ajuste_fino_modelo_hugging_face_v1
This model is a fine-tuned version of google-bert/bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.5848
- Accuracy: 0.5698
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1704 | 1.0 | 625 | 1.0946 | 0.525 |
| 0.9192 | 2.0 | 1250 | 1.0280 | 0.5588 |
| 0.7161 | 3.0 | 1875 | 1.1614 | 0.573 |
| 0.4003 | 4.0 | 2500 | 1.5113 | 0.5698 |
| 0.2678 | 5.0 | 3125 | 2.3124 | 0.556 |
| 0.2277 | 6.0 | 3750 | 2.7098 | 0.5722 |
| 0.1286 | 7.0 | 4375 | 3.2215 | 0.5642 |
| 0.0402 | 8.0 | 5000 | 3.4412 | 0.57 |
| 0.0212 | 9.0 | 5625 | 3.5369 | 0.576 |
| 0.015 | 10.0 | 6250 | 3.5848 | 0.5698 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1