|
--- |
|
license: cc-by-sa-4.0 |
|
base_model: nlpaueb/bert-base-uncased-contracts |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: clause_model_nov14 |
|
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. --> |
|
|
|
# clause_model_nov14 |
|
|
|
This model is a fine-tuned version of [nlpaueb/bert-base-uncased-contracts](https://huggingface.co/nlpaueb/bert-base-uncased-contracts) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0520 |
|
- Accuracy: 0.9917 |
|
|
|
## 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 |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
| 1.5312 | 1.0 | 1179 | 0.8775 | 0.795 | |
|
| 0.6044 | 2.0 | 2358 | 0.3375 | 0.9192 | |
|
| 0.2778 | 3.0 | 3537 | 0.1704 | 0.9625 | |
|
| 0.162 | 4.0 | 4716 | 0.1016 | 0.9792 | |
|
| 0.121 | 5.0 | 5895 | 0.0791 | 0.9842 | |
|
| 0.0748 | 6.0 | 7074 | 0.0596 | 0.9875 | |
|
| 0.0705 | 7.0 | 8253 | 0.0618 | 0.9917 | |
|
| 0.052 | 8.0 | 9432 | 0.0622 | 0.9908 | |
|
| 0.0299 | 9.0 | 10611 | 0.0505 | 0.9917 | |
|
| 0.031 | 10.0 | 11790 | 0.0520 | 0.9917 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.0 |
|
- Pytorch 2.5.1+cu121 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.19.1 |
|
|
