metadata
license: cc-by-sa-4.0
tags:
- generated_from_trainer
datasets:
- lex_glue
model-index:
- name: ECHR_test_2
results: []
ECHR_test_2
This model is a fine-tuned version of nlpaueb/legal-bert-base-uncased on the lex_glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.2263
- Macro-f1: 0.3868
- Micro-f1: 0.5469
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: 0.0001
- 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: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Macro-f1 | Micro-f1 |
|---|---|---|---|---|---|
| 0.2058 | 0.44 | 500 | 0.2743 | 0.3073 | 0.4578 |
| 0.1583 | 0.89 | 1000 | 0.2576 | 0.3335 | 0.5014 |
| 0.1602 | 1.33 | 1500 | 0.2343 | 0.3632 | 0.5341 |
| 0.1474 | 1.78 | 2000 | 0.2263 | 0.3868 | 0.5469 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1