|
--- |
|
license: cc-by-sa-4.0 |
|
base_model: lexlms/legal-roberta-large |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
model-index: |
|
- name: legal-roberta-large |
|
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-roberta-large |
|
|
|
This model is a fine-tuned version of [lexlms/legal-roberta-large](https://huggingface.co/lexlms/legal-roberta-large) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0297 |
|
- F1: 0.4489 |
|
|
|
## 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-06 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 100 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 30 |
|
- num_epochs: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 0.2471 | 0.96 | 18 | 0.8701 | 0.4711 | |
|
| 0.1889 | 1.97 | 37 | 0.9103 | 0.4562 | |
|
| 0.1444 | 2.99 | 56 | 0.9706 | 0.4489 | |
|
| 0.1283 | 4.0 | 75 | 1.0204 | 0.4562 | |
|
| 0.1411 | 4.8 | 90 | 1.0297 | 0.4489 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
