metadata
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: []
clause_model_nov14
This model is a fine-tuned version of nlpaueb/bert-base-uncased-contracts on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9001
- Accuracy: 0.8546
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 |
|---|---|---|---|---|
| 1.3476 | 1.0 | 1269 | 0.8415 | 0.8147 |
| 0.5667 | 2.0 | 2538 | 0.6364 | 0.8466 |
| 0.3336 | 3.0 | 3807 | 0.6719 | 0.8537 |
| 0.2592 | 4.0 | 5076 | 0.6984 | 0.8582 |
| 0.1558 | 5.0 | 6345 | 0.7896 | 0.8466 |
| 0.1148 | 6.0 | 7614 | 0.8543 | 0.8493 |
| 0.0722 | 7.0 | 8883 | 0.8264 | 0.8626 |
| 0.0716 | 8.0 | 10152 | 0.9042 | 0.8520 |
| 0.0589 | 9.0 | 11421 | 0.8841 | 0.8564 |
| 0.0349 | 10.0 | 12690 | 0.9001 | 0.8546 |
Framework versions
- Transformers 4.42.0
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1