metadata
license: cc-by-sa-4.0
tags:
- generated_from_trainer
base_model: nlpaueb/legal-bert-base-uncased
metrics:
- accuracy
model-index:
- name: legal-bert-base-uncased-5-epochs-fine-tune
results: []
legal-bert-base-uncased-5-epochs-fine-tune
This model is a fine-tuned version of nlpaueb/legal-bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8581
- Accuracy: 1
- F1 Micro: 1
- F1 Macro: 1
- F1 Weighted: 1
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Micro | F1 Macro | F1 Weighted |
|---|---|---|---|---|---|---|---|
| 1.348 | 1.0 | 643 | 0.6934 | 1 | 1 | 1 | 1 |
| 0.6471 | 2.0 | 1286 | 0.6506 | 1 | 1 | 1 | 1 |
| 0.4944 | 3.0 | 1929 | 0.7049 | 1 | 1 | 1 | 1 |
| 0.2113 | 4.0 | 2572 | 0.8336 | 1 | 1 | 1 | 1 |
| 0.1352 | 5.0 | 3215 | 0.8581 | 1 | 1 | 1 | 1 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2