e_care_albert_base_finetuned
This model is a fine-tuned version of albert/albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4498
- F1: 0.7290
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.552 | 1.0 | 933 | 0.5073 | 0.7380 |
| 0.392 | 2.0 | 1866 | 0.5267 | 0.7455 |
| 0.2009 | 3.0 | 2799 | 0.7612 | 0.7446 |
| 0.0715 | 4.0 | 3732 | 1.0338 | 0.7479 |
| 0.0243 | 5.0 | 4665 | 1.2592 | 0.7328 |
| 0.0079 | 6.0 | 5598 | 1.4134 | 0.7347 |
| 0.0035 | 7.0 | 6531 | 1.4498 | 0.7290 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1