lexglue-unfair-tos
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0314
- Macro-f1: 0.7675
- Micro-f1: 0.9531
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 1
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Macro-f1 | Micro-f1 |
|---|---|---|---|---|---|
| 0.0994 | 1.0 | 692 | 0.0443 | 0.4100 | 0.9246 |
| 0.0453 | 2.0 | 1384 | 0.0281 | 0.5823 | 0.9384 |
| 0.0205 | 3.0 | 2076 | 0.0253 | 0.7639 | 0.9474 |
| 0.0133 | 4.0 | 2768 | 0.0265 | 0.7521 | 0.9462 |
| 0.0092 | 5.0 | 3460 | 0.0280 | 0.7430 | 0.9401 |
| 0.0062 | 6.0 | 4152 | 0.0278 | 0.7611 | 0.9488 |
| 0.0049 | 7.0 | 4844 | 0.0292 | 0.7492 | 0.9431 |
| 0.0032 | 8.0 | 5536 | 0.0314 | 0.7675 | 0.9531 |
| 0.0025 | 9.0 | 6228 | 0.0316 | 0.7549 | 0.9498 |
| 0.0022 | 10.0 | 6920 | 0.0347 | 0.7404 | 0.9481 |
| 0.0016 | 11.0 | 7612 | 0.0333 | 0.7628 | 0.9514 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.1.2+cu121
- Datasets 3.0.2
- Tokenizers 0.19.1