|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
base_model: law-ai/InLegalBERT |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
model-index: |
|
- name: InLegalBERT |
|
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. --> |
|
|
|
# InLegalBERT |
|
|
|
This model is a fine-tuned version of [law-ai/InLegalBERT](https://huggingface.co/law-ai/InLegalBERT) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.5527 |
|
- Accuracy: 0.7591 |
|
- Precision: 0.7598 |
|
- Recall: 0.7591 |
|
- Precision Macro: 0.6792 |
|
- Recall Macro: 0.6780 |
|
- Macro Fpr: 0.0228 |
|
- Weighted Fpr: 0.0222 |
|
- Weighted Specificity: 0.9703 |
|
- Macro Specificity: 0.9820 |
|
- Weighted Sensitivity: 0.7591 |
|
- Macro Sensitivity: 0.6780 |
|
- F1 Micro: 0.7591 |
|
- F1 Macro: 0.6756 |
|
- F1 Weighted: 0.7583 |
|
|
|
## 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 |
|
|
|
### 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:---------------:|:------------:|:---------:|:------------:|:--------------------:|:-----------------:|:--------------------:|:-----------------:|:--------:|:--------:|:-----------:| |
|
| 1.9079 | 1.0 | 643 | 1.2971 | 0.5732 | 0.5257 | 0.5732 | 0.3206 | 0.3555 | 0.0535 | 0.0505 | 0.9314 | 0.9670 | 0.5732 | 0.3555 | 0.5732 | 0.3189 | 0.5343 | |
|
| 1.2081 | 2.0 | 1286 | 0.9146 | 0.7103 | 0.7163 | 0.7103 | 0.6091 | 0.5215 | 0.0287 | 0.0283 | 0.9651 | 0.9784 | 0.7103 | 0.5215 | 0.7103 | 0.5206 | 0.7070 | |
|
| 0.9303 | 3.0 | 1929 | 0.8692 | 0.7405 | 0.7472 | 0.7405 | 0.6654 | 0.5940 | 0.0248 | 0.0244 | 0.9679 | 0.9806 | 0.7405 | 0.5940 | 0.7405 | 0.5993 | 0.7362 | |
|
| 0.4996 | 4.0 | 2572 | 1.1656 | 0.7033 | 0.7270 | 0.7033 | 0.6366 | 0.6241 | 0.0297 | 0.0292 | 0.9651 | 0.9779 | 0.7033 | 0.6241 | 0.7033 | 0.6125 | 0.6959 | |
|
| 0.3592 | 5.0 | 3215 | 1.0837 | 0.7459 | 0.7535 | 0.7459 | 0.6627 | 0.6131 | 0.0241 | 0.0238 | 0.9668 | 0.9808 | 0.7459 | 0.6131 | 0.7459 | 0.6261 | 0.7447 | |
|
| 0.2809 | 6.0 | 3858 | 1.2175 | 0.7545 | 0.7607 | 0.7545 | 0.6758 | 0.6585 | 0.0232 | 0.0227 | 0.9695 | 0.9816 | 0.7545 | 0.6585 | 0.7545 | 0.6599 | 0.7531 | |
|
| 0.1664 | 7.0 | 4501 | 1.3113 | 0.7637 | 0.7645 | 0.7637 | 0.6855 | 0.6886 | 0.0221 | 0.0216 | 0.9717 | 0.9824 | 0.7637 | 0.6886 | 0.7637 | 0.6841 | 0.7631 | |
|
| 0.0733 | 8.0 | 5144 | 1.4751 | 0.7552 | 0.7610 | 0.7552 | 0.6835 | 0.6990 | 0.0231 | 0.0226 | 0.9697 | 0.9817 | 0.7552 | 0.6990 | 0.7552 | 0.6871 | 0.7566 | |
|
| 0.0716 | 9.0 | 5787 | 1.5509 | 0.7637 | 0.7605 | 0.7637 | 0.7018 | 0.7035 | 0.0224 | 0.0216 | 0.9690 | 0.9822 | 0.7637 | 0.7035 | 0.7637 | 0.7006 | 0.7609 | |
|
| 0.0286 | 10.0 | 6430 | 1.5527 | 0.7591 | 0.7598 | 0.7591 | 0.6792 | 0.6780 | 0.0228 | 0.0222 | 0.9703 | 0.9820 | 0.7591 | 0.6780 | 0.7591 | 0.6756 | 0.7583 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.15.2 |
|
|
