<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
consejo-textcat
This model is a fine-tuned version of dccuchile/distilbert-base-spanish-uncased on the Consejo dataset. It achieves the following results on the evaluation set:
- Loss: 0.1062
- Accuracy: 0.9851
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: 2e-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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 38 | 1.1395 | 0.5672 |
| No log | 2.0 | 76 | 0.6276 | 0.8358 |
| No log | 3.0 | 114 | 0.3375 | 0.9552 |
| No log | 4.0 | 152 | 0.1894 | 0.9851 |
| No log | 5.0 | 190 | 0.1331 | 0.9851 |
| No log | 6.0 | 228 | 0.1223 | 0.9851 |
| No log | 7.0 | 266 | 0.1104 | 0.9851 |
| No log | 8.0 | 304 | 0.1079 | 0.9851 |
| No log | 9.0 | 342 | 0.1064 | 0.9851 |
| No log | 10.0 | 380 | 0.1062 | 0.9851 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
