distilbert-base-multilingual-cased-finetuned-for-contract-sections-v1
This model is a fine-tuned version of distilbert/distilbert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2293
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: 64
- eval_batch_size: 64
- 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 |
|---|---|---|---|
| 2.4985 | 1.0 | 66 | 1.8246 |
| 1.8039 | 2.0 | 132 | 1.5683 |
| 1.565 | 3.0 | 198 | 1.4441 |
| 1.4159 | 4.0 | 264 | 1.3548 |
| 1.3323 | 5.0 | 330 | 1.3140 |
| 1.2804 | 6.0 | 396 | 1.2679 |
| 1.2397 | 7.0 | 462 | 1.2465 |
| 1.1987 | 8.0 | 528 | 1.2331 |
| 1.1844 | 9.0 | 594 | 1.2200 |
| 1.1675 | 10.0 | 660 | 1.2263 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 5