cc-by-sa-4.0 |
|
tags: |
|
- generated_from_trainer |
|
base_model: nlpaueb/legal-bert-base-uncased |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
model-index: |
|
- name: legal-bert-base-uncased |
|
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. --> |
|
|
|
# legal-bert-base-uncased |
|
|
|
This model is a fine-tuned version of [nlpaueb/legal-bert-base-uncased](https://huggingface.co/nlpaueb/legal-bert-base-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.2564 |
|
- Accuracy: 0.8273 |
|
- Precision: 0.8292 |
|
- Recall: 0.8273 |
|
- Precision Macro: 0.7794 |
|
- Recall Macro: 0.7759 |
|
- Macro Fpr: 0.0153 |
|
- Weighted Fpr: 0.0147 |
|
- Weighted Specificity: 0.9772 |
|
- Macro Specificity: 0.9870 |
|
- Weighted Sensitivity: 0.8273 |
|
- Macro Sensitivity: 0.7759 |
|
- F1 Micro: 0.8273 |
|
- F1 Macro: 0.7741 |
|
- F1 Weighted: 0.8269 |
|
|
|
## 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: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | Precision Macro | Recall Macro | Macro Fpr | Weighted Fpr | Weighted Specificity | Macro Specificity | Weighted Sensitivity | Macro Sensitivity | F1 Micro | F1 Macro | F1 Weighted | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:---------------:|:------------:|:---------:|:------------:|:--------------------:|:-----------------:|:--------------------:|:-----------------:|:--------:|:--------:|:-----------:| |
|
| 1.2105 | 1.0 | 643 | 0.7916 | 0.7761 | 0.7729 | 0.7761 | 0.6230 | 0.5920 | 0.0214 | 0.0202 | 0.9664 | 0.9828 | 0.7761 | 0.5920 | 0.7761 | 0.5703 | 0.7551 | |
|
| 0.6521 | 2.0 | 1286 | 0.6834 | 0.8025 | 0.8067 | 0.8025 | 0.7779 | 0.7152 | 0.0180 | 0.0173 | 0.9721 | 0.9850 | 0.8025 | 0.7152 | 0.8025 | 0.7181 | 0.7983 | |
|
| 0.513 | 3.0 | 1929 | 0.8107 | 0.8141 | 0.8142 | 0.8141 | 0.7859 | 0.7227 | 0.0168 | 0.0160 | 0.9740 | 0.9859 | 0.8141 | 0.7227 | 0.8141 | 0.7261 | 0.8083 | |
|
| 0.2635 | 4.0 | 2572 | 0.8442 | 0.8249 | 0.8285 | 0.8249 | 0.8298 | 0.7733 | 0.0156 | 0.0149 | 0.9759 | 0.9867 | 0.8249 | 0.7733 | 0.8249 | 0.7812 | 0.8242 | |
|
| 0.1821 | 5.0 | 3215 | 0.9549 | 0.8226 | 0.8287 | 0.8226 | 0.8135 | 0.7623 | 0.0157 | 0.0152 | 0.9766 | 0.9866 | 0.8226 | 0.7623 | 0.8226 | 0.7758 | 0.8233 | |
|
| 0.1123 | 6.0 | 3858 | 1.0790 | 0.8273 | 0.8316 | 0.8273 | 0.7865 | 0.7758 | 0.0152 | 0.0147 | 0.9779 | 0.9870 | 0.8273 | 0.7758 | 0.8273 | 0.7671 | 0.8268 | |
|
| 0.0465 | 7.0 | 4501 | 1.1538 | 0.8280 | 0.8324 | 0.8280 | 0.7857 | 0.8054 | 0.0152 | 0.0146 | 0.9780 | 0.9871 | 0.8280 | 0.8054 | 0.8280 | 0.7890 | 0.8285 | |
|
| 0.0256 | 8.0 | 5144 | 1.2413 | 0.8180 | 0.8263 | 0.8180 | 0.7780 | 0.8012 | 0.0162 | 0.0156 | 0.9771 | 0.9863 | 0.8180 | 0.8012 | 0.8180 | 0.7792 | 0.8196 | |
|
| 0.0166 | 9.0 | 5787 | 1.2510 | 0.8218 | 0.8222 | 0.8218 | 0.7782 | 0.7600 | 0.0159 | 0.0152 | 0.9755 | 0.9865 | 0.8218 | 0.7600 | 0.8218 | 0.7660 | 0.8210 | |
|
| 0.0107 | 10.0 | 6430 | 1.2564 | 0.8273 | 0.8292 | 0.8273 | 0.7794 | 0.7759 | 0.0153 | 0.0147 | 0.9772 | 0.9870 | 0.8273 | 0.7759 | 0.8273 | 0.7741 | 0.8269 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.15.2 |
|
|
